<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (cshalizi)</title>
    <link>https://pinboard.in/u:cshalizi/public/</link>
    <description>recent bookmarks from cshalizi</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://psycnet.apa.org/doiLanding?doi=10.1037%2Fmet0000764"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2211.15934"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2512.00175"/>
	<rdf:li rdf:resource="https://www.aeaweb.org/articles?id=10.1257/aer.20211811"/>
	<rdf:li rdf:resource="https://www.degruyterbrill.com/document/doi/10.1515/jci-2024-0002/html"/>
	<rdf:li rdf:resource="https://www.cambridge.org/core/journals/philosophy-of-science/article/causal-direction-in-causal-bayes-nets/7CEA494FFE2E054D6EBB26C442B218DB?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Articles"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2411.10908"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.06469"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2504.08324"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2503.19873"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2503.20769"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2503.07811"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.01637"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2306.16591"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w32273"/>
	<rdf:li rdf:resource="https://www.nowpublishers.com/article/Details/HPE-0078"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2305.04116"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2410.03514"/>
	<rdf:li rdf:resource="https://www.cambridge.org/core/journals/american-political-science-review/article/abs/how-to-make-causal-inferences-with-timeseries-crosssectional-data-under-selection-on-observables/498BE04E5AF9802EC4D33DD7A4016584"/>
	<rdf:li rdf:resource="https://web.stanford.edu/~swager/causal_inf_book.pdf"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w32822"/>
	<rdf:li rdf:resource="https://academic.oup.com/qje/article-abstract/139/2/891/7473710"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w32342"/>
	<rdf:li rdf:resource="https://www.cambridge.org/core/journals/british-journal-of-political-science/article/unequal-and-unsupportive-exposure-to-poor-people-weakens-support-for-redistribution-among-the-rich/FC32FA59B3C5525A178C7012859F95D8"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.14959"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.14979"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.15502"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/1745-9125.12353#crim12353-supitem-0001"/>
	<rdf:li rdf:resource="https://nowpublishers.com/article/Details/MAL-106"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.14777"/>
	<rdf:li rdf:resource="https://direct.mit.edu/rest/article-abstract/doi/10.1162/rest_a_01323/115634/Flight-from-Urban-Blight-Lead-Poisoning-Crime-and?redirectedFrom=fulltext"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2309.03969"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2310.16626"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2103.01802"/>
	<rdf:li rdf:resource="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0286067"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2304.07896"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2302.05380"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/abs/10.1080/01621459.2021.1941053"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2210.11021"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-soc-030320-102100"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.08353"/>
	<rdf:li rdf:resource="https://jmlr.org/papers/v23/21-0082.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2108.09265"/>
	<rdf:li rdf:resource="https://www.aeaweb.org/articles?id=10.1257/aer.101.3.532"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA10582?casa_token=RYQGxAm5NPsAAAAA:Gjw9Whp2sT1TTcF-EurC9U-K98m8jQ6Z1Tl6-PTOVvOZYU9vgik8XniEBql7ru0bqZ7U8aepTqF3"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.11603"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2204.04119"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.00416"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.01249"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-criminol-030920-112506"/>
	<rdf:li rdf:resource="https://academic.oup.com/biomet/article-abstract/109/2/551/6308304?redirectedFrom=fulltext"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/full/10.1080/10618600.2022.2071905"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2201.07055"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2205.01593"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w29691"/>
	<rdf:li rdf:resource="https://research.google/pubs/pub49197/"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w29820"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2201.13451"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w29709"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-051120-111443"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.04103"/>
	<rdf:li rdf:resource="https://www.jstor.org/stable/20684590?seq=1#metadata_info_tab_contents"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2110.03973"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2109.13471"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2109.15154"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2109.00725"/>
	<rdf:li rdf:resource="https://dl.acm.org/doi/abs/10.1145/3447548.3470795"/>
	<rdf:li rdf:resource="https://www.aeaweb.org/articles?id=10.1257/aer.20200513"/>
	<rdf:li rdf:resource="https://www.aeaweb.org/articles?id=10.1257/aer.20190415"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-032015-010015"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://psycnet.apa.org/doiLanding?doi=10.1037%2Fmet0000764">
    <title>Estimating causal effects on psychological networks using item response theory.</title>
    <dc:date>2025-12-18T04:11:31+00:00</dc:date>
    <link>https://psycnet.apa.org/doiLanding?doi=10.1037%2Fmet0000764</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Network models in which each variable interacts with the others in a complex system have emerged as an important alternative to latent variable models in psychometric research. However, confirmatory methods for group network comparison can be limited by practical constraints, such as the computational intractability of the Ising model in large networks. In this study, we demonstrate how to estimate causal effects on network state and strength when direct network estimation is not feasible by leveraging the mathematical equivalencies between the Ising model and item response theory (IRT) models. We demonstrate through simulation that a two-parameter logistic explanatory IRT model can simultaneously recover causal effects on network state and strength. We first apply the method to a single empirical example of a vocabulary assessment from a content literacy intervention to demonstrate model building and interpretation strategies. We then replicate our approach with 72 empirical data sets from randomized controlled trials with item-level outcome data in education, economics, health, and related fields. Our results show that causal effects on network strength are both common and uncorrelated with effects on network state, suggesting that causal network models can provide new insight into the impact of interventions in the social and behavioral sciences."]]></description>
<dc:subject>to:NB psychometrics causal_inference of_course_its_really_a_spin_glass</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:26208897c888/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:of_course_its_really_a_spin_glass"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2211.15934">
    <title>[2211.15934] Causal identification for continuous-time stochastic processes</title>
    <dc:date>2025-12-18T04:10:32+00:00</dc:date>
    <link>https://arxiv.org/abs/2211.15934</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many real-world processes are trajectories that may be regarded as continuous-time "functional data". Examples include patients' biomarker concentrations, environmental pollutant levels, and prices of stocks. Corresponding advances in data collection have yielded near continuous-time measurements, from e.g. physiological monitors, wearable digital devices, and environmental sensors. Statistical methodology for estimating the causal effect of a time-varying treatment, measured discretely in time, is well developed. But discrete-time methods like the g-formula, structural nested models, and marginal structural models do not generalize easily to continuous time, due to the entanglement of uncountably infinite variables. Moreover, researchers have shown that the choice of discretization time scale can seriously affect the quality of causal inferences about the effects of an intervention. In this paper, we establish causal identification results for continuous-time treatment-outcome relationships for general cadlag stochastic processes under continuous-time confounding, through orthogonalization and weighting. We use three concrete running examples to demonstrate the plausibility of our identification assumptions, as well as their connections to the discrete-time g methods literature."]]></description>
<dc:subject>causality stochastic_processes causal_inference martingales in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:96f77e1ff841/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:martingales"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2512.00175">
    <title>[2512.00175] Comparing Two Proxy Methods for Causal Identification</title>
    <dc:date>2025-12-07T15:10:34+00:00</dc:date>
    <link>https://arxiv.org/abs/2512.00175</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Identifying causal effects in the presence of unmeasured variables is a fundamental challenge in causal inference, for which proxy variable methods have emerged as a powerful solution. We contrast two major approaches in this framework: (1) bridge equation methods, which leverage solutions to integral equations to recover causal targets, and (2) array decomposition methods, which recover latent factors composing counterfactual quantities by exploiting unique determination of eigenspaces. We compare the model restrictions underlying these two approaches and provide insight into implications of the underlying assumptions, clarifying the scope of applicability for each method."]]></description>
<dc:subject>to:NB causal_inference statistics ogburn.elizabeth to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:17f84a7565d6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ogburn.elizabeth"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.aeaweb.org/articles?id=10.1257/aer.20211811">
    <title>Innovative Ideas and Gender (In)equality - American Economic Association</title>
    <dc:date>2025-09-22T17:16:39+00:00</dc:date>
    <link>https://www.aeaweb.org/articles?id=10.1257/aer.20211811</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper analyzes recognition of women's innovative ideas compared to men's using bibliometric data in economics, mathematics, and sociology. I establish similarities between papers to construct relevant counterfactual citations. On average, all-female papers receive 10 percent fewer citations than all-male papers, a disparity reduced by 40 percent when considering team sizes and disappearing in most fields with authors' publication records. Additionally, strong in-group preferences emerge: All-male teams omit more papers with women, and vice versa. Accounting for publication histories, female scholars are cited 0 percent (economics) to 11 percent (mathematics) less, with early-career women enduring a 9–14 percent citation penalty."

--- Really curious to see how the matching is done, because everything's going to turn on this.]]></description>
<dc:subject>to:NB bibliometry inequality sexism academia sociology_of_science causal_inference text_mining</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:531ac8f380a6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bibliometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sexism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:academia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sociology_of_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.degruyterbrill.com/document/doi/10.1515/jci-2024-0002/html">
    <title>The necessity of construct and external validity for deductive causal inference</title>
    <dc:date>2025-08-16T13:22:43+00:00</dc:date>
    <link>https://www.degruyterbrill.com/document/doi/10.1515/jci-2024-0002/html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The Credibility Revolution advances internally valid research designs intended to identify causal effects from quantitative data. The ensuing emphasis on internal validity, however, has enabled a neglect of construct and external validity. We show that ignoring construct and external validity within identification strategies undermines the Credibility Revolution’s own goal of understanding causality deductively. Without assumptions regarding construct validity, one cannot accurately label the cause or outcome. Without assumptions regarding external validity, one cannot label the conditions enabling the cause to have an effect. If any of the assumptions regarding internal, construct, and external validity are missing, the claim is not deductively supported. The critical role of theoretical and substantive knowledge in deductive causal inference is illuminated by making such assumptions explicit. This article critically reviews approaches to identification in causal inference while developing a framework called causal specification. Causal specification augments existing identification strategies to enable and justify deductive, generalized claims about causes and effects. In the process, we review a variety of developments in the philosophy of science and causality and interdisciplinary social science methodology."]]></description>
<dc:subject>to:NB philosophy_of_science causal_inference measurement</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f9f4621cffeb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:philosophy_of_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:measurement"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/core/journals/philosophy-of-science/article/causal-direction-in-causal-bayes-nets/7CEA494FFE2E054D6EBB26C442B218DB?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Articles">
    <title>Causal Direction in Causal Bayes Nets | Philosophy of Science | Cambridge Core</title>
    <dc:date>2025-08-16T13:16:48+00:00</dc:date>
    <link>https://www.cambridge.org/core/journals/philosophy-of-science/article/causal-direction-in-causal-bayes-nets/7CEA494FFE2E054D6EBB26C442B218DB?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Articles</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Some authors maintain that we can use causal Bayes nets to infer whether X → Y or X ← Y by consulting a probability distribution defined over some exogenous source of variation for X or Y. We raise a problem for this approach. Specifically, we point out that there are cases where an exogenous cause of X (Ex) has no probabilistic influence on Y no matter the direction of causation—namely, cases where Ex → X → Y and Ex → X ← Y are probabilistically indistinguishable. We then assess the philosophical significance of this problem and discuss some potential solutions."]]></description>
<dc:subject>to:NB causal_inference graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:36b69b86c1af/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2411.10908">
    <title>[2411.10908] The Conflict Graph Design: Estimating Causal Effects under Arbitrary Neighborhood Interference</title>
    <dc:date>2025-04-28T02:05:56+00:00</dc:date>
    <link>https://arxiv.org/abs/2411.10908</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A fundamental problem in network experiments is selecting an appropriate experimental design in order to precisely estimate a given causal effect of interest. In this work, we propose the Conflict Graph Design, a general approach for constructing experiment designs under network interference with the goal of precisely estimating a pre-specified causal effect. A central aspect of our approach is the notion of a conflict graph, which captures the fundamental unobservability associated with the causal effect and the underlying network. In order to estimate effects, we propose a modified Horvitz--Thompson estimator. We show that its variance under the Conflict Graph Design is bounded as O(λ(H)/n), where λ(H) is the largest eigenvalue of the adjacency matrix of the conflict graph. These rates depend on both the underlying network and the particular causal effect under investigation. Not only does this yield the best known rates of estimation for several well-studied causal effects (e.g. the global and direct effects) but it also provides new methods for effects which have received less attention from the perspective of experiment design (e.g. spill-over effects). Finally, we construct conservative variance estimators which facilitate asymptotically valid confidence intervals for the causal effect of interest."]]></description>
<dc:subject>to:NB to_read experimental_design causal_inference network_data_analysis re:do_not_adjust_your_receiver</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d8cfab94679b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experimental_design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:do_not_adjust_your_receiver"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.06469">
    <title>[2203.06469] Semiparametric doubly robust targeted double machine learning: a review</title>
    <dc:date>2025-04-28T01:51:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.06469</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this review we cover the basics of efficient nonparametric parameter estimation (also called functional estimation), with a focus on parameters that arise in causal inference problems. We review both efficiency bounds (i.e., what is the best possible performance for estimating a given parameter?) and the analysis of particular estimators (i.e., what is this estimator's error, and does it attain the efficiency bound?) under weak assumptions. We emphasize minimax-style efficiency bounds, worked examples, and practical shortcuts for easing derivations. We gloss over most technical details, in the interest of highlighting important concepts and providing intuition for main ideas."

--- I need to revise the causal inference chapters (and problem sets?) to at least mention this stuff.

--- ETA after reading:
1. I'm relieved that the title is a joke.  (I kind of suspected, knowing Ed, but the first footnote is still re-assuring.)
2. The notation in this area sucks, _I_ have trouble keeping track of $\psi$ vs $\varphi$ (and I think I saw a $\phi$ which may have just been a typo?) vs...
3. I'm a little surprised that EHK doesn't get into issues about total estimation error, as opposed to just bias-correction followed by confidence intervals.
4. As for incorporating this into ADAfaEPoV, there's _probably_ a way, but it'll need a lot of writing on my part.  I _could_ just say "here're the bias correction terms for these cases", but that seems wrong, contrary to the spirit of the book.  OTOH going that deep into influence functions, well...]]></description>
<dc:subject>causal_inference nonparametrics kith_and_kin kennedy.edward_h. re:ADAfaEPoV have_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0dbbe6f7f177/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kennedy.edward_h."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2504.08324">
    <title>[2504.08324] An Introduction to Double/Debiased Machine Learning</title>
    <dc:date>2025-04-28T01:50:22+00:00</dc:date>
    <link>https://arxiv.org/abs/2504.08324</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper provides a practical introduction to Double/Debiased Machine Learning (DML). DML provides a general approach to performing inference about a target parameter in the presence of nuisance parameters. The aim of DML is to reduce the impact of nuisance parameter estimation on estimators of the parameter of interest. We describe DML and its two essential components: Neyman orthogonality and cross-fitting. We highlight that DML reduces functional form dependence and accommodates the use of complex data types, such as text data. We illustrate its application through three empirical examples that demonstrate DML's applicability in cross-sectional and panel settings."

--- I need to revise the causal inference chapters (and problem sets?) to at least mention this stuff.]]></description>
<dc:subject>to:NB causal_inference to_read re:ADAfaEPoV</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6e664109a8bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2503.19873">
    <title>[2503.19873] Identification of Average Treatment Effects in Nonparametric Panel Models</title>
    <dc:date>2025-04-28T01:38:31+00:00</dc:date>
    <link>https://arxiv.org/abs/2503.19873</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper studies identification of average treatment effects in a panel data setting. It introduces a novel nonparametric factor model and proves identification of average treatment effects. The identification proof is based on the introduction of a consistent estimator. Underlying the proof is a result that there is a consistent estimator for the expected outcome in the absence of the treatment for each unit and time period; this result can be applied more broadly, for example in problems of decompositions of group-level differences in outcomes, such as the much-studied gender wage gap."]]></description>
<dc:subject>to:NB causal_inference time_series athey.susan to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:42071199fb7e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:athey.susan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2503.20769">
    <title>[2503.20769] Inferring Treatment Effects in Large Panels by Uncovering Latent Similarities</title>
    <dc:date>2025-04-28T01:36:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2503.20769</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The presence of unobserved confounders is one of the main challenges in identifying treatment effects. In this paper, we propose a new approach to causal inference using panel data with large large N and T. Our approach imputes the untreated potential outcomes for treated units using the outcomes for untreated individuals with similar values of the latent confounders. In order to find units with similar latent characteristics, we utilize long pre-treatment histories of the outcomes. Our analysis is based on a nonparametric, nonlinear, and nonseparable factor model for untreated potential outcomes and treatments. The model satisfies minimal smoothness requirements. We impute both missing counterfactual outcomes and propensity scores using kernel smoothing based on the constructed measure of latent similarity between units, and demonstrate that our estimates can achieve the optimal nonparametric rate of convergence up to log terms. Using these estimates, we construct a doubly robust estimator of the period-specifc average treatment effect on the treated (ATT), and provide conditions, under which this estimator is N‾‾√-consistent, and asymptotically normal and unbiased. Our simulation study demonstrates that our method provides accurate inference for a wide range of data generating processes."]]></description>
<dc:subject>to:NB factor_analysis causal_inference to_read time_series</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e4e836c06c31/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:factor_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2503.07811">
    <title>[2503.07811] A primer on optimal transport for causal inference with observational data</title>
    <dc:date>2025-03-24T00:13:43+00:00</dc:date>
    <link>https://arxiv.org/abs/2503.07811</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The theory of optimal transportation has developed into a powerful and elegant framework for comparing probability distributions, with wide-ranging applications in all areas of science. The fundamental idea of analyzing probabilities by comparing their underlying state space naturally aligns with the core idea of causal inference, where understanding and quantifying counterfactual states is paramount. Despite this intuitive connection, explicit research at the intersection of optimal transport and causal inference is only beginning to develop. Yet, many foundational models in causal inference have implicitly relied on optimal transport principles for decades, without recognizing the underlying connection. Therefore, the goal of this review is to offer an introduction to the surprisingly deep existing connections between optimal transport and the identification of causal effects with observational data -- where optimal transport is not just a set of potential tools, but actually builds the foundation of model assumptions. As a result, this review is intended to unify the language and notation between different areas of statistics, mathematics, and econometrics, by pointing out these existing connections, and to explore novel problems and directions for future work in both areas derived from this realization."]]></description>
<dc:subject>to:NB causal_inference probability via:lal.apoorva</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2407cdee4ed6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:lal.apoorva"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.01637">
    <title>[1903.01637] When do common time series estimands have nonparametric causal meaning?</title>
    <dc:date>2025-03-24T00:13:24+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.01637</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we introduce the direct potential outcome system as a framework for analyzing dynamic causal effects of assignments on outcomes in observational time series settings. We provide conditions under which common predictive time series estimands, such as the impulse response function, generalized impulse response function, local projection, and local projection instrumental variables, have a nonparametric causal interpretation in terms of dynamic causal effects. The direct potential outcome system therefore provides a foundation for analyzing popular reduced-form methods for estimating the causal effect of macroeconomic shocks on outcomes in time series settings."]]></description>
<dc:subject>to:NB causal_inference time_series via:lal.apoorva</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a639ca0a7018/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:lal.apoorva"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2306.16591">
    <title>[2306.16591] Nonparametric Causal Decomposition of Group Disparities</title>
    <dc:date>2025-01-06T14:48:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2306.16591</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce a new nonparametric causal decomposition approach that identifies the mechanisms by which a treatment variable contributes to a group-based outcome disparity. Our approach distinguishes three mechanisms: group differences in 1) treatment prevalence, 2) average treatment effects, and 3) selection into treatment based on individual-level treatment effects. Our approach reformulates classic Kitagawa-Blinder-Oaxaca decompositions in causal and nonparametric terms, complements causal mediation analysis by explaining group disparities instead of group effects, and isolates conceptually distinct mechanisms conflated in recent random equalization decompositions. In contrast to all prior approaches, our framework uniquely identifies differential selection into treatment as a novel disparity-generating mechanism. Our approach can be used for both the retrospective causal explanation of disparities and the prospective planning of interventions to change disparities. We present both an unconditional and a conditional decomposition, where the latter quantifies the contributions of the treatment within levels of certain covariates. We develop nonparametric estimators that are n‾√-consistent, asymptotically normal, semiparametrically efficient, and multiply robust. We apply our approach to analyze the mechanisms by which college graduation causally contributes to intergenerational income persistence (the disparity in adult income between the children of high- vs low-income parents). Empirically, we demonstrate a previously undiscovered role played by the new selection component in intergenerational income persistence."]]></description>
<dc:subject>to:NB to_read have_skimmed causal_inference statistics elwert.felix to_teach:statistics_of_inequality_and_discrimination sds_icsd_search</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3123a651d148/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_skimmed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:elwert.felix"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sds_icsd_search"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w32273">
    <title>Ban-the-Box Laws: Fair and Effective? | NBER</title>
    <dc:date>2024-12-22T03:22:27+00:00</dc:date>
    <link>https://www.nber.org/papers/w32273</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Ban-the-box (BTB) laws are a widely used public policy rooted in employment law related to unnecessarily exclusionary hiring practices. BTB laws are intended to improve the employment opportunities of those with criminal backgrounds by giving them a fair chance during the hiring process. Prior research on the effectiveness of these laws in meeting their objective is limited and inconclusive. In this article, we extend the prior literature in two ways: we expand the years of analysis to a period of rapid expansion of BTB laws and we examine different types of BTB laws depending on the employers affected (e.g., public sector). Results indicate that BTB laws, any type of BTB law or BTB laws covering different types of employers, have no systematic or statistically significant association with employment of low-educated men, both young and old and across racial and ethnic groups. We speculate that the lack of effectiveness of BTB laws stems from the difficulty in enforcing such laws and already high rates of employer willingness to hire those with criminal histories."]]></description>
<dc:subject>to:NB to_teach:statistics_of_inequality_and_discrimination economics causal_inference to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5e7580fe1f83/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nowpublishers.com/article/Details/HPE-0078">
    <title>now publishers - Randomized Controlled History?</title>
    <dc:date>2024-12-11T19:42:19+00:00</dc:date>
    <link>https://www.nowpublishers.com/article/Details/HPE-0078</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A newer strand of research in historical political economy applies a "design-based inference" approach to history in order to approximate a randomized controlled trial. But can this exacting approach work given the messy nature of historical data? Using the example of research on the long-term effects of British colonialism in India, I evaluate six recent articles that use techniques like natural experiments of history, instrumental variable analyses, and matching designs to overcome the fact that colonization was not random. I find that despite generating important methodological conversations about causation, the use of these techniques in these studies depends on thin or sometimes inaccurate historical evidence. It is therefore unclear that "randomized controlled history" can make more credible causal inferences than a selection on observables approach. This article suggests best practices for future research that aims to study history in an experimental format."]]></description>
<dc:subject>to:NB causal_inference historiography social_science_methodology imperialism</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8cff81fd6b62/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:historiography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_science_methodology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:imperialism"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2305.04116">
    <title>[2305.04116] The Fundamental Limits of Structure-Agnostic Functional Estimation</title>
    <dc:date>2024-12-11T19:37:38+00:00</dc:date>
    <link>https://arxiv.org/abs/2305.04116</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many recent developments in causal inference, and functional estimation problems more generally, have been motivated by the fact that classical one-step (first-order) debiasing methods, or their more recent sample-split double machine-learning avatars, can outperform plugin estimators under surprisingly weak conditions. These first-order corrections improve on plugin estimators in a black-box fashion, and consequently are often used in conjunction with powerful off-the-shelf estimation methods. These first-order methods are however provably suboptimal in a minimax sense for functional estimation when the nuisance functions live in Holder-type function spaces. This suboptimality of first-order debiasing has motivated the development of "higher-order" debiasing methods. The resulting estimators are, in some cases, provably optimal over Holder-type spaces, but both the estimators which are minimax-optimal and their analyses are crucially tied to properties of the underlying function space.
"In this paper we investigate the fundamental limits of structure-agnostic functional estimation, where relatively weak conditions are placed on the underlying nuisance functions. We show that there is a strong sense in which existing first-order methods are optimal. We achieve this goal by providing a formalization of the problem of functional estimation with black-box nuisance function estimates, and deriving minimax lower bounds for this problem. Our results highlight some clear tradeoffs in functional estimation -- if we wish to remain agnostic to the underlying nuisance function spaces, impose only high-level rate conditions, and maintain compatibility with black-box nuisance estimators then first-order methods are optimal. When we have an understanding of the structure of the underlying nuisance functions then carefully constructed higher-order estimators can outperform first-order estimators."]]></description>
<dc:subject>to:NB to_read statistics nonparametrics entropy_estimation kith_and_kin kennedy.edward_h. wasserman.larry balakrishnan.sivaraman causal_inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0ee8eb04a835/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:entropy_estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kennedy.edward_h."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wasserman.larry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:balakrishnan.sivaraman"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2410.03514">
    <title>[2410.03514] Stabilized Neural Prediction of Potential Outcomes in Continuous Time</title>
    <dc:date>2024-12-06T14:06:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2410.03514</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Patient trajectories from electronic health records are widely used to predict potential outcomes of treatments over time, which then allows to personalize care. Yet, existing neural methods for this purpose have a key limitation: while some adjust for time-varying confounding, these methods assume that the time series are recorded in discrete time. In other words, they are constrained to settings where measurements and treatments are conducted at fixed time steps, even though this is unrealistic in medical practice. In this work, we aim to predict potential outcomes in continuous time. The latter is of direct practical relevance because it allows for modeling patient trajectories where measurements and treatments take place at arbitrary, irregular timestamps. We thus propose a new method called stabilized continuous time inverse propensity network (SCIP-Net). For this, we further derive stabilized inverse propensity weights for robust prediction of the potential outcomes. To the best of our knowledge, our SCIP-Net is the first neural method that performs proper adjustments for time-varying confounding in continuous time."]]></description>
<dc:subject>to:NB causal_inference time_series neural_networks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:eb65f95e0d92/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/core/journals/american-political-science-review/article/abs/how-to-make-causal-inferences-with-timeseries-crosssectional-data-under-selection-on-observables/498BE04E5AF9802EC4D33DD7A4016584">
    <title>How to Make Causal Inferences with Time-Series Cross-Sectional Data under Selection on Observables | American Political Science Review | Cambridge Core</title>
    <dc:date>2024-12-06T14:05:57+00:00</dc:date>
    <link>https://www.cambridge.org/core/journals/american-political-science-review/article/abs/how-to-make-causal-inferences-with-timeseries-crosssectional-data-under-selection-on-observables/498BE04E5AF9802EC4D33DD7A4016584</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Repeated measurements of the same countries, people, or groups over time are vital to many fields of political science. These measurements, sometimes called time-series cross-sectional (TSCS) data, allow researchers to estimate a broad set of causal quantities, including contemporaneous effects and direct effects of lagged treatments. Unfortunately, popular methods for TSCS data can only produce valid inferences for lagged effects under some strong assumptions. In this paper, we use potential outcomes to define causal quantities of interest in these settings and clarify how standard models like the autoregressive distributed lag model can produce biased estimates of these quantities due to post-treatment conditioning. We then describe two estimation strategies that avoid these post-treatment biases—inverse probability weighting and structural nested mean models—and show via simulations that they can outperform standard approaches in small sample settings. We illustrate these methods in a study of how welfare spending affects terrorism."]]></description>
<dc:subject>to:NB time_series causal_inference to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e670918cfed0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://web.stanford.edu/~swager/causal_inf_book.pdf">
    <title>Causal Inference: A Statistical Learning Approach</title>
    <dc:date>2024-10-09T14:27:09+00:00</dc:date>
    <link>https://web.stanford.edu/~swager/causal_inf_book.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to:NB causal_inference wager.stefan via:??? books:noted downloaded</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ebbcc88b908e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wager.stefan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:???"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:noted"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:downloaded"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w32822">
    <title>Local Projections | NBER</title>
    <dc:date>2024-09-19T20:04:38+00:00</dc:date>
    <link>https://www.nber.org/papers/w32822</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A central question in applied research is to estimate the effect of an exogenous intervention or shock on an outcome. The intervention can affect the outcome and controls on impact and over time. Moreover, there can be subsequent feedback between outcomes, controls and the intervention. Many of these interactions can be untangled using local projections. This method’s simplicity makes it a convenient and versatile tool in the empiricist’s kit, one that is generalizable to complex settings. This article reviews the state-of-the art for the practitioner, discusses best practices and possible extensions of local projections methods, along with their limitations."]]></description>
<dc:subject>to:NB causal_inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:524b19492fea/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/qje/article-abstract/139/2/891/7473710">
    <title>Logs with Zeros? Some Problems and Solutions* | The Quarterly Journal of Economics | Oxford Academic</title>
    <dc:date>2024-06-24T13:38:04+00:00</dc:date>
    <link>https://academic.oup.com/qje/article-abstract/139/2/891/7473710</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["When studying an outcome Y that is weakly positive but can equal zero (e.g., earnings), researchers frequently estimate an average treatment effect (ATE) for a “log-like” transformation that behaves like log (Y) for large Y but is defined at zero (e.g., log (1 + Y), arcsinh(𝑌)⁠). We argue that ATEs for log-like transformations should not be interpreted as approximating percentage effects, since unlike a percentage, they depend on the units of the outcome. In fact, we show that if the treatment affects the extensive margin, one can obtain a treatment effect of any magnitude simply by rescaling the units of Y before taking the log-like transformation. This arbitrary unit dependence arises because an individual-level percentage effect is not well-defined for individuals whose outcome changes from zero to nonzero when receiving treatment, and the units of the outcome implicitly determine how much weight the ATE for a log-like transformation places on the extensive margin. We further establish a trilemma: when the outcome can equal zero, there is no treatment effect parameter that is an average of individual-level treatment effects, unit invariant, and point identified. We discuss several alternative approaches that may be sensible in settings with an intensive and extensive margin, including (i) expressing the ATE in levels as a percentage (e.g., using Poisson regression), (ii) explicitly calibrating the value placed on the intensive and extensive margins, and (iii) estimating separate effects for the two margins (e.g., using Lee bounds). We illustrate these approaches in three empirical applications."]]></description>
<dc:subject>to:NB regression causal_inference to_teach:undergrad-ADA</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:67420daed294/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w32342">
    <title>Social Movements and Public Opinion in the United States | NBER</title>
    <dc:date>2024-05-14T13:03:25+00:00</dc:date>
    <link>https://www.nber.org/papers/w32342</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recent social movements stand out by their spontaneous nature and lack of stable leadership, raising doubts on their ability to generate political change. This article provides systematic evidence on the effects of protests on public opinion and political attitudes. Drawing on a database covering the quasi-universe of protests held in the United States, we identify 14 social movements that took place from 2017 to 2022, covering topics related to environmental protection, gender equality, gun control, immigration, national and international politics, and racial issues. We use Twitter data, Google search volumes, and high-frequency surveys to track the evolution of online interest, policy views, and vote intentions before and after the outset of each movement. Combining national-level event studies with difference-in-differences designs exploiting variation in local protest intensity, we find that protests generate substantial internet activity but have limited effects on political attitudes. Except for the Black Lives Matter protests following the death of George Floyd, which shifted views on racial discrimination and increased votes for the Democrats, we estimate precise null effects of protests on public opinion and electoral behavior."

--- This paper looks interesting, but I am kind of blown away that it seems to not cite any social-movement scholars from sociology or political science.  (I haven't double-checked everyone's affiliation, maybe I'm being _slightly_ unfair there.)]]></description>
<dc:subject>to:NB social_movements causal_inference us_politics via:? economistic_imperialism</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fc5b3281d19d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_movements"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:us_politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:economistic_imperialism"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/core/journals/british-journal-of-political-science/article/unequal-and-unsupportive-exposure-to-poor-people-weakens-support-for-redistribution-among-the-rich/FC32FA59B3C5525A178C7012859F95D8">
    <title>Unequal and Unsupportive: Exposure to Poor People Weakens Support for Redistribution among the Rich | British Journal of Political Science | Cambridge Core</title>
    <dc:date>2024-04-21T01:28:39+00:00</dc:date>
    <link>https://www.cambridge.org/core/journals/british-journal-of-political-science/article/unequal-and-unsupportive-exposure-to-poor-people-weakens-support-for-redistribution-among-the-rich/FC32FA59B3C5525A178C7012859F95D8</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Do the rich become more or less supportive of redistribution when exposed to poor people in their local surroundings? Most existing observational studies find that exposure to poor individuals is positively associated with support for redistribution among the well-off, but one prominent field experiment found a negative link. We seek to resolve these divergent findings by employing a design closer to the studies that have found a positive link, but with more causal leverage than these; specifically, a three-wave panel survey linked with fine-grained registry data on local income composition in Denmark. In within-individual models, increased exposure to poor individuals is associated with lower support for redistribution among wealthy individuals. By contrast, between-individual models yield a positive relationship, thus indicating that self-selection based on stable individual characteristics likely explains the predominant finding in previous work."]]></description>
<dc:subject>to:NB inequality causal_inference political_economy time_series to_teach:statistics_of_inequality_and_discrimination</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6502f4833e85/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:political_economy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.14959">
    <title>[2402.14959] A Causal Framework to Evaluate Racial Bias in Law Enforcement Systems</title>
    <dc:date>2024-03-05T18:26:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.14959</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We are interested in developing a data-driven method to evaluate race-induced biases in law enforcement systems. While the recent works have addressed this question in the context of police-civilian interactions using police stop data, they have two key limitations. First, bias can only be properly quantified if true criminality is accounted for in addition to race, but it is absent in prior works. Second, law enforcement systems are multi-stage and hence it is important to isolate the true source of bias within the "causal chain of interactions" rather than simply focusing on the end outcome; this can help guide reforms. In this work, we address these challenges by presenting a multi-stage causal framework incorporating criminality. We provide a theoretical characterization and an associated data-driven method to evaluate (a) the presence of any form of racial bias, and (b) if so, the primary source of such a bias in terms of race and criminality. Our framework identifies three canonical scenarios with distinct characteristics: in settings like (1) airport security, the primary source of observed bias against a race is likely to be bias in law enforcement against innocents of that race; (2) AI-empowered policing, the primary source of observed bias against a race is likely to be bias in law enforcement against criminals of that race; and (3) police-civilian interaction, the primary source of observed bias against a race could be bias in law enforcement against that race or bias from the general public in reporting against the other race. Through an extensive empirical study using police-civilian interaction data and 911 call data, we find an instance of such a counter-intuitive phenomenon: in New Orleans, the observed bias is against the majority race and the likely reason for it is the over-reporting (via 911 calls) of incidents involving the minority race by the general public."

--- Very curious to see what this approach would say about sex bias (where the naive "just look at the disparities!" approach indicates massive systematic misandry, all over the world).]]></description>
<dc:subject>to:NB causal_inference crime racism algorithmic_fairness winship.christopher to_teach:statistics_of_inequality_and_discrimination</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:57747bf61594/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:crime"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:racism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algorithmic_fairness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:winship.christopher"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.14979">
    <title>[2402.14979] Optimizing Language Models for Human Preferences is a Causal Inference Problem</title>
    <dc:date>2024-03-05T18:22:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.14979</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["As large language models (LLMs) see greater use in academic and commercial settings, there is increasing interest in methods that allow language models to generate texts aligned with human preferences. In this paper, we present an initial exploration of language model optimization for human preferences from direct outcome datasets, where each sample consists of a text and an associated numerical outcome measuring the reader's response. We first propose that language model optimization should be viewed as a causal problem to ensure that the model correctly learns the relationship between the text and the outcome. We formalize this causal language optimization problem, and we develop a method--causal preference optimization (CPO)--that solves an unbiased surrogate objective for the problem. We further extend CPO with doubly robust CPO (DR-CPO), which reduces the variance of the surrogate objective while retaining provably strong guarantees on bias. Finally, we empirically demonstrate the effectiveness of (DR-)CPO in optimizing state-of-the-art LLMs for human preferences on direct outcome data, and we validate the robustness of DR-CPO under difficult confounding conditions."]]></description>
<dc:subject>in_NB large_language_models_(so_called) causal_inference kith_and_kin ben-michael.eli</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1f908b3a5d94/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_language_models_(so_called)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ben-michael.eli"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.15502">
    <title>[2402.15502] Generative invariance: causal extrapolation without exogeneity</title>
    <dc:date>2024-03-05T16:43:01+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.15502</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We present a new estimator for predicting outcomes in different distributional settings under hidden confounding without relying on instruments or exogenous variables. The population definition of our estimator identifies causal parameters, whose empirical version is plugged into a generative model capable of replicating the conditional law within a test environment. We check that the probabilistic affinity between our proposal and test distributions is invariant across interventions. This work enhances the current statistical comprehension of causality by demonstrating that predictions in a test environment can be made without the need for exogenous variables and without specific assumptions regarding the strength of perturbations or the overlap of distributions."]]></description>
<dc:subject>causal_inference color_me_skeptical in_NB big_if_true</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b86afd7f6228/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:big_if_true"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/1745-9125.12353#crim12353-supitem-0001">
    <title>Streetwork at the crossroads: An evaluation of a street gang outreach intervention and holistic appraisal of the research evidence - Hureau - 2023 - Criminology - Wiley Online Library</title>
    <dc:date>2024-03-04T14:27:53+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/1745-9125.12353#crim12353-supitem-0001</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Spurred by the success of public health violence interventions, and accelerated by policy pressure to reduce violence without exacerbating overpolicing and mass incarceration, streetwork programs—those that provide anti-violence services by neighborhood-based workers who perform their work beyond the walls of parochial institutions—have positioned themselves as the most important non–law-enforcement violence prevention option available to urban policy makers. Yet despite their importance, the state of the field seems difficult to interpret for academics and practitioners alike. In this article, we make several contributions that bring forth new findings and deliver new perspectives on streetwork as a violence reduction strategy. First, we offer an extended analytic review of the streetwork evaluation literature that connects the study of contemporary public health violence interventions to a preceding tradition of criminologically inspired streetwork studies. Second, we present the results of an impact evaluation of StreetSafe Boston (SSB)—a multiyear streetwork intervention that served 20 Boston gangs. We find that the SSB intervention had no detectable effect on violence among the gangs that it served. We conclude by offering a framework for understanding a field at multiple crossroads: past and present, proclaimed successes and failures, help and harm."

--- That last sentence is the most poetic way I can remember of announcing an informative null result.
--- Last tag is conditional on finding replication data.]]></description>
<dc:subject>to:NB to_read causal_inference crime violence public_policy winship.christopher to_teach:undergrad-ADA</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f109c63b3182/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:crime"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:violence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:public_policy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:winship.christopher"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://nowpublishers.com/article/Details/MAL-106">
    <title>now publishers - Causal Fairness Analysis: A Causal Toolkit for Fair Machine Learning</title>
    <dc:date>2024-03-02T19:20:27+00:00</dc:date>
    <link>https://nowpublishers.com/article/Details/MAL-106</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Decision-making systems based on AI and machine learning have been used throughout a wide range of real-world scenarios, including healthcare, law enforcement, education, and finance. It is no longer far-fetched to envision a future where autonomous systems will drive entire business decisions and, more broadly, support large-scale decision-making infrastructure to solve society’s most challenging problems. Issues of unfairness and discrimination are pervasive when decisions are being made by humans, and remain (or are potentially amplified) when decisions are made using machines with little transparency, accountability, and fairness. In this monograph, we introduce a framework for causal fairness analysis with the intent of filling in this gap, i.e., understanding, modeling, and possibly solving issues of fairness in decision-making settings.
"The main insight of our approach will be to link the quantification of the disparities present in the observed data with the underlying, often unobserved, collection of causal mechanisms that generate the disparity in the first place, a challenge we call the Fundamental Problem of Causal Fairness Analysis (FPCFA). In order to solve the FPCFA, we study the problem of decomposing variations and empirical measures of fairness that attribute such variations to structural mechanisms and different units of the population. Our effort culminates in the Fairness Map, the first systematic attempt to organize and explain the relationship between various criteria found in the literature. Finally, we study which causal assumptions are minimally needed for performing causal fairness analysis and propose the Fairness Cookbook, which allows one to assess the existence of disparate impact and disparate treatment."

--- Ungated: [https://causalai.net/r90.pdf]]]></description>
<dc:subject>to:NB algorithmic_fairness causal_inference to_read to_teach:statistics_of_inequality_and_discrimination to_teach:data-mining bareinboim.elias</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:58b48843b8d2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algorithmic_fairness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bareinboim.elias"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.14777">
    <title>[2402.14777] Causal Imputation for Counterfactual SCMs: Bridging Graphs and Latent Factor Models</title>
    <dc:date>2024-03-01T03:30:18+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.14777</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the task of causal imputation, where we aim to predict the outcomes of some set of actions across a wide range of possible contexts. As a running example, we consider predicting how different drugs affect cells from different cell types. We study the index-only setting, where the actions and contexts are categorical variables with a finite number of possible values. Even in this simple setting, a practical challenge arises, since often only a small subset of possible action-context pairs have been studied. Thus, models must extrapolate to novel action-context pairs, which can be framed as a form of matrix completion with rows indexed by actions, columns indexed by contexts, and matrix entries corresponding to outcomes. We introduce a novel SCM-based model class, where the outcome is expressed as a counterfactual, actions are expressed as interventions on an instrumental variable, and contexts are defined based on the initial state of the system. We show that, under a linearity assumption, this setup induces a latent factor model over the matrix of outcomes, with an additional fixed effect term. To perform causal prediction based on this model class, we introduce simple extension to the Synthetic Interventions estimator (Agarwal et al., 2020). We evaluate several matrix completion approaches on the PRISM drug repurposing dataset, showing that our method outperforms all other considered matrix completion approaches."]]></description>
<dc:subject>to:NB causal_inference low-rank_approximation factor_analysis uhler.caroline</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2d719526204b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:low-rank_approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:factor_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:uhler.caroline"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://direct.mit.edu/rest/article-abstract/doi/10.1162/rest_a_01323/115634/Flight-from-Urban-Blight-Lead-Poisoning-Crime-and?redirectedFrom=fulltext">
    <title>Flight from Urban Blight: Lead Poisoning, Crime, and Suburbanization | The Review of Economics and Statistics | MIT Press</title>
    <dc:date>2024-01-08T02:25:26+00:00</dc:date>
    <link>https://direct.mit.edu/rest/article-abstract/doi/10.1162/rest_a_01323/115634/Flight-from-Urban-Blight-Lead-Poisoning-Crime-and?redirectedFrom=fulltext</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper we study the effect of violent crime on residential and firms location decisions and their implications for segregation in cities. We do so by proposing a new instrument to exogenously predict violent crime in city centers. We base our instrument on chemical and medical evidence that links local characteristics of the soil to lead poisoning and aggression. We show that the increase in violent crime between 1960 and 1990 due to lead poisoning moved almost 8 million people to the suburbs. Firms followed by leaving the city centers. We then show that the suburbanization process was characterized by “white flight”."

--- Really interested to see how they argue the _only_ channel for their instrument is through lead...]]></description>
<dc:subject>to:NB lead violence economic_history causal_inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2800ba1fc860/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lead"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:violence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:economic_history"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2309.03969">
    <title>[2309.03969] Estimating the prevalance of peer effects and other spillovers</title>
    <dc:date>2023-11-02T01:17:18+00:00</dc:date>
    <link>https://arxiv.org/abs/2309.03969</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In settings where interference between units is possible, we define the prevalance of indirect effects to be the number of units who are affected by the treatment of others. This quantity does not fully identify an indirect effect, but may be used to show whether such effects are widely prevalent. Given a randomized experiment with binary-valued outcomes, methods are presented for conservative point estimation and one-sided interval estimation. No assumptions beyond randomization of treatment are required, allowing for usage in settings where models or assumptions on interference might be questionable. To show asymptotic coverage of our intervals in settings not covered by existing results, we provide a central limit theorem that combines local dependence and sampling without replacement. Consistency and minimax properties of the point estimator are shown as well. The approach is demonstrated on an experiment in which students were treated for a highly transmissible parasitic infection, for which we find that a significant fraction of students were affected by the treatment of schools other than their own."]]></description>
<dc:subject>to:NB causal_inference experiments_on_networks network_data_analysis kith_and_kin choi.david_s.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4f870f4f26ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experiments_on_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:choi.david_s."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2310.16626">
    <title>[2310.16626] Scalable Causal Structure Learning via Amortized Conditional Independence Testing</title>
    <dc:date>2023-10-28T18:09:49+00:00</dc:date>
    <link>https://arxiv.org/abs/2310.16626</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Controlling false positives (Type I errors) through statistical hypothesis testing is a foundation of modern scientific data analysis. Existing causal structure discovery algorithms either do not provide Type I error control or cannot scale to the size of modern scientific datasets. We consider a variant of the causal discovery problem with two sets of nodes, where the only edges of interest form a bipartite causal subgraph between the sets. We develop Scalable Causal Structure Learning (SCSL), a method for causal structure discovery on bipartite subgraphs that provides Type I error control. SCSL recasts the discovery problem as a simultaneous hypothesis testing problem and uses discrete optimization over the set of possible confounders to obtain an upper bound on the test statistic for each edge. Semi-synthetic simulations demonstrate that SCSL scales to handle graphs with hundreds of nodes while maintaining error control and good power. We demonstrate the practical applicability of the method by applying it to a cancer dataset to reveal connections between somatic gene mutations and metastases to different tissues."]]></description>
<dc:subject>to:NB hypothesis_testing causal_inference kith_and_kin ramdas.aaditya</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:750d79d0c649/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ramdas.aaditya"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2103.01802">
    <title>[2103.01802] Median Optimal Treatment Regimes</title>
    <dc:date>2023-06-29T16:01:22+00:00</dc:date>
    <link>https://arxiv.org/abs/2103.01802</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Optimal treatment regimes are personalized policies for making a treatment decision based on subject characteristics, with the policy chosen to maximize some value. It is common to aim to maximize the mean outcome in the population, via a regime assigning treatment only to those whose mean outcome is higher under treatment versus control. However, the mean can be an unstable measure of centrality, resulting in imprecise statistical procedures, as well as unrobust decisions that can be overly influenced by a small fraction of subjects. In this work, we propose a new median optimal treatment regime that instead treats individuals whose conditional median is higher under treatment. This ensures that optimal decisions for individuals from the same group are not overly influenced either by (i) a small fraction of the group (unlike the mean criterion), or (ii) unrelated subjects from different groups (unlike marginal median/quantile criteria). We introduce a new measure of value, the Average Conditional Median Effect (ACME), which summarizes across-group median treatment outcomes of a policy, and which the median optimal treatment regime maximizes. After developing key motivating examples that distinguish median optimal treatment regimes from mean and marginal median optimal treatment regimes, we give a nonparametric efficiency bound for estimating the ACME of a policy, and propose a new doubly robust-style estimator that achieves the efficiency bound under weak conditions. To construct the median optimal treatment regime, we introduce a new doubly robust-style estimator for the conditional median treatment effect. Finite-sample properties are explored via numerical simulations and the proposed algorithm is illustrated using data from a randomized clinical trial in patients with HIV."]]></description>
<dc:subject>to_read decision_theory causal_inference kennedy.edward_h. kith_and_kin re:codename:one_law_for_the_lion_and_ox_is_oppression in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c25bcb7497ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:decision_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kennedy.edward_h."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:codename:one_law_for_the_lion_and_ox_is_oppression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0286067">
    <title>Causal implicatures from correlational statements | PLOS ONE</title>
    <dc:date>2023-05-22T18:20:47+00:00</dc:date>
    <link>https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0286067</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Correlation does not imply causation, but this does not necessarily stop people from drawing causal inferences from correlational statements. We show that people do in fact infer causality from statements of association, under minimal conditions. In Study 1, participants interpreted statements of the form “X is associated with Y” to imply that Y causes X. In Studies 2 and 3, participants interpreted statements of the form “X is associated with an increased risk of Y” to imply that X causes Y. Thus, even the most orthodox correlational language can give rise to causal inferences."

--- Good to have this confirmed!]]></description>
<dc:subject>causal_inference psychology to_teach:undergrad-ADA gershman.samuel via:? in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:86677951c9ee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gershman.samuel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:?"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2304.07896">
    <title>[2304.07896] Out-of-Variable Generalization</title>
    <dc:date>2023-05-02T21:17:14+00:00</dc:date>
    <link>https://arxiv.org/abs/2304.07896</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The ability of an agent to perform well in new and unseen environments is a crucial aspect of intelligence. In machine learning, this ability is referred to as strong or out-of-distribution generalization. However, simply considering differences in data distributions is not sufficient to fully capture differences in environments. In the present paper, we assay out-of-variable generalization, which refers to an agent's ability to handle new situations that involve variables never jointly observed before. We expect that such ability is important also for AI-driven scientific discovery: humans, too, explore 'Nature' by probing, observing and measuring subsets of variables at one time. Mathematically, it requires efficient re-use of past marginal knowledge, i.e., knowledge over subsets of variables. We study this problem, focusing on prediction tasks that involve observing overlapping, yet distinct, sets of causal parents. We show that the residual distribution of one environment encodes the partial derivative of the true generating function with respect to the unobserved causal parent. Hence, learning from the residual allows zero-shot prediction even when we never observe the outcome variable in the other environment."]]></description>
<dc:subject>in_NB causal_inference causal_discovery via:rvenkat scholkopf.bernhard</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:24a252e35734/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:rvenkat"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:scholkopf.bernhard"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2302.05380">
    <title>[2302.05380] On the Interventional Kullback-Leibler Divergence</title>
    <dc:date>2023-05-02T21:15:08+00:00</dc:date>
    <link>https://arxiv.org/abs/2302.05380</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Modern machine learning approaches excel in static settings where a large amount of i.i.d. training data are available for a given task. In a dynamic environment, though, an intelligent agent needs to be able to transfer knowledge and re-use learned components across domains. It has been argued that this may be possible through causal models, aiming to mirror the modularity of the real world in terms of independent causal mechanisms. However, the true causal structure underlying a given set of data is generally not identifiable, so it is desirable to have means to quantify differences between models (e.g., between the ground truth and an estimate), on both the observational and interventional level.
"In the present work, we introduce the Interventional Kullback-Leibler (IKL) divergence to quantify both structural and distributional differences between models based on a finite set of multi-environment distributions generated by interventions from the ground truth. Since we generally cannot quantify all differences between causal models for every finite set of interventional distributions, we propose a sufficient condition on the intervention targets to identify subsets of observed variables on which the models provably agree or disagree."]]></description>
<dc:subject>in_NB causal_inference information_theory via:rvenkat scholkopf.bernhard</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c5364517c43b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:rvenkat"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:scholkopf.bernhard"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/abs/10.1080/01621459.2021.1941053">
    <title>The Generalized Oaxaca-Blinder Estimator: Journal of the American Statistical Association: Vol 0, No 0</title>
    <dc:date>2023-03-07T15:40:40+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/abs/10.1080/01621459.2021.1941053</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["After performing a randomized experiment, researchers often use ordinary least-square (OLS) regression to adjust for baseline covariates when estimating the average treatment effect. It is widely known that the resulting confidence interval is valid even if the linear model is misspecified. In this article, we generalize that conclusion to covariate adjustment with nonlinear models. We introduce an intuitive way to use any “simple” nonlinear model to construct a covariate-adjusted confidence interval for the average treatment effect. The confidence interval derives its validity from randomization alone, and when nonlinear models fit the data better than linear models, it is narrower than the usual interval from OLS adjustment."]]></description>
<dc:subject>to:NB causal_inference experimental_design statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c6eec1e68747/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experimental_design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2210.11021">
    <title>[2210.11021] Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models</title>
    <dc:date>2022-12-09T20:02:54+00:00</dc:date>
    <link>https://arxiv.org/abs/2210.11021</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Causal discovery aims to recover causal structures generating the observational data. Despite its success in certain problems, in many real-world scenarios the observed variables are not the target variables of interest, but the imperfect measures of the target variables. Causal discovery under measurement error aims to recover the causal graph among unobserved target variables from observations made with measurement error. We consider a specific formulation of the problem, where the unobserved target variables follow a linear non-Gaussian acyclic model, and the measurement process follows the random measurement error model. Existing methods on this formulation rely on non-scalable over-complete independent component analysis (OICA). In this work, we propose the Transformed Independent Noise (TIN) condition, which checks for independence between a specific linear transformation of some measured variables and certain other measured variables. By leveraging the non-Gaussianity and higher-order statistics of data, TIN is informative about the graph structure among the unobserved target variables. By utilizing TIN, the ordered group decomposition of the causal model is identifiable. In other words, we could achieve what once required OICA to achieve by only conducting independence tests. Experimental results on both synthetic and real-world data demonstrate the effectiveness and reliability of our method."]]></description>
<dc:subject>to:NB causal_inference inference_to_latent_objects spirtes.peter zhang.kun to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b389406b2d4e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spirtes.peter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:zhang.kun"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-soc-030320-102100">
    <title>Causal Network Analysis | Annual Review of Sociology</title>
    <dc:date>2022-08-06T16:26:17+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-soc-030320-102100</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Fueled by recent advances in statistical modeling and the rapid growth of network data, social network analysis has become increasingly popular in sociology and related disciplines. However, a significant amount of work in the field has been descriptive and correlational, which prevents the findings from being more rigorously translated into practices and policies. This article provides a review of the popular models and methods for causal network analysis, with a focus on causal inference threats (such as measurement error, missing data, network endogeneity, contextual confounding, simultaneity, and collinearity) and potential solutions (such as instrumental variables, specialized experiments, and leveraging longitudinal data). It covers major models and methods for both network formation and network effects and for both sociocentric networks and egocentric networks. Lastly, this review also discusses future directions for causal network analysis."

--- Last tag applies to the proposed fixes.]]></description>
<dc:subject>to:NB to_read causal_inference network_data_analysis re:homophily_and_confounding social_networks color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c844f4b17fb8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:homophily_and_confounding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.08353">
    <title>[2206.08353] Towards Understanding How Machines Can Learn Causal Overhypotheses</title>
    <dc:date>2022-07-22T14:46:51+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.08353</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence. The extensive literature in cognitive science using the ``blicket detector'' environment shows that children are adept at many kinds of causal inference and learning. We propose to adapt that environment for machine learning agents. One of the key challenges for current machine learning algorithms is modeling and understanding causal overhypotheses: transferable abstract hypotheses about sets of causal relationships. In contrast, even young children spontaneously learn and use causal overhypotheses. In this work, we present a new benchmark -- a flexible environment which allows for the evaluation of existing techniques under variable causal overhypotheses -- and demonstrate that many existing state-of-the-art methods have trouble generalizing in this environment."]]></description>
<dc:subject>in_NB causal_inference causal_discovery artificial_intelligence cognitive_science gopnik.alison</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:92821459c251/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:artificial_intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cognitive_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gopnik.alison"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://jmlr.org/papers/v23/21-0082.html">
    <title>Rethinking Nonlinear Instrumental Variable Models through Prediction Validity</title>
    <dc:date>2022-07-15T12:26:19+00:00</dc:date>
    <link>https://jmlr.org/papers/v23/21-0082.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Instrumental variables (IV) are widely used in the social and health sciences in situations where a researcher would like to measure a causal effect but cannot perform an experiment. For valid causal inference in an IV model, there must be external (exogenous) variation that (i) has a sufficiently large impact on the variable of interest (called the relevance assumption) and where (ii) the only pathway through which the external variation impacts the outcome is via the variable of interest (called the exclusion restriction). For statistical inference, researchers must also make assumptions about the functional form of the relationship between the three variables. Current practice assumes (i) and (ii) are met, then postulates a functional form with limited input from the data. In this paper, we describe a framework that leverages machine learning to validate these typically unchecked but consequential assumptions in the IV framework, providing the researcher empirical evidence about the quality of the instrument given the data at hand. Central to the proposed approach is the idea of prediction validity. Prediction validity checks that error terms -- which should be independent from the instrument -- cannot be modeled with machine learning any better than a model that is identically zero. We use prediction validity to develop both one-stage and two-stage approaches for IV, and demonstrate their performance on an example relevant to climate change policy."]]></description>
<dc:subject>to_read regression instrumental_variables causal_inference mccormick.tyler rudin.cynthia re:ADAfaEPoV in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4accdfd21078/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:instrumental_variables"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mccormick.tyler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:rudin.cynthia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2108.09265">
    <title>[2108.09265] Efficient Online Estimation of Causal Effects by Deciding What to Observe</title>
    <dc:date>2022-07-14T18:31:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2108.09265</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Researchers often face data fusion problems, where multiple data sources are available, each capturing a distinct subset of variables. While problem formulations typically take the data as given, in practice, data acquisition can be an ongoing process. In this paper, we aim to estimate any functional of a probabilistic model (e.g., a causal effect) as efficiently as possible, by deciding, at each time, which data source to query. We propose online moment selection (OMS), a framework in which structural assumptions are encoded as moment conditions. The optimal action at each step depends, in part, on the very moments that identify the functional of interest. Our algorithms balance exploration with choosing the best action as suggested by current estimates of the moments. We propose two selection strategies: (1) explore-then-commit (OMS-ETC) and (2) explore-then-greedy (OMS-ETG), proving that both achieve zero asymptotic regret as assessed by MSE. We instantiate our setup for average treatment effect estimation, where structural assumptions are given by a causal graph and data sources may include subsets of mediators, confounders, and instrumental variables."]]></description>
<dc:subject>in_NB causal_inference low-regret_learning experimental_design lipton.zachary_c. childers.david</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:490828503859/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:low-regret_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experimental_design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lipton.zachary_c."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:childers.david"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.aeaweb.org/articles?id=10.1257/aer.101.3.532">
    <title>Oaxaca-Blinder as a Reweighting Estimator - American Economic Association</title>
    <dc:date>2022-07-09T18:59:16+00:00</dc:date>
    <link>https://www.aeaweb.org/articles?id=10.1257/aer.101.3.532</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The classic regression based estimator of counterfactual means studied by Ronald Oaxaca (1973) and Alan Blinder (1973) is shown to constitute a propensity score reweighting estimator based upon a linear model for the conditional odds of being treated."]]></description>
<dc:subject>to:NB regression inequality causal_inference via:donsker_class to_teach:statistics_of_inequality_and_discrimination</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:36e5fbd7447f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:donsker_class"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA10582?casa_token=RYQGxAm5NPsAAAAA:Gjw9Whp2sT1TTcF-EurC9U-K98m8jQ6Z1Tl6-PTOVvOZYU9vgik8XniEBql7ru0bqZ7U8aepTqF3">
    <title>Inference on Counterfactual Distributions - Chernozhukov - 2013 - Econometrica - Wiley Online Library</title>
    <dc:date>2022-07-09T18:58:01+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA10582?casa_token=RYQGxAm5NPsAAAAA:Gjw9Whp2sT1TTcF-EurC9U-K98m8jQ6Z1Tl6-PTOVvOZYU9vgik8XniEBql7ru0bqZ7U8aepTqF3</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Counterfactual distributions are important ingredients for policy analysis and decomposition analysis in empirical economics. In this article, we develop modeling and inference tools for counterfactual distributions based on regression methods. The counterfactual scenarios that we consider consist of ceteris paribus changes in either the distribution of covariates related to the outcome of interest or the conditional distribution of the outcome given covariates. For either of these scenarios, we derive joint functional central limit theorems and bootstrap validity results for regression-based estimators of the status quo and counterfactual outcome distributions. These results allow us to construct simultaneous confidence sets for function-valued effects of the counterfactual changes, including the effects on the entire distribution and quantile functions of the outcome as well as on related functionals. These confidence sets can be used to test functional hypotheses such as no-effect, positive effect, or stochastic dominance. Our theory applies to general counterfactual changes and covers the main regression methods including classical, quantile, duration, and distribution regressions. We illustrate the results with an empirical application to wage decompositions using data for the United States.
"As a part of developing the main results, we introduce distribution regression as a comprehensive and flexible tool for modeling and estimating the entire conditional distribution. We show that distribution regression encompasses the Cox duration regression and represents a useful alternative to quantile regression. We establish functional central limit theorems and bootstrap validity results for the empirical distribution regression process and various related functionals."]]></description>
<dc:subject>to:NB density_estimation regression causal_inference inequality via:donsker_class to_teach:statistics_of_inequality_and_discrimination</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4147b5ca4a38/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:density_estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:donsker_class"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.11603">
    <title>[1811.11603] Distribution Regression with Sample Selection, with an Application to Wage Decompositions in the UK</title>
    <dc:date>2022-07-09T18:57:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.11603</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We develop a distribution regression model under endogenous sample selection. This model is a semiparametric generalization of the Heckman selection model that accommodates much richer patterns of heterogeneity in the selection process and effect of the covariates. The model applies to continuous, discrete and mixed outcomes. We study the identification of the model, and develop a computationally attractive two-step method to estimate the model parameters, where the first step is a probit regression for the selection equation and the second step consists of multiple distribution regressions with selection corrections for the outcome equation. We construct estimators of functionals of interest such as actual and counterfactual distributions of latent and observed outcomes via plug-in rule. We derive functional central limit theorems for all the estimators and show the validity of multiplier bootstrap to carry out functional inference. We apply the methods to wage decompositions in the UK using new data. Here we decompose the difference between the male and female wage distributions into four effects: composition, wage structure, selection structure and selection sorting. After controlling for endogenous employment selection, we still find substantial gender wage gap -- ranging from 21% to 40% throughout the (latent) offered wage distribution that is not explained by observable labor market characteristics. We also uncover positive sorting for single men and negative sorting for married women that accounts for a substantive fraction of the gender wage gap at the top of the distribution. These findings can be interpreted as evidence of assortative matching in the marriage market and glass-ceiling in the labor market."

--- Last tag is "I should know this stuff", not "I should teach it to sophomores and juniors".]]></description>
<dc:subject>to:NB statistics density_estimation regression causal_inference inequality via:donsker_class to_teach:statistics_of_inequality_and_discrimination</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a84c4133e283/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:density_estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:donsker_class"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2204.04119">
    <title>[2204.04119] Bespoke Instrumental Variables for Causal Inference</title>
    <dc:date>2022-06-14T13:07:25+00:00</dc:date>
    <link>https://arxiv.org/abs/2204.04119</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many proposals for the identification of causal effects in the presence of unmeasured confounding require an instrumental variable or negative control that satisfies strong, untestable assumptions. In this paper, we will instead show how one can identify causal effects for a point exposure by using a measured confounder as a 'bespoke instrumental variable'. This strategy requires an external reference population that does not have access to the exposure, and a stability condition on the confounder outcome association between reference and target populations. Building on recent identification results of Richardson and Tchetgen Tchetgen (2021), we develop the semiparametric efficiency theory for a general bespoke instrumental variable model, and obtain a multiply robust locally efficient estimator of the average treatment effect in the treated."

--- Looks cool but I will be missing the talk here (2022-06-15, 11:00--12:00 Baker Hall 232M)]]></description>
<dc:subject>causal_inference instrumental_variables to_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f1ca9e948f35/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:instrumental_variables"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.00416">
    <title>[2206.00416] In the Eye of the Beholder: Robust Prediction with Causal User Modeling</title>
    <dc:date>2022-06-09T10:12:23+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.00416</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Accurately predicting the relevance of items to users is crucial to the success of many social platforms. Conventional approaches train models on logged historical data; but recommendation systems, media services, and online marketplaces all exhibit a constant influx of new content -- making relevancy a moving target, to which standard predictive models are not robust. In this paper, we propose a learning framework for relevance prediction that is robust to changes in the data distribution. Our key observation is that robustness can be obtained by accounting for how users causally perceive the environment. We model users as boundedly-rational decision makers whose causal beliefs are encoded by a causal graph, and show how minimal information regarding the graph can be used to contend with distributional changes. Experiments in multiple settings demonstrate the effectiveness of our approach."]]></description>
<dc:subject>to:NB recommender_systems causal_inference graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a3ca652cf3ca/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:recommender_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.01249">
    <title>[2206.01249] Single-World Intervention Graphs for Defining, Identifying, and Communicating Estimands in Clinical Trials</title>
    <dc:date>2022-06-09T08:32:05+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.01249</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Confusion often arises when attempting to articulate target estimand(s) of a clinical trial in plain language. We aim to rectify this confusion by using a type of causal graph called the Single-World Intervention Graph (SWIG) to provide a visual representation of the estimand that can be effectively communicated to interdisciplinary stakeholders. These graphs not only display estimands, but also illustrate the assumptions under which a causal estimand is identifiable by presenting the graphical relationships between the treatment, intercurrent events, and clinical outcomes. To demonstrate its usefulness in pharmaceutical research, we present examples of SWIGs for various intercurrent event strategies specified in the ICH E9(R1) addendum, as well as an example from a real-world clinical trial for chronic pain. Latex code to generate all the SWIGs shown is this paper is made available. We advocate clinical trialists adopt the use of SWIGs in their estimand discussions during the planning stages of their studies."]]></description>
<dc:subject>to:NB graphical_models causal_inference experimental_design</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1b9f0627bcae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experimental_design"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-criminol-030920-112506">
    <title>The Impact of Incarceration on Recidivism | Annual Review of Criminology</title>
    <dc:date>2022-06-09T07:54:01+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-criminol-030920-112506</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The US prison population stands at 1.43 million persons, with an additional 740,000 persons in local jails. Nearly all will eventually return to society. This review examines the available evidence on how the experience of incarceration is likely to impact the probability that formerly incarcerated individuals will reoffend. Our focus is on two types of studies, those based on the random assignments of cases to judges, called judge instrumental-variable studies, and those based on discontinuities in sentence severity in sentencing grids, called regression discontinuity studies. Both types of studies are designed to account for selection bias in nonexperimental estimates of the impact of incarceration on reoffending. Most such studies find that the experience of postconviction imprisonment has little impact on the probability of recidivism. A smaller number of studies do, however, find significant effects, both positive and negative. The negative, recidivism-reducing effects are mostly in settings in which rehabilitative programming is emphasized and the positive, criminogenic effects are found in settings in which such programming is not emphasized. The findings of studies of pretrial incarceration are more consistent—most find a deleterious effect on postrelease reoffending. We also conclude that additional work is needed to better understand the heterogeneous effects of incarceration as well as the mechanisms through which incarceration effects, when observed, are generated. For policy, our conclusion of the generally deleterious effect of pretrial detention adds to a larger body of evidence pointing to the social value of limiting its use."

--- The "to_teach" tags are really "to mention, when the inevitable questions about what we're doing modeling the COMPAS/ProPublica data come up".]]></description>
<dc:subject>to:NB crime causal_inference to_teach:data-mining to_teach:statistics_of_inequality_and_discrimination nagin.daniel</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f5c024c3bf2d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:crime"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nagin.daniel"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/biomet/article-abstract/109/2/551/6308304?redirectedFrom=fulltext">
    <title>On the inconsistency of matching without replacement | Biometrika | Oxford Academic</title>
    <dc:date>2022-06-06T13:00:21+00:00</dc:date>
    <link>https://academic.oup.com/biomet/article-abstract/109/2/551/6308304?redirectedFrom=fulltext</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The paper shows that matching without replacement on propensity scores produces estimators that generally are inconsistent for the average treatment effect of the treated. To achieve consistency, practitioners must either assume that no units exist with propensity scores greater than 1/2 or assume that there is no confounding among such units. The result is not driven by the use of propensity scores, and similar artifacts arise when matching on other scores as long as it is without replacement."]]></description>
<dc:subject>to:NB causal_inference matching</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:61bd5aebf433/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:matching"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/full/10.1080/10618600.2022.2071905">
    <title>A General Method for Deriving Tight Symbolic Bounds on Causal Effects</title>
    <dc:date>2022-06-06T12:59:45+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/full/10.1080/10618600.2022.2071905</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A causal query will commonly not be identifiable from observed data, in which case no estimator of the query can be contrived without further assumptions or measured variables, regardless of the amount or precision of the measurements of observed variables. However, it may still be possible to derive symbolic bounds on the query in terms of the distribution of observed variables. Bounds, numeric or symbolic, can often be more valuable than a statistical estimator derived under implausible assumptions. Symbolic bounds, however, provide a measure of uncertainty and information loss due to the lack of an identifiable estimand even in the absence of data. We develop and describe a general approach for computation of symbolic bounds and characterize a class of settings in which our method is guaranteed to provide tight valid bounds. This expands the known settings in which tight causal bounds are solutions to linear programs. We also prove that our method can provide valid and possibly informative symbolic bounds that are not guaranteed to be tight in a larger class of problems. We illustrate the use and interpretation of our algorithms in three examples in which we derive novel symbolic bounds."]]></description>
<dc:subject>to:NB causal_inference partial_identification optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cafc00f3a79c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:partial_identification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2201.07055">
    <title>[2201.07055] Close Enough? A Large-Scale Exploration of Non-Experimental Approaches to Advertising Measurement</title>
    <dc:date>2022-06-05T22:17:22+00:00</dc:date>
    <link>https://arxiv.org/abs/2201.07055</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Randomized controlled trials (RCTs) have become increasingly popular in both marketing practice and academia. However, RCTs are not always available as a solution for advertising measurement, necessitating the use of observational methods. We present the first large-scale exploration of two observational methods, double/debiased machine learning (DML) and stratified propensity score matching (SPSM). Specifically, we analyze 663 large-scale experiments at Facebook, each of which is described using over 5,000 user- and experiment-level features. Although DML performs better than SPSM, neither method performs well, despite using deep learning models to implement the propensity scores and outcome models. The median absolute percentage point difference in lift is 115%, 107%, and 62% for upper, mid, and lower funnel outcomes, respectively. These are large measurement errors, given that the median RCT lifts are 28%, 19%, and 6% for the funnel outcomes, respectively. We further leverage our large sample of experiments to characterize the circumstances under which each method performs comparatively better. However, broadly speaking, our results suggest that state-of-the-art observational methods are unable to recover the causal effect of online advertising at Facebook. We conclude that observational methods for estimating ad effectiveness may not work until advertising platforms log auction-specific features for modeling."]]></description>
<dc:subject>to:NB causal_inference advertising facebook social_media</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ba09b0070350/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:advertising"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:facebook"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_media"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2205.01593">
    <title>[2205.01593] Causal Regularization: On the trade-off between in-sample risk and out-of-sample risk guarantees</title>
    <dc:date>2022-05-11T16:49:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2205.01593</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In recent decades, a number of ways of dealing with causality in practice, such as propensity score matching, the PC algorithm and invariant causal prediction, have been introduced. Besides its interpretational appeal, the causal model provides the best out-of-sample prediction guarantees. In this paper, we study the identification of causal-like models from in-sample data that provide out-of-sample risk guarantees when predicting a target variable from a set of covariates.
"Whereas ordinary least squares provides the best in-sample risk with limited out-of-sample guarantees, causal models have the best out-of-sample guarantees but achieve an inferior in-sample risk. By defining a trade-off of these properties, we introduce causal regularization. As the regularization is increased, it provides estimators whose risk is more stable across sub-samples at the cost of increasing their overall in-sample risk. The increased risk stability is shown to lead to out-of-sample risk guarantees. We provide finite sample risk bounds for all models and prove the adequacy of cross-validation for attaining these bounds."]]></description>
<dc:subject>to:NB causal_inference learning_theory prediction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b92b191c8fa9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w29691">
    <title>Two-Way Fixed Effects and Differences-in-Differences with Heterogeneous Treatment Effects: A Survey | NBER</title>
    <dc:date>2022-03-19T23:06:05+00:00</dc:date>
    <link>https://www.nber.org/papers/w29691</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Linear regressions with period and group fixed effects are widely used to estimate policies' effects: 26 of the 100 most cited papers published by the American Economic Review from 2015 to 2019 estimate such regressions. It has recently been show that those regressions may produce misleading estimates, if the policy's effect is heterogeneous between groups or over time, as is often the case. This survey reviews a fast-growing literature that documents this issue, and that proposes alternative estimators robust to heterogeneous effects."

--- For "recently been shown", read "was obvious if you stopped to think about it just one moment", but more joy over the returned prodigal, etc., etc.]]></description>
<dc:subject>to:NB linear_regression causal_inference econometrics re:TALR</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:430867822da3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:econometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:TALR"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://research.google/pubs/pub49197/">
    <title>Predictive State Propensity Subclassification (PSPS): A causal inference method for optimal data-driven propensity score stratification – Google Research</title>
    <dc:date>2022-03-16T14:27:13+00:00</dc:date>
    <link>https://research.google/pubs/pub49197/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce Predictive State Propensity Subclassification (PSPS), a novel estimation method for undertaking causal inference from observational studies. The methodology applies to both discrete and continuous treatments and can estimate unit-level and population-level average treatment effects. PSPS combines propensity and outcome models into one encompassing probabilistic model, which can be jointly estimated using maximum likelihood or Bayesian inference. We give a detailed overview on the TensorFlow implementation for likelihood optimization and show via large-scale simulations that it outperforms several state of the art methods -- both in terms of bias and variance for average as well as unit-level treatment effects. Finally we illustrate the methodology and algorithms on standard datasets in the literature."

--- Forthcoming, CLeaR 2022 [https://www.cclear.cc/Acceptedpapers]; obviously I wasn't involved in the refereeing because GMG was my Ph.D. student.]]></description>
<dc:subject>to:NB causal_inference statistics estimation prediction_processes kith_and_kin goerg.georg_m.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:07155ec09ca0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goerg.georg_m."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w29820">
    <title>Systemic Discrimination: Theory and Measurement | NBER</title>
    <dc:date>2022-03-15T13:21:46+00:00</dc:date>
    <link>https://www.nber.org/papers/w29820</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Economics tends to define and measure discrimination as disparities stemming from the direct (causal) effects of protected group membership. But work in other fields notes that such measures are incomplete, as they can miss important systemic (i.e. indirect) channels. For example, racial disparities in criminal records due to discrimination in policing can lead to disparate outcomes for equally-qualified job applicants despite a race-neutral hiring rule. We develop new tools for modeling and measuring both direct and systemic forms of discrimination. We define systemic discrimination as emerging from group-based differences in non-group characteristics, conditional on a measure of individual qualification. We formalize sources of systemic discrimination as disparities in signaling technologies and opportunities for skill development. Notably, standard tools for measuring direct discrimination, such as audit or correspondence studies, cannot detect systemic discrimination. We propose a measure of systemic discrimination based on a novel decomposition of total discrimination—disparities that condition on underlying qualification—into direct and systemic components. This decomposition highlights the type of data needed to measure systemic discrimination and guides identification strategies in both observational and (quasi-)experimental data. We illustrate these tools in two hiring experiments. Our findings highlight how discrimination in one domain, due to either accurate beliefs or bias, can drive persistent disparities through systemic channels even when direct discrimination is eliminated."

--- I am going to be very, very interested to <strike>see how the way they set up their decomposition presupposes their conclusions</strike> examine their identification assumptions.]]></description>
<dc:subject>to:NB discrimination econometrics causal_inference statistics to_teach:statistics_of_inequality_and_discrimination color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:acabb2f1cc5f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:econometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2201.13451">
    <title>[2201.13451] Causal Inference with Orthogonalized Regression Adjustment: Taming the Phantom</title>
    <dc:date>2022-02-15T04:54:07+00:00</dc:date>
    <link>https://arxiv.org/abs/2201.13451</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Standard regression adjustment gives inconsistent estimates of causal effects when there are time-varying treatment effects and time-varying covariates. Loosely speaking, the issue is that some covariates are post-treatment variables because they may be affected by prior treatment status, and regressing out post-treatment variables causes bias. More precisely, the bias is due to certain non-confounding latent variables that create colliders in the causal graph. These latent variables, which we call phantoms, do not harm the identifiability of the causal effect, but they render naive regression estimates inconsistent. Motivated by this, we ask: how can we modify regression methods so that they hold up even in the presence of phantoms? We develop an estimator for this setting based on regression modeling (linear, log-linear, probit and Cox regression), proving that it is consistent for the causal effect of interest. In particular, the estimator is a regression model fit with a simple adjustment for collinearity, making it easy to understand and implement with standard regression software. From a causal point of view, the proposed estimator is an instance of the parametric g-formula. Importantly, we show that our estimator is immune to the null paradox that plagues most other parametric g-formula methods."]]></description>
<dc:subject>to:NB to_read causal_inference kith_and_kin</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:42f73d436288/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w29709">
    <title>When is TSLS Actually LATE? | NBER</title>
    <dc:date>2022-02-02T23:00:41+00:00</dc:date>
    <link>https://www.nber.org/papers/w29709</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Linear instrumental variable estimators, such as two-stage least squares (TSLS), are commonly interpreted as estimating positively weighted averages of causal effects, referred to as local average treatment effects (LATEs). We examine whether the LATE interpretation actually applies to the types of TSLS specifications that are used in practice. We show that if the specification includes covariates, which most empirical work does, then the LATE interpretation does not apply in general. Instead, the TSLS estimator will in general reflect treatment effects for both compliers and always/never-takers, and some of the treatment effects for the always/never-takers will necessarily be negatively weighted. We show that the only specifications that have a LATE interpretation are "saturated" specifications that control for covariates nonparametrically, implying that such specifications are both sufficient and necessary for TSLS to have a LATE interpretation, at least without additional parametric assumptions. This result is concerning because, as we document, empirical researchers almost never control for covariates nonparametrically, and rarely discuss or justify parametric specifications of covariates. We develop a decomposition that quantifies the extent to which the usual LATE interpretation fails. We apply the decomposition to four empirical analyses and find strong evidence that the LATE interpretation of TSLS is far from accurate for the types of specifications actually used in practice."]]></description>
<dc:subject>instrumental_variables causal_inference nonparametrics re:ADAfaEPoV in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4f733f8f89d2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:instrumental_variables"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-051120-111443">
    <title>Testing Causal Theories with Learned Proxies | Annual Review of Political Science</title>
    <dc:date>2022-01-30T02:02:34+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-051120-111443</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Social scientists commonly use computational models to estimate proxies of unobserved concepts, then incorporate these proxies into subsequent tests of their theories. The consequences of this practice, which occurs in over two-thirds of recent computational work in political science, are underappreciated. Imperfect proxies can reflect noise and contamination from other concepts, producing biased point estimates and standard errors. We demonstrate how analysts can use causal diagrams to articulate theoretical concepts and their relationships to estimated proxies, then apply straightforward rules to assess which conclusions are rigorously supportable. We formalize and extend common heuristics for “signing the bias”—a technique for reasoning about unobserved confounding—to scenarios with imperfect proxies. Using these tools, we demonstrate how, in often-encountered research settings, proxy-based analyses allow for valid tests for the existence and direction of theorized effects. We conclude with best-practice recommendations for the rapidly growing literature using learned proxies to test causal theories."]]></description>
<dc:subject>causal_inference social_science_methodology social_measurement to_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b2d4f740c120/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_science_methodology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_measurement"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.04103">
    <title>[2104.04103] Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters</title>
    <dc:date>2022-01-24T17:27:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.04103</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Causal decision making (CDM) based on machine learning has become a routine part of business. Businesses algorithmically target offers, incentives, and recommendations to affect consumer behavior. Recently, we have seen an acceleration of research related to CDM and causal effect estimation (CEE) using machine-learned models. This article highlights an important perspective: CDM is not the same as CEE, and counterintuitively, accurate CEE is not necessary for accurate CDM. Our experience is that this is not well understood by practitioners or most researchers. Technically, the estimand of interest is different, and this has important implications both for modeling and for the use of statistical models for CDM. We draw on prior research to highlight three implications. (1) We should consider carefully the objective function of the causal machine learning, and if possible, optimize for accurate treatment assignment rather than for accurate effect-size estimation. (2) Confounding does not have the same effect on CDM as it does on CEE. The upshot is that for supporting CDM it may be just as good or even better to learn with confounded data as with unconfounded data. Finally, (3) causal statistical modeling may not be necessary to support CDM because a proxy target for statistical modeling might do as well or better. This third observation helps to explain at least one broad common CDM practice that seems wrong at first blush: the widespread use of non-causal models for targeting interventions. The last two implications are particularly important in practice, as acquiring (unconfounded) data on all counterfactuals can be costly and often impracticable. These observations open substantial research ground. We hope to facilitate research in this area by pointing to related articles from multiple contributing fields, including two dozen articles published the last three to four years."

--- ETA after reading: Think of decision-making as a classification problem, rather than estimation.  If your classifier mis-estimates Pr(Y|X=x), but you're nonetheless on the correct side of 1/2 (or whatever your optimal boundary might be), it doesn't matter for classification accuracy!  So if you over-estimate the benefits of treatment for those you decide to treat, well, you're still treating them...]]></description>
<dc:subject>causal_inference decision-making via:vaguery to_teach:data-mining provost.foster have_read blogged in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4546e3e7d5f3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:vaguery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:provost.foster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:blogged"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.jstor.org/stable/20684590?seq=1#metadata_info_tab_contents">
    <title>Does Indiscriminate Violence Incite Insurgent Attacks? Evidence from Chechnya on JSTOR</title>
    <dc:date>2021-12-13T06:14:16+00:00</dc:date>
    <link>https://www.jstor.org/stable/20684590?seq=1#metadata_info_tab_contents</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to:NB to_read causal_inference war via:henry_farrell</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c0038c3fd650/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:war"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:henry_farrell"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2110.03973">
    <title>[2110.03973] Many Proxy Controls</title>
    <dc:date>2021-12-05T17:06:35+00:00</dc:date>
    <link>https://arxiv.org/abs/2110.03973</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A recent literature considers causal inference using noisy proxies for unobserved confounding factors. The proxies are divided into two sets that are independent conditional on the confounders. One set of proxies are `negative control treatments' and the other are `negative control outcomes'. Existing work applies to low-dimensional settings with a fixed number of proxies and confounders. In this work we consider linear models with many proxy controls and possibly many confounders. A key insight is that if each group of proxies is strictly larger than the number of confounding factors, then a matrix of nuisance parameters has a low-rank structure and a vector of nuisance parameters has a sparse structure. We can exploit the rank-restriction and sparsity to reduce the number of free parameters to be estimated. The number of unobserved confounders is not known a priori but we show that it is identified, and we apply penalization methods to adapt to this quantity. We provide an estimator with a closed-form as well as a doubly-robust estimator that must be evaluated using numerical methods. We provide conditions under which our doubly-robust estimator is uniformly root-n consistent, asymptotically centered normal, and our suggested confidence intervals have asymptotically correct coverage. We provide simulation evidence that our methods achieve better performance than existing approaches in high dimensions, particularly when the number of proxies is substantially larger than the number of confounders."]]></description>
<dc:subject>to:NB causal_inference inference_to_latent_objects to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6a3b1e623127/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2109.13471">
    <title>[2109.13471] An Automated Approach to Causal Inference in Discrete Settings</title>
    <dc:date>2021-10-18T13:53:49+00:00</dc:date>
    <link>https://arxiv.org/abs/2109.13471</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["When causal quantities cannot be point identified, researchers often pursue partial identification to quantify the range of possible values. However, the peculiarities of applied research conditions can make this analytically intractable. We present a general and automated approach to causal inference in discrete settings. We show causal questions with discrete data reduce to polynomial programming problems, and we present an algorithm to automatically bound causal effects using efficient dual relaxation and spatial branch-and-bound techniques. The user declares an estimand, states assumptions, and provides data (however incomplete or mismeasured). The algorithm then searches over admissible data-generating processes and outputs the most precise possible range consistent with available information -- i.e., sharp bounds -- including a point-identified solution if one exists. Because this search can be computationally intensive, our procedure reports and continually refines non-sharp ranges that are guaranteed to contain the truth at all times, even when the algorithm is not run to completion. Moreover, it offers an additional guarantee we refer to as ϵ-sharpness, characterizing the worst-case looseness of the incomplete bounds. Analytically validated simulations show the algorithm accommodates classic obstacles, including confounding, selection, measurement error, noncompliance, and nonresponse."]]></description>
<dc:subject>to:NB causal_inference to_read shpitser.ilya optimization partial_identification</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5317f9815532/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:shpitser.ilya"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:partial_identification"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2109.15154">
    <title>[2109.15154] Causal Matrix Completion</title>
    <dc:date>2021-10-11T02:22:54+00:00</dc:date>
    <link>https://arxiv.org/abs/2109.15154</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Matrix completion is the study of recovering an underlying matrix from a sparse subset of noisy observations. Traditionally, it is assumed that the entries of the matrix are "missing completely at random" (MCAR), i.e., each entry is revealed at random, independent of everything else, with uniform probability. This is likely unrealistic due to the presence of "latent confounders", i.e., unobserved factors that determine both the entries of the underlying matrix and the missingness pattern in the observed matrix. For example, in the context of movie recommender systems -- a canonical application for matrix completion -- a user who vehemently dislikes horror films is unlikely to ever watch horror films. In general, these confounders yield "missing not at random" (MNAR) data, which can severely impact any inference procedure that does not correct for this bias. We develop a formal causal model for matrix completion through the language of potential outcomes, and provide novel identification arguments for a variety of causal estimands of interest. We design a procedure, which we call "synthetic nearest neighbors" (SNN), to estimate these causal estimands. We prove finite-sample consistency and asymptotic normality of our estimator. Our analysis also leads to new theoretical results for the matrix completion literature. In particular, we establish entry-wise, i.e., max-norm, finite-sample consistency and asymptotic normality results for matrix completion with MNAR data. As a special case, this also provides entry-wise bounds for matrix completion with MCAR data. Across simulated and real data, we demonstrate the efficacy of our proposed estimator."]]></description>
<dc:subject>to:NB low-rank_approximation missing_data causal_inference nearest_neighbors to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d4294b0e4a48/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:low-rank_approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:missing_data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nearest_neighbors"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2109.00725">
    <title>[2109.00725] Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond</title>
    <dc:date>2021-09-23T22:53:55+00:00</dc:date>
    <link>https://arxiv.org/abs/2109.00725</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has traditionally placed more emphasis on predictive tasks. This distinction is beginning to fade, with an emerging area of interdisciplinary research at the convergence of causal inference and language processing. Still, research on causality in NLP remains scattered across domains without unified definitions, benchmark datasets and clear articulations of the remaining challenges. In this survey, we consolidate research across academic areas and situate it in the broader NLP landscape. We introduce the statistical challenge of estimating causal effects, encompassing settings where text is used as an outcome, treatment, or as a means to address confounding. In addition, we explore potential uses of causal inference to improve the performance, robustness, fairness, and interpretability of NLP models. We thus provide a unified overview of causal inference for the computational linguistics community."]]></description>
<dc:subject>to:NB to_read causal_inference natural_language_processing text_mining</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4b632534e148/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_language_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://dl.acm.org/doi/abs/10.1145/3447548.3470795">
    <title>Causal Inference from Network Data | Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &amp; Data Mining</title>
    <dc:date>2021-09-06T13:22:45+00:00</dc:date>
    <link>https://dl.acm.org/doi/abs/10.1145/3447548.3470795</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This tutorial presents state-of-the-art research on causal inference from network data in the presence of interference. We start by motivating research in this area with real-world applications, such as measuring influence in social networks and market experimentation. We discuss the challenges of applying existing causal inference techniques designed for independent and identically distributed (i.i.d.) data to relational data, some of the solutions that currently exist and the gaps and opportunities for future research. We present existing network experiment designs for measuring different possible effects of interest. Then we focus on causal inference from observational data, its representation, identification, and estimation. We conclude with research on causal discovery in networks."]]></description>
<dc:subject>to:NB to_read network_data_analysis causal_inference causal_discovery re:homophily_and_confounding</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c59868f8ecfb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:homophily_and_confounding"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.aeaweb.org/articles?id=10.1257/aer.20200513">
    <title>Media, Pulpit, and Populist Persuasion: Evidence from Father Coughlin - American Economic Association</title>
    <dc:date>2021-08-30T15:11:11+00:00</dc:date>
    <link>https://www.aeaweb.org/articles?id=10.1257/aer.20200513</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["I study the political impact of the first populist radio personality in American history. Father Charles Coughlin blended populist demagoguery, anti-Semitism, and fascist sympathies to create a hugely popular radio program that attracted 30 million weekly listeners in the 1930s. I find that exposure to Father Coughlin's anti-Roosevelt broadcast reduced Franklin D. Roosevelt's vote share in the 1936 presidential election. Coughlin's effects were larger among Catholics and persisted after Coughlin left the air. Moreover, places more exposed to Coughlin's broadcast were more likely to form a local branch of the pro-Nazi German-American Bund and sold fewer war bonds during World War II."

--- I'll be interested to see how it gets around the obvious selection issue, that places where lots of people chose to listen to Coughlin, and/or places where broadcasters chose to re-broadcast him, were apt to be reactionary people and places anyway.  (Also, why on Earth is this in AER, rather than _American Historical Review_ or the like? [That's a rhetorical question, I know why...])]]></description>
<dc:subject>to:NB causal_inference american_history running_dogs_of_reaction media_effects</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:349250674e1b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:american_history"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:running_dogs_of_reaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:media_effects"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.aeaweb.org/articles?id=10.1257/aer.20190415">
    <title>The Effects of Parental and Sibling Incarceration: Evidence from Ohio - American Economic Association</title>
    <dc:date>2021-08-30T14:49:58+00:00</dc:date>
    <link>https://www.aeaweb.org/articles?id=10.1257/aer.20190415</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Every year, millions of Americans experience the incarceration of a family member. Using 30 years of administrative data from Ohio and exploiting differing incarceration propensities of randomly assigned judges, this paper provides the first quasi-experimental estimates of the effects of parental and sibling incarceration in the United States. Parental incarceration has beneficial effects on some important outcomes for children, reducing their likelihood of incarceration by 4.9 percentage points and improving their adult neighborhood quality. While estimates on academic performance and teen parenthood are imprecise, we reject large positive or negative effects. Sibling incarceration leads to similar reductions in criminal activity."]]></description>
<dc:subject>to:NB crime causal_inference color_me_skeptical prison</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7ee3653c0727/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:crime"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prison"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-032015-010015">
    <title>Race as a Bundle of Sticks: Designs that Estimate Effects of Seemingly Immutable Characteristics | Annual Review of Political Science</title>
    <dc:date>2021-08-23T17:11:56+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-032015-010015</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Although understanding the role of race, ethnicity, and identity is central to political science, methodological debates persist about whether it is possible to estimate the effect of something immutable. At the heart of the debate is an older theoretical question: Is race best understood under an essentialist or constructivist framework? In contrast to the “immutable characteristics” or essentialist approach, we argue that race should be operationalized as a “bundle of sticks” that can be disaggregated into elements. With elements of race, causal claims may be possible using two designs: (a) studies that measure the effect of exposure to a racial cue and (b) studies that exploit within-group variation to measure the effect of some manipulable element. These designs can reconcile scholarship on race and causation and offer a clear framework for future research."]]></description>
<dc:subject>to:NB social_science_methodology causal_inference to_teach:statistics_of_inequality_and_discrimination</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b70ed529ccd2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_science_methodology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>