<?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://www.cambridge.org/core/journals/philosophy-of-science/article/case-for-time-in-causal-dags/FB8A5FA21249300B5250358B21A3E26D?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Articles"/>
	<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/2308.07037"/>
	<rdf:li rdf:resource="https://philpapers.org/rec/KINBCC"/>
	<rdf:li rdf:resource="https://www.journals.uchicago.edu/doi/abs/10.1086/691274"/>
	<rdf:li rdf:resource="https://proceedings.mlr.press/v151/baak22a.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.08120"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/abs/10.1080/13569317.2022.2138293?journalCode=cjpi20"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2305.11561"/>
	<rdf:li rdf:resource="https://link.springer.com/chapter/10.1007/1-4020-4876-9_5"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.05829"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.06124"/>
	<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://arxiv.org/abs/2108.03099"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2206.01152"/>
	<rdf:li rdf:resource="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/Total-positivity-in-exponential-families-with-application-to-binary-variables/10.1214/20-AOS2007.short"/>
	<rdf:li rdf:resource="https://psyarxiv.com/kjh2f"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.02180"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2102.10324"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.05694"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.03969"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2102.13384"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.10350"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.06221"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/full/10.1080/01621459.2021.1874961"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.09271"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2006.11970"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.03501"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.03093"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.02332"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-economics-072219-111921"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2006.11937"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.10980"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.11281"/>
	<rdf:li rdf:resource="https://jmlr.org/papers/v21/20-175.html"/>
	<rdf:li rdf:resource="https://journals.sagepub.com/doi/abs/10.1177/0049124120926208"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.08154"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.05269"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1607677245"/>
	<rdf:li rdf:resource="https://www.aeaweb.org/articles?id=10.1257/aer.20191099"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.10854"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-031017-100053"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.ejs/1605582080"/>
	<rdf:li rdf:resource="https://ieeexplore.ieee.org/document/8804234"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2009.12246"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.03662"/>
	<rdf:li rdf:resource="https://link.springer.com/chapter/10.1007/978-94-011-5014-9_16"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1023/A:1009602825894"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2004.10984"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11229-018-02014-7"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11336-017-9557-x"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.08364"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1911.10114"/>
	<rdf:li rdf:resource="https://academic.oup.com/biomet/article-abstract/106/4/973/5573229"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1911.02700"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.12993"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.10134"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.02997"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1807.02877"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.13186"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.13189"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.09141"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.07186"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.09596#"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.06282"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.03586"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/0804.4451"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.05418"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.01577"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.cambridge.org/core/journals/philosophy-of-science/article/case-for-time-in-causal-dags/FB8A5FA21249300B5250358B21A3E26D?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Articles">
    <title>The Case For Time in Causal DAGs | Philosophy of Science | Cambridge Core</title>
    <dc:date>2026-06-24T12:55:55+00:00</dc:date>
    <link>https://www.cambridge.org/core/journals/philosophy-of-science/article/case-for-time-in-causal-dags/FB8A5FA21249300B5250358B21A3E26D?WT.mc_id=New%2520Cambridge%2520Alert%2520-%2520Articles</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We make the case for incorporating a notion of time into causal directed acyclic graphs (DAGs). We demonstrate that nontemporal causal DAGs are ambiguous and obstruct justification of the acyclicity assumption. Assuming that causes precede effects, causal relationships are relative to the time order, and causal DAGs require temporal qualification. We propose a formalization via composite causal variables that refer to quantities at one or multiple time points. We emphasize that the acyclicity assumption requires different justifications depending on whether the time order allows cycles. We conclude by discussing implications for the interpretation and applicability of DAGs as causal models."]]></description>
<dc:subject>to:NB graphical_models causality philosophy_of_science</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:90a1d2ee3253/</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:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:philosophy_of_science"/>
</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/2308.07037">
    <title>[2308.07037] Bayesian Flow Networks</title>
    <dc:date>2025-03-10T13:55:12+00:00</dc:date>
    <link>https://arxiv.org/abs/2308.07037</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian inference in the light of noisy data samples, then passed as input to a neural network that outputs a second, interdependent distribution. Starting from a simple prior and iteratively updating the two distributions yields a generative procedure similar to the reverse process of diffusion models; however it is conceptually simpler in that no forward process is required. Discrete and continuous-time loss functions are derived for continuous, discretised and discrete data, along with sample generation procedures. Notably, the network inputs for discrete data lie on the probability simplex, and are therefore natively differentiable, paving the way for gradient-based sample guidance and few-step generation in discrete domains such as language modelling. The loss function directly optimises data compression and places no restrictions on the network architecture. In our experiments BFNs achieve competitive log-likelihoods for image modelling on dynamically binarized MNIST and CIFAR-10, and outperform all known discrete diffusion models on the text8 character-level language modelling task."]]></description>
<dc:subject>to:NB graphical_models neural_networks simulation statistics computational_statistics to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4f89537c0697/</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:neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://philpapers.org/rec/KINBCC">
    <title>David Kinney &amp; Tania Lombrozo, Building Compressed Causal Models of the World - PhilPapers</title>
    <dc:date>2024-12-11T19:55:08+00:00</dc:date>
    <link>https://philpapers.org/rec/KINBCC</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A given causal system can be represented in a variety of ways. How do agents determine which variables to include in their causal representations, and at what level of granularity? Using techniques from Bayesian networks, information theory, and decision theory, we develop a formal theory according to which causal representations reflect a trade-off between compression and informativeness, where the optimal trade-off depends on the decision-theoretic value of information for a given agent in a given context. This theory predicts that, all else being equal, agents prefer causal models that are as compressed as possible. When compression is associated with information loss, however, all else is not equal, and our theory predicts that agents will favor compressed models only when the information they sacrifice is not informative with respect to the agent’s anticipated decisions. We then show, across six studies reported here (N=2,364) and one study reported in the supplemental materials (N=182), that participants’ preferences over causal models are in keeping with the predictions of our theory. Our theory offers a unification of different dimensions of causal evaluation identified within the philosophy of science (proportionality and stability), and contributes to a more general picture of human cognition according to which the capacity to create compressed (causal) representations plays a central role"]]></description>
<dc:subject>to:NB cognitive_science graphical_models causality information_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ebc6286ac206/</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:cognitive_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.journals.uchicago.edu/doi/abs/10.1086/691274">
    <title>Belief Network Analysis: A Relational Approach to Understanding the Structure of Attitudes1 | American Journal of Sociology: Vol 122, No 5</title>
    <dc:date>2024-12-11T19:50:45+00:00</dc:date>
    <link>https://www.journals.uchicago.edu/doi/abs/10.1086/691274</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many accounts of political belief systems conceive of them as networks of interrelated opinions, in which some beliefs are central and others peripheral. This article formally shows how such structural features can be used to construct direct measures of belief centrality in a network of correlations. This method is applied to the 2000 ANES data, which have been used to argue that political beliefs are organized around parenting schemas. This structural approach instead yields results consistent with the central role of political identity, which individuals may use as the organizing heuristic to filter information from the political field. In light of recent accounts of belief system heterogeneity, a search for population heterogeneity in this organizing logic was undertaken first by comparing 44 demographic subpopulations and then using inductive techniques. Contra these recent accounts, the study finds that belief systems of different groups vary in the amount of organization but not in the logic that organizes them."

--- Last tag is a guess based on the abstract.]]></description>
<dc:subject>to:NB causal_discovery ideology political_science sociology graphical_models of_course_its_really_a_spin_glass</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4281f10e72a8/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ideology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:political_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sociology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<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://proceedings.mlr.press/v151/baak22a.html">
    <title>Synthsonic: Fast, Probabilistic modeling and Synthesis of Tabular Data</title>
    <dc:date>2024-12-09T21:40:14+00:00</dc:date>
    <link>https://proceedings.mlr.press/v151/baak22a.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The creation of realistic, synthetic datasets has several purposes with growing demand in recent times, e.g. privacy protection and other cases where real data cannot be easily shared. A multitude of primarily neural networks (NNs), e.g. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), or Bayesian Network (BN) approaches have been created to tackle this problem, however these require extensive compute resources, lack interpretability, and in some instances lack replication fidelity as well. We propose a hybrid, probabilistic approach for synthesizing pairwise independent tabular data, called Synthsonic. A sequence of well-understood, invertible statistical transformations removes first-order correlations, then a Bayesian Network jointly models continuous and categorical variables, and a calibrated discriminative learner captures the remaining dependencies. Replication studies on MIT’s SDGym benchmark show marginally or significantly better performance than all prior BN-based approaches, while being competitive with NN-based approaches (first place in 10 out of 13 benchmark datasets). The computational time required to learn the data distribution is at least one order of magnitude lower than the NN methods. Furthermore, inspecting intermediate results during the synthetic data generation allows easy diagnostics and tailored corrections. We believe the combination of out-of-the-box performance, speed and interpretability make this method a significant addition to the synthetic data generation..."]]></description>
<dc:subject>to:NB computational_statistics simulation graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a839fb404ad2/</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:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.08120">
    <title>[2206.08120] Simultaneous Estimation of Graphical Models by Neighborhood Selection</title>
    <dc:date>2023-06-28T16:15:37+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.08120</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In many applications concerning statistical graphical models the data originate from several subpopulations that share similarities but have also significant differences. This raises the question of how to estimate several graphical models simultaneously. Compiling all the data together to estimate a single graph would ignore the differences among subpopulations. On the other hand, estimating a graph from each subpopulation separately does not make efficient use of the common structure in the data. We develop a new method for simultaneous estimation of multiple graphical models by estimating the topological neighborhoods of the involved variables under a sparse inducing penalty that takes into account the common structure in the subpopulations. Unlike the existing methods for joint graphical models, our method does not rely on spectral decomposition of large matrices, and is therefore more computationally attractive for estimating large networks. In addition, we develop the asymptotic properties of our method, demonstrate its the numerical complexity, and compare it with several existing methods by simulation. Finally, we apply our method to the estimation of genomic networks for a lung cancer dataset which consists of several subpopulations."]]></description>
<dc:subject>graphical_models model_selection in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7f61e925f50c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/abs/10.1080/13569317.2022.2138293?journalCode=cjpi20">
    <title>Mapping ideologies as networks of ideas: Journal of Political Ideologies: Vol 0, No 0</title>
    <dc:date>2023-06-08T22:05:24+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/abs/10.1080/13569317.2022.2138293?journalCode=cjpi20</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Individuals in a non-representative sample of 93 US progressives were asked which social outcomes they valued and then asked about the relationships among these opinions. Did each outcome provide a reason for a different one? Would each outcome cause a different one? If each outcome came to pass, would it make them more likely to support another outcome? Network diagrams derived from these responses represent portions of these individuals’ ideologies, understood as structures of political thought. Scrutiny of the network diagrams and analysis of the aggregate data suggest that most respondents carefully and reasonably identified relationships among their own ideas. Features of their networks predicted their assessments of five prominent politicians. This exploratory study paints a strikingly different picture of the sample than what would emerge from more conventional methods, such as factor analysis. Instead of a group that looks ideologically homogeneous on a unidimensional scale or that exhibits a low level of ideological coherence (because very few of their ideas are correlated), this method displays a collection of people who hold diverse and complex structures of thought. The method should be replicated with representative samples to explore the variation and significance of such structures."]]></description>
<dc:subject>to:NB graphical_models ideology cognitive_science to_read re:democratic_cognition</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d643359afe28/</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:ideology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cognitive_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:democratic_cognition"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2305.11561">
    <title>[2305.11561] Formalising causal inference in time and frequency on process graphs with latent components</title>
    <dc:date>2023-05-27T16:19:33+00:00</dc:date>
    <link>https://arxiv.org/abs/2305.11561</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["When dealing with time series data, causal inference methods often employ structural vector autoregressive (SVAR) processes to model time-evolving random systems. In this work, we rephrase recursive SVAR processes with possible latent component processes as a linear Structural Causal Model (SCM) of stochastic processes on a simple causal graph, the \emph{process graph}, that models every process as a single node. Using this reformulation, we generalise Wright's well-known path-rule for linear Gaussian SCMs to the newly introduced process SCMs and we express the auto-covariance sequence of an SVAR process by means of a generalised trek-rule. Employing the Fourier-Transformation, we derive compact expressions for causal effects in the frequency domain that allow us to efficiently visualise the causal interactions in a multivariate SVAR process. Finally, we observe that the process graph can be used to formulate graphical criteria for identifying causal effects and to derive algebraic relations with which these frequency domain causal effects can be recovered from the observed spectral density."

--- The phrase "frequency domain causal effects" makes my head hurt.]]></description>
<dc:subject>time_series causality graphical_models fourier_analysis in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:41a08583d9d8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fourier_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/chapter/10.1007/1-4020-4876-9_5">
    <title>Markov Properties and Quantum Experiments | SpringerLink</title>
    <dc:date>2023-05-01T19:56:32+00:00</dc:date>
    <link>https://link.springer.com/chapter/10.1007/1-4020-4876-9_5</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Ungated: https://www.cmu.edu/dietrich/philosophy/docs/glymour/markovquantum.pdf
]]></description>
<dc:subject>in_NB graphical_models causality quantum_mechanics have_read kith_and_kin glymour.clark cleaning_out_the_filing_cabinet_for_the_first_time_since_2005</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5056035702c1/</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:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:quantum_mechanics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:glymour.clark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cleaning_out_the_filing_cabinet_for_the_first_time_since_2005"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.05829">
    <title>[2206.05829] A non-graphical representation of conditional independence via the neighbourhood lattice</title>
    <dc:date>2022-06-15T17:48:21+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.05829</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce and study the neighbourhood lattice decomposition of a distribution, which is a compact, non-graphical representation of conditional independence that is valid in the absence of a faithful graphical representation. The idea is to view the set of neighbourhoods of a variable as a subset lattice, and partition this lattice into convex sublattices, each of which directly encodes a collection of conditional independence relations. We show that this decomposition exists in any compositional graphoid and can be computed efficiently and consistently in high-dimensions. In particular, this gives a way to encode all of independence relations implied by a distribution that satisfies the composition axiom, which is strictly weaker than the faithfulness assumption that is typically assumed by graphical approaches. We also discuss various special cases such as graphical models and projection lattices, each of which has intuitive interpretations. Along the way, we see how this problem is closely related to neighbourhood regression, which has been extensively studied in the context of graphical models and structural equations."]]></description>
<dc:subject>to:NB graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6293cf9ae283/</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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2206.06124">
    <title>[2206.06124] Causal Discovery in Hawkes Processes by Minimum Description Length</title>
    <dc:date>2022-06-15T17:47:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.06124</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Hawkes processes are a special class of temporal point processes which exhibit a natural notion of causality, as occurrence of events in the past may increase the probability of events in the future. Discovery of the underlying influence network among the dimensions of multi-dimensional temporal processes is of high importance in disciplines where a high-frequency data is to model, e.g. in financial data or in seismological data. This paper approaches the problem of learning Granger-causal network in multi-dimensional Hawkes processes. We formulate this problem as a model selection task in which we follow the minimum description length (MDL) principle. Moreover, we propose a general algorithm for MDL-based inference using a Monte-Carlo method and we use it for our causal discovery problem. We compare our algorithm with the state-of-the-art baseline methods on synthetic and real-world financial data. The synthetic experiments demonstrate superiority of our method incausal graph discovery compared to the baseline methods with respect to the size of the data. The results of experiments with the G-7 bonds price data are consistent with the experts knowledge."

--- Peeve: people talking about "causal discovery" when they only mean "Granger causality".]]></description>
<dc:subject>to:NB point_processes graphical_models model_selection minimum_description_length</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dfa84229e268/</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:point_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:minimum_description_length"/>
</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://arxiv.org/abs/2108.03099">
    <title>[2108.03099] Causal Inference Theory with Information Dependency Models</title>
    <dc:date>2022-06-06T12:55:51+00:00</dc:date>
    <link>https://arxiv.org/abs/2108.03099</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Inferring the potential consequences of an unobserved event is a fundamental scientific question. To this end, Pearl's celebrated do-calculus provides a set of inference rules to derive an interventional probability from an observational one. In this framework, the primitive causal relations are encoded as functional dependencies in a Structural Causal Model (SCM), which are generally mapped into a Directed Acyclic Graph (DAG) in the absence of cycles. In this paper, by contrast, we capture causality without reference to graphs or functional dependencies, but with information fields and Witsenhausen's intrinsic model. The three rules of do-calculus reduce to a unique sufficient condition for conditional independence, the topological separation, which presents interesting theoretical and practical advantages over the d-separation. With this unique rule, we can deal with systems that cannot be represented with DAGs, for instance systems with cycles and/or 'spurious' edges. We treat an example that cannot be handled-to the extent of our knowledge-with the tools of the current literature. We also explain why, in the presence of cycles, the theory of causal inference might require different tools, depending on whether the random variables are discrete or continuous."

--- The absence of a citation to Raginsky (2011) [https://arxiv.org/abs/1110.0718] is distinctly suspicious.]]></description>
<dc:subject>to:NB causality graphical_models information_theory color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ffb707aff322/</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:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<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/2206.01152">
    <title>[2206.01152] Causal Structure Learning: a Combinatorial Perspective</title>
    <dc:date>2022-06-06T12:52:56+00:00</dc:date>
    <link>https://arxiv.org/abs/2206.01152</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this review, we discuss approaches for learning causal structure from data, also called causal discovery. In particular, we focus on approaches for learning directed acyclic graphs (DAGs) and various generalizations which allow for some variables to be unobserved in the available data. We devote special attention to two fundamental combinatorial aspects of causal structure learning. First, we discuss the structure of the search space over causal graphs. Second, we discuss the structure of equivalence classes over causal graphs, i.e., sets of graphs which represent what can be learned from observational data alone, and how these equivalence classes can be refined by adding interventional data."]]></description>
<dc:subject>to:NB causal_discovery graphical_models computational_statistics uhler.caroline to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dc366a20c919/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:uhler.caroline"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/Total-positivity-in-exponential-families-with-application-to-binary-variables/10.1214/20-AOS2007.short">
    <title>Total positivity in exponential families with application to binary variables</title>
    <dc:date>2021-08-10T14:09:30+00:00</dc:date>
    <link>https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/Total-positivity-in-exponential-families-with-application-to-binary-variables/10.1214/20-AOS2007.short</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study exponential families of distributions that are multivariate totally positive of order 2 (MTP2), show that these are convex exponential families and derive conditions for existence of the MLE. Quadratic exponential familes of MTP2 distributions contain attractive Gaussian graphical models and ferromagnetic Ising models as special examples. We show that these are defined by intersecting the space of canonical parameters with a polyhedral cone whose faces correspond to conditional independence relations. Hence MTP2 serves as an implicit regularizer for quadratic exponential families and leads to sparsity in the estimated graphical model. We prove that the maximum likelihood estimator (MLE) in an MTP2 binary exponential family exists if and only if both of the sign patterns (1,−1) and (−1,1) are represented in the sample for every pair of variables; in particular, this implies that the MLE may exist with n=d observations, in stark contrast to unrestricted binary exponential families where 2^d observations are required. Finally, we provide a novel and globally convergent algorithm for computing the MLE for MTP2 Ising models similar to iterative proportional scaling and apply it to the analysis of data from two psychological disorders."]]></description>
<dc:subject>to_read exponential_families graphical_models uhler.caroline lauritzen.steffen of_course_its_really_a_spin_glass in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c1464c953dee/</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:exponential_families"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:uhler.caroline"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lauritzen.steffen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:of_course_its_really_a_spin_glass"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://psyarxiv.com/kjh2f">
    <title>PsyArXiv Preprints | The Confidence Interval that Wasn’t: Bootstrapped “Confidence Intervals” in L1-Regularized Partial Correlation Networks</title>
    <dc:date>2021-07-19T13:52:15+00:00</dc:date>
    <link>https://psyarxiv.com/kjh2f</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["I shed much needed light upon the default measure of parameter uncertainty in network psychometrics; that is, ``confidence intervals'' (CI) computed from bootstrapping $\ell_1$-regularized partial correlations. Due to the nature of the $\ell_1$-penalty, however, bootstrapping does not provide an accurate sampling distribution. Although this has long been known in the statistical literature, I set out to determine whether the intervals can at least be considered \emph{approximate}. In multiple regression, I first describe the fundamental tension between model selection and estimation consistency inherent to the $\ell_1$-penalty---in the pursuit of sparsity, the sampling distribution of the non-zero coefficients is necessarily compromised which translates into coverage far below nominal levels.
"With the foundation laid, I proceed to investigate coverage for non-zero relations in partial correlation networks. At best, average coverage was around 0.65 for 90\% CIs. With increasing sample sizes, average coverage decreased to 0.30, perhaps approaching 0 if larger sample sizes were explored. Further, coverage was heavily influenced by the mere position of an edge in the network, ranging from essentially 0 to 0.90, with an average of around 0.50. Meanwhile, for the same simulation conditions, simply bootstrapping the sample covariance matrix provided coverage at the nominal level. In light of the results, I then demonstrate how to judiciously use the bootstrap in both regularized and non-regularized networks: the former can provide a useful summary of data-mining, whereas the latter allows for making inference on network parameters. To ensure network researchers have the option of computing valid CIs, I implemented a non-regularized bootstrap for various types of partial correlations in the {\tt R} package \textbf{GGMnonreg}. "]]></description>
<dc:subject>to:NB sparsity model_selection graphical_models statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f65b9477b29f/</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:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.02180">
    <title>[2105.02180] A unifying tutorial on Approximate Message Passing</title>
    <dc:date>2021-06-28T03:49:13+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.02180</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Over the last decade or so, Approximate Message Passing (AMP) algorithms have become extremely popular in various structured high-dimensional statistical problems. The fact that the origins of these techniques can be traced back to notions of belief propagation in the statistical physics literature lends a certain mystique to the area for many statisticians. Our goal in this work is to present the main ideas of AMP from a statistical perspective, to illustrate the power and flexibility of the AMP framework. Along the way, we strengthen and unify many of the results in the existing literature."]]></description>
<dc:subject>to:NB graphical_models computational_statistics statistics samworth.richard_j.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:268aa73d4c33/</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:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:samworth.richard_j."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2102.10324">
    <title>[2102.10324] Necessary and sufficient graphical conditions for optimal adjustment sets in causal graphical models with hidden variables</title>
    <dc:date>2021-06-28T03:42:54+00:00</dc:date>
    <link>https://arxiv.org/abs/2102.10324</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The problem of selecting optimal valid backdoor adjustment sets to estimate causal effects in graphical models with hidden and conditioned variables is addressed. Previous work has defined optimality as achieving the smallest asymptotic variance compared to other adjustment sets and identified a graphical criterion for an optimal set for the case without hidden variables. For the case with hidden variables currently a sufficient graphical criterion and a corresponding construction algorithm exists. Here optimality is characterized by an information-theoretic approach based on the conditional mutual informations among cause, effect, adjustment set, and conditioned variables. This characterization allows to derive the main contributions of this paper: A necessary and sufficient graphical criterion for the existence of an optimal adjustment set and a definition and algorithm to construct it. Further, the optimal set is valid if and only if a valid adjustment set exists and has smaller (or equal) asymptotic variance compared to the Adjust-set proposed in Perkovic et al. (2018) (arXiv:1606.06903) for any graph, whether graphical optimality holds or not. The results are valid for a class of estimators whose asymptotic variance follows a certain information-theoretic relation. Numerical experiments indicate that the asymptotic results also hold for relatively small sample sizes. For estimators outside of the class studied here none of the considered adjustment sets outperforms all others, but a minimized variant of the optimal set proposed here tends to have lower variance. Surprisingly, among the randomly created setups more than 80\% fulfill the optimality conditions indicating that also in many real-world scenarios graphical optimality may hold."]]></description>
<dc:subject>to:NB causal_inference graphical_models statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:154daf02af07/</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:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.05694">
    <title>[2106.05694] Confidence in Causal Discovery with Linear Causal Models</title>
    <dc:date>2021-06-24T20:41:33+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.05694</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Structural causal models postulate noisy functional relations among a set of interacting variables. The causal structure underlying each such model is naturally represented by a directed graph whose edges indicate for each variable which other variables it causally depends upon. Under a number of different model assumptions, it has been shown that this causal graph and, thus also, causal effects are identifiable from mere observational data. For these models, practical algorithms have been devised to learn the graph. Moreover, when the graph is known, standard techniques may be used to give estimates and confidence intervals for causal effects. We argue, however, that a two-step method that first learns a graph and then treats the graph as known yields confidence intervals that are overly optimistic and can drastically fail to account for the uncertain causal structure. To address this issue we lay out a framework based on test inversion that allows us to give confidence regions for total causal effects that capture both sources of uncertainty: causal structure and numerical size of nonzero effects. Our ideas are developed in the context of bivariate linear causal models with homoscedastic errors, but as we exemplify they are generalizable to larger systems as well as other settings such as, in particular, linear non-Gaussian models."

--- This idea is obviously pointed in the right direction, but didn't Maathuis et al. say correct in like 2011 that the right thing to do is to look over the _set_ of possible DAGs and calculate the effect in each?  I suppose there could be some annoying fiddling with the required confidence levels...]]></description>
<dc:subject>to_read graphical_models causal_discovery confidence_sets drton.mathias in_NB statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2815f8e350f1/</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:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:drton.mathias"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.03969">
    <title>[2106.03969] Chow-Liu++: Optimal Prediction-Centric Learning of Tree Ising Models</title>
    <dc:date>2021-06-10T02:24:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.03969</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of learning a tree-structured Ising model from data, such that subsequent predictions computed using the model are accurate. Concretely, we aim to learn a model such that posteriors P(Xi|XS) for small sets of variables S are accurate. Since its introduction more than 50 years ago, the Chow-Liu algorithm, which efficiently computes the maximum likelihood tree, has been the benchmark algorithm for learning tree-structured graphical models. A bound on the sample complexity of the Chow-Liu algorithm with respect to the prediction-centric local total variation loss was shown in [BK19]. While those results demonstrated that it is possible to learn a useful model even when recovering the true underlying graph is impossible, their bound depends on the maximum strength of interactions and thus does not achieve the information-theoretic optimum. In this paper, we introduce a new algorithm that carefully combines elements of the Chow-Liu algorithm with tree metric reconstruction methods to efficiently and optimally learn tree Ising models under a prediction-centric loss. Our algorithm is robust to model misspecification and adversarial corruptions. In contrast, we show that the celebrated Chow-Liu algorithm can be arbitrarily suboptimal."
]]></description>
<dc:subject>to:NB graphical_models chow-liu statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:529de0ce908f/</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:chow-liu"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2102.13384">
    <title>[2102.13384] Why did the distribution change?</title>
    <dc:date>2021-05-26T04:12:55+00:00</dc:date>
    <link>https://arxiv.org/abs/2102.13384</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We describe a formal approach based on graphical causal models to identify the "root causes" of the change in the probability distribution of variables. After factorizing the joint distribution into conditional distributions of each variable, given its parents (the "causal mechanisms"), we attribute the change to changes of these causal mechanisms. This attribution analysis accounts for the fact that mechanisms often change independently and sometimes only some of them change. Through simulations, we study the performance of our distribution change attribution method. We then present a real-world case study identifying the drivers of the difference in the income distribution between men and women."]]></description>
<dc:subject>to:NB explanation graphical_models causal_inference inequality to_teach:statistics_of_inequality_and_discrimination statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ad1b7d268f83/</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:explanation"/>
	<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:inequality"/>
	<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:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.10350">
    <title>[2105.10350] Definite Non-Ancestral Relations and Structure Learning</title>
    <dc:date>2021-05-24T22:52:26+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.10350</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In causal graphical models based on directed acyclic graphs (DAGs), directed paths represent causal pathways between the corresponding variables. The variable at the beginning of such a path is referred to as an ancestor of the variable at the end of the path. Ancestral relations between variables play an important role in causal modeling. In existing literature on structure learning, these relations are usually deduced from learned structures and used for orienting edges or formulating constraints of the space of possible DAGs. However, they are usually not posed as immediate target of inference. In this work we investigate the graphical characterization of ancestral relations via CPDAGs and d-separation relations. We propose a framework that can learn definite non-ancestral relations without first learning the skeleton. This frame-work yields structural information that can be used in both score- and constraint-based algorithms to learn causal DAGs more efficiently."]]></description>
<dc:subject>to:NB causal_discovery graphical_models shojaie.alie drton.mathias statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bae75ae66b9f/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:shojaie.alie"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:drton.mathias"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.06221">
    <title>[1611.06221] Foundations of Structural Causal Models with Cycles and Latent Variables</title>
    <dc:date>2021-05-12T18:09:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.06221</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Structural causal models (SCMs), also known as (nonparametric) structural equation models (SEMs), are widely used for causal modeling purposes. In particular, acyclic SCMs, also known as recursive SEMs, form a well-studied subclass of SCMs that generalize causal Bayesian networks to allow for latent confounders. In this paper, we investigate SCMs in a more general setting, allowing for the presence of both latent confounders and cycles. We show that in the presence of cycles, many of the convenient properties of acyclic SCMs do not hold in general: they do not always have a solution; they do not always induce unique observational, interventional and counterfactual distributions; a marginalization does not always exist, and if it exists the marginal model does not always respect the latent projection; they do not always satisfy a Markov property; and their graphs are not always consistent with their causal semantics. We prove that for SCMs in general each of these properties does hold under certain solvability conditions. Our work generalizes results for SCMs with cycles that were only known for certain special cases so far. We introduce the class of simple SCMs that extends the class of acyclic SCMs to the cyclic setting, while preserving many of the convenient properties of acyclic SCMs. With this paper we aim to provide the foundations for a general theory of statistical causal modeling with SCMs."]]></description>
<dc:subject>to:NB graphical_models causality peters.jonas</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f3134825315f/</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:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:peters.jonas"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/full/10.1080/01621459.2021.1874961">
    <title>Graphical Models for Processing Missing Data: Journal of the American Statistical Association: Vol 0, No 0</title>
    <dc:date>2021-04-12T03:43:38+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/full/10.1080/01621459.2021.1874961</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This article reviews recent advances in missing data research using graphical models to represent multivariate dependencies. We first examine the limitations of traditional frameworks from three different perspectives: transparency, estimability, and testability. We then show how procedures based on graphical models can overcome these limitations and provide meaningful performance guarantees even when data are missing not at random (MNAR). In particular, we identify conditions that guarantee consistent estimation in broad categories of missing data problems, and derive procedures for implementing this estimation. Finally, we derive testable implications for missing data models in both missing at random and MNAR categories."]]></description>
<dc:subject>to:NB missing_data pearl.judea graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:67193b91bb61/</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:missing_data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:pearl.judea"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.09271">
    <title>[2101.09271] Representation of Context-Specific Causal Models with Observational and Interventional Data</title>
    <dc:date>2021-04-12T03:16:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.09271</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of representing causal models that encode context-specific information for discrete data. To represent such models we use a proper subclass of staged tree models which we call CStrees. We show that the context-specific information encoded by a CStree can be equivalently expressed via a collection of DAGs. As not all staged tree models admit this property, CStrees are a subclass that provides a transparent, intuitive and compact representation of context-specific causal information. Model equivalence for CStrees also takes a simpler form than for general staged trees: We provide a characterization of the complete set of asymmetric conditional independence relations encoded by a CStree. As a consequence, we obtain a global Markov property for CStrees which leads to a graphical criterion of model equivalence for CStrees generalizing that of Verma and Pearl for DAG models. In addition, we provide a closed-form formula for the maximum likelihood estimator of a CStree and use it to show that the Bayesian information criterion is a locally consistent score function for this model class. We also give an analogous global Markov property and characterization of model equivalence for general interventions in CStrees. As examples, we apply these results to two real data sets, and examine how BIC-optimal CStrees for each provide a clear and concise representation of the learned context-specific causal structure."]]></description>
<dc:subject>to:NB graphical_models causal_inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:21234b5d4504/</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:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2006.11970">
    <title>[2006.11970] A polynomial-time algorithm for learning nonparametric causal graphs</title>
    <dc:date>2021-03-17T17:38:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2006.11970</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We establish finite-sample guarantees for a polynomial-time algorithm for learning a nonlinear, nonparametric directed acyclic graphical (DAG) model from data. The analysis is model-free and does not assume linearity, additivity, independent noise, or faithfulness. Instead, we impose a condition on the residual variances that is closely related to previous work on linear models with equal variances. Compared to an optimal algorithm with oracle knowledge of the variable ordering, the additional cost of the algorithm is linear in the dimension d and the number of samples n. Finally, we compare the proposed algorithm to existing approaches in a simulation study."]]></description>
<dc:subject>to_read causal_discovery statistics graphical_models in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3bd512ec799e/</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:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.03501">
    <title>[2101.03501] Entropic Causal Inference: Identifiability and Finite Sample Results</title>
    <dc:date>2021-01-12T20:55:32+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.03501</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Entropic causal inference is a framework for inferring the causal direction between two categorical variables from observational data. The central assumption is that the amount of unobserved randomness in the system is not too large. This unobserved randomness is measured by the entropy of the exogenous variable in the underlying structural causal model, which governs the causal relation between the observed variables. Kocaoglu et al. conjectured that the causal direction is identifiable when the entropy of the exogenous variable is not too large. In this paper, we prove a variant of their conjecture. Namely, we show that for almost all causal models where the exogenous variable has entropy that does not scale with the number of states of the observed variables, the causal direction is identifiable from observational data. We also consider the minimum entropy coupling-based algorithmic approach presented by Kocaoglu et al., and for the first time demonstrate algorithmic identifiability guarantees using a finite number of samples. We conduct extensive experiments to evaluate the robustness of the method to relaxing some of the assumptions in our theory and demonstrate that both the constant-entropy exogenous variable and the no latent confounder assumptions can be relaxed in practice. We also empirically characterize the number of observational samples needed for causal identification. Finally, we apply the algorithm on Tuebingen cause-effect pairs dataset."]]></description>
<dc:subject>to:NB causal_inference causal_discovery graphical_models information_theory color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8969f6a9698e/</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:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<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/2101.03093">
    <title>[2101.03093] Learning non-Gaussian graphical models via Hessian scores and triangular transport</title>
    <dc:date>2021-01-11T16:32:41+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.03093</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Undirected probabilistic graphical models represent the conditional dependencies, or Markov properties, of a collection of random variables. Knowing the sparsity of such a graphical model is valuable for modeling multivariate distributions and for efficiently performing inference. While the problem of learning graph structure from data has been studied extensively for certain parametric families of distributions, most existing methods fail to consistently recover the graph structure for non-Gaussian data. Here we propose an algorithm for learning the Markov structure of continuous and non-Gaussian distributions. To characterize conditional independence, we introduce a score based on integrated Hessian information from the joint log-density, and we prove that this score upper bounds the conditional mutual information for a general class of distributions. To compute the score, our algorithm SING estimates the density using a deterministic coupling, induced by a triangular transport map, and iteratively exploits sparse structure in the map to reveal sparsity in the graph. For certain non-Gaussian datasets, we show that our algorithm recovers the graph structure even with a biased approximation to the density. Among other examples, we apply sing to learn the dependencies between the states of a chaotic dynamical system with local interactions."]]></description>
<dc:subject>to:NB graphical_models sparsity statistics information_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fb9eca8344a8/</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:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.02332">
    <title>[2101.02332] Identification of Latent Variables From Graphical Model Residuals</title>
    <dc:date>2021-01-08T03:39:39+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.02332</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Graph-based causal discovery methods aim to capture conditional independencies consistent with the observed data and differentiate causal relationships from indirect or induced ones. Successful construction of graphical models of data depends on the assumption of causal sufficiency: that is, that all confounding variables are measured. When this assumption is not met, learned graphical structures may become arbitrarily incorrect and effects implied by such models may be wrongly attributed, carry the wrong magnitude, or mis-represent direction of correlation. Wide application of graphical models to increasingly less curated "big data" draws renewed attention to the unobserved confounder problem.
"We present a novel method that aims to control for the latent space when estimating a DAG by iteratively deriving proxies for the latent space from the residuals of the inferred model. Under mild assumptions, our method improves structural inference of Gaussian graphical models and enhances identifiability of the causal effect. In addition, when the model is being used to predict outcomes, it un-confounds the coefficients on the parents of the outcomes and leads to improved predictive performance when out-of-sample regime is very different from the training data. We show that any improvement of prediction of an outcome is intrinsically capped and cannot rise beyond a certain limit as compared to the confounded model. We extend our methodology beyond GGMs to ordinal variables and nonlinear cases. Our R package provides both PCA and autoencoder implementations of the methodology, suitable for GGMs with some guarantees and for better performance in general cases but without such guarantees."]]></description>
<dc:subject>to:NB causal_discovery graphical_models inference_to_latent_objects statistics to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:653363dd410a/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<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-economics-072219-111921">
    <title>Behavioral Implications of Causal Misperceptions | Annual Review of Economics</title>
    <dc:date>2021-01-03T19:35:30+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-economics-072219-111921</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This review presents an approach to modeling decision making under misspecified subjective models. The approach is based on the idea that decision makers impose subjective causal interpretations on observed correlations, and it borrows basic concepts and tools from the statistics and artificial intelligence literatures on Bayesian networks. While these background literatures used Bayesian networks as a platform for normative and computational analysis of probabilistic and causal inference, in the framework proposed here graphical models represent causal misperceptions and help analyze their behavioral implications. I show how this approach sheds light on earlier equilibrium models with nonrational expectations and demonstrate its scope of economic applications."]]></description>
<dc:subject>to:NB economics decision-making graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3a715566107e/</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:economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:decision-making"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2006.11937">
    <title>[2006.11937] Learning of Discrete Graphical Models with Neural Networks</title>
    <dc:date>2020-12-26T17:46:11+00:00</dc:date>
    <link>https://arxiv.org/abs/2006.11937</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Graphical models are widely used in science to represent joint probability distributions with an underlying conditional dependence structure. The inverse problem of learning a discrete graphical model given i.i.d samples from its joint distribution can be solved with near-optimal sample complexity using a convex optimization method known as Generalized Regularized Interaction Screening Estimator (GRISE). But the computational cost of GRISE becomes prohibitive when the energy function of the true graphical model has higher-order terms. We introduce NeurISE, a neural net based algorithm for graphical model learning, to tackle this limitation of GRISE. We use neural nets as function approximators in an Interaction Screening objective function. The optimization of this objective then produces a neural-net representation for the conditionals of the graphical model. NeurISE algorithm is seen to be a better alternative to GRISE when the energy function of the true model has a high order with a high degree of symmetry. In these cases NeurISE is able to find the correct parsimonious representation for the conditionals without being fed any prior information about the true model. NeurISE can also be used to learn the underlying structure of the true model with some simple modifications to its training procedure. In addition, we also show a variant of NeurISE that can be used to learn a neural net representation for the full energy function of the true model."

--- Comment before reading: I'm willing to bet it's the "high degree of symmetry" that's doing the work, and not any magic of neural networks.  But I could be wrong!]]></description>
<dc:subject>to:NB graphical_models causal_discovery nonparametrics statistics neural_networks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:db060342bc93/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.10980">
    <title>[2012.10980] Measurement bias: a structural perspective</title>
    <dc:date>2020-12-24T15:47:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.10980</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The causal structure for measurement bias (MB) remains controversial. Aided by the Directed Acyclic Graph (DAG), this paper proposes a new structure for measuring one singleton variable whose MB arises in the selection of an imperfect I/O device-like measurement system. For effect estimation, however, an extra source of MB arises from any redundant association between a measured exposure and a measured outcome. The misclassification will be bidirectionally differential for a common outcome, unidirectionally differential for a causal relation, and non-differential for a common cause between the measured exposure and the measured outcome or a null effect. The measured exposure can actually affect the measured outcome, or vice versa. Reverse causality is a concept defined at the level of measurement. Our new DAGs have clarified the structures and mechanisms of MB."]]></description>
<dc:subject>to:NB causal_inference graphical_models measurement</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:353018eb50eb/</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:li rdf:resource="https://pinboard.in/u:cshalizi/t:measurement"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.11281">
    <title>[2012.11281] Towards Conditional Path Analysis</title>
    <dc:date>2020-12-22T03:53:51+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.11281</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We extend path analysis by giving sufficient conditions for computing the partial covariance of two random variables from their covariance. This is specifically done by correcting the covariance with the product of some partial variance ratios. As a result, the partial covariance retains the covariance's salient feature of factorizing over the edges in the paths between the two variables of interest."]]></description>
<dc:subject>to:NB graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6db972682890/</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:Bag></taxo:topics>
</item>
<item rdf:about="https://jmlr.org/papers/v21/20-175.html">
    <title>On Efficient Adjustment in Causal Graphs</title>
    <dc:date>2020-12-21T04:36:35+00:00</dc:date>
    <link>https://jmlr.org/papers/v21/20-175.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider estimation of a total causal effect from observational data via covariate adjustment. Ideally, adjustment sets are selected based on a given causal graph, reflecting knowledge of the underlying causal structure. Valid adjustment sets are, however, not unique. Recent research has introduced a graphical criterion for an 'optimal' valid adjustment set (O-set). For a given graph, adjustment by the O-set yields the smallest asymptotic variance compared to other adjustment sets in certain parametric and non-parametric models. In this paper, we provide three new results on the O-set. First, we give a novel, more intuitive graphical characterisation: We show that the O-set is the parent set of the outcome node(s) in a suitable latent projection graph, which we call the forbidden projection. An important property is that the forbidden projection preserves all information relevant to total causal effect estimation via covariate adjustment, making it a useful methodological tool in its own right. Second, we extend the existing IDA algorithm to use the O-set, and argue that the algorithm remains semi-local. This is implemented in the R-package pcalg. Third, we present assumptions under which the O-set can be viewed as the target set of popular non-graphical variable selection algorithms such as stepwise backward selection."]]></description>
<dc:subject>to:NB graphical_models causal_inference maathuis.marloes didelez.vanessa</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f6cb91d47edd/</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:maathuis.marloes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:didelez.vanessa"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.sagepub.com/doi/abs/10.1177/0049124120926208">
    <title>The Structure of Academic Achievement: Searching for Proximal Mechanisms Using Causal Discovery Algorithms - Rafael Quintana, 2020</title>
    <dc:date>2020-12-16T21:29:07+00:00</dc:date>
    <link>https://journals.sagepub.com/doi/abs/10.1177/0049124120926208</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Causal search algorithms have been effectively applied in different fields including biology, genetics, climate science, medicine, and neuroscience. However, there have been scant applications of these methods in social and behavioral sciences. This article provides an illustrative example of how causal search algorithms can shed light on important social and behavioral problems by using these algorithms to find the proximal mechanisms of academic achievement. Using a nationally representative data set with a wide range of relevant contextual and psychological factors, I implement four causal search procedures that varied important dimensions in the algorithms. Consistent with previous research, the algorithms identified prior achievement, executive functions (in particular, working memory, cognitive flexibility, and attentional focusing), and motivation as direct causes of academic achievement. I discuss the advantages and limitations of graphical models in general and causal search algorithms in particular for understanding social and behavioral problems."]]></description>
<dc:subject>to:NB to_read causal_discovery graphical_models education academia</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:214b1f21f62c/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:education"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:academia"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.08154">
    <title>[2012.08154] Inference of Causal Effects when Adjustment Sets are Unknown</title>
    <dc:date>2020-12-16T17:45:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.08154</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Conventional methods in causal effect inference typically rely on specifying a valid set of adjustment variables. When this set is unknown or misspecified, inferences will be erroneous. We propose a method for inferring average causal effects when the adjustment set is unknown. When the data-generating process belongs to the class of acyclical linear structural equation models, we prove that the method yields asymptotically valid confidence intervals. Our results build upon a smooth characterization of linear acyclic directed graphs. We verify the capability of the method to produce valid confidence intervals for average causal effects using synthetic data, even when the appropriate adjustment sets are unknown."]]></description>
<dc:subject>to:NB causal_inference statistics graphical_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dbc42aa2fb0e/</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:graphical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.05269">
    <title>[2012.05269] Hard and Soft EM in Bayesian Network Learning from Incomplete Data</title>
    <dc:date>2020-12-12T18:13:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.05269</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Incomplete data are a common feature in many domains, from clinical trials to industrial applications. Bayesian networks (BNs) are often used in these domains because of their graphical and causal interpretations. BN parameter learning from incomplete data is usually implemented with the Expectation-Maximisation algorithm (EM), which computes the relevant sufficient statistics ("soft EM") using belief propagation. Similarly, the Structural Expectation-Maximisation algorithm (Structural EM) learns the network structure of the BN from those sufficient statistics using algorithms designed for complete data. However, practical implementations of parameter and structure learning often impute missing data ("hard EM") to compute sufficient statistics instead of using belief propagation, for both ease of implementation and computational speed. In this paper, we investigate the question: what is the impact of using imputation instead of belief propagation on the quality of the resulting BNs? From a simulation study using synthetic data and reference BNs, we find that it is possible to recommend one approach over the other in several scenarios based on the characteristics of the data. We then use this information to build a simple decision tree to guide practitioners in choosing the EM algorithm best suited to their problem."]]></description>
<dc:subject>to:NB missing_data causal_discovery graphical_models em_algorithm statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4910988c3fe1/</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:missing_data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:em_algorithm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1607677245">
    <title>Evans : Model selection and local geometry</title>
    <dc:date>2020-12-11T17:33:36+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1607677245</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider problems in model selection caused by the geometry of models close to their points of intersection. In some cases—including common classes of causal or graphical models, as well as time series models—distinct models may nevertheless have identical tangent spaces. This has two immediate consequences: first, in order to obtain constant power to reject one model in favour of another we need local alternative hypotheses that decrease to the null at a slower rate than the usual parametric n−1/2n−1/2 (typically we will require n−1/4n−1/4 or slower); in other words, to distinguish between the models we need large effect sizes or very large sample sizes. Second, we show that under even weaker conditions on their tangent cones, models in these classes cannot be made simultaneously convex by a reparameterization.
"This shows that Bayesian network models, amongst others, cannot be learned directly with a convex method similar to the graphical lasso. However, we are able to use our results to suggest methods for model selection that learn the tangent space directly, rather than the model itself. In particular, we give a generic algorithm for learning Bayesian network models."]]></description>
<dc:subject>model_selection information_geometry statistics causal_discovery graphical_models to_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d9e2275be851/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<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://www.aeaweb.org/articles?id=10.1257/aer.20191099">
    <title>A Model of Competing Narratives - American Economic Association</title>
    <dc:date>2020-11-30T16:04:28+00:00</dc:date>
    <link>https://www.aeaweb.org/articles?id=10.1257/aer.20191099</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We formalize the argument that political disagreements can be traced to a "clash of narratives." Drawing on the "Bayesian Networks" literature, we represent a narrative by a causal model that maps actions into consequences, weaving a selection of other random variables into the story. Narratives generate beliefs by interpreting long-run correlations between these variables. An equilibrium is defined as a probability distribution over narrative-policy pairs that maximize a representative agent's anticipatory utility, capturing the idea that people are drawn to hopeful narratives. Our equilibrium analysis sheds light on the structure of prevailing narratives, the variables they involve, the policies they sustain, and their contribution to political polarization."

1. Words have meanings; a causal model is not a "narrative".
2. Why on Earth would you think that people are generally drawn to the  most optimistic scenario?  Have you met people (who aren't Americans)?]]></description>
<dc:subject>to:NB to_read graphical_models model_selection psychology_by_economists color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d71c6317abb6/</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:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychology_by_economists"/>
	<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/1810.10854">
    <title>[1810.10854] Structure learning of undirected graphical models for count data</title>
    <dc:date>2020-11-25T14:54:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.10854</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Biological processes underlying the basic functions of a cell involve complex interactions between genes. From a technical point of view, these interactions can be represented through a graph where genes and their connections are, respectively, nodes and edges. The main objective of this paper is to develop a statistical framework for modelling the interactions between genes when the activity of genes is measured on a discrete scale. In detail, we define a new algorithm for learning the structure of undirected graphs, PC-LPGM, proving its theoretical consistence in the limit of infinite observations. The proposed algorithm shows promising results when applied to simulated data as well as to real data."]]></description>
<dc:subject>to:NB graphical_models biochemical_networks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cb5740b4e4f1/</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:biochemical_networks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-031017-100053">
    <title>Algebraic Statistics in Practice: Applications to Networks | Annual Review of Statistics and Its Application</title>
    <dc:date>2020-11-19T20:04:23+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-031017-100053</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Algebraic statistics uses tools from algebra (especially from multilinear algebra, commutative algebra, and computational algebra), geometry, and combinatorics to provide insight into knotty problems in mathematical statistics. In this review, we illustrate this on three problems related to networks: network models for relational data, causal structure discovery, and phylogenetics. For each problem, we give an overview of recent results in algebraic statistics, with emphasis on the statistical achievements made possible by these tools and their practical relevance for applications to other scientific disciplines."

]]></description>
<dc:subject>to:NB statistics phylogenetics network_data_analysis graphical_models algebra petrovic.sonja uhler.caroline</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a80cef74bdd5/</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:phylogenetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algebra"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:petrovic.sonja"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:uhler.caroline"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.ejs/1605582080">
    <title>Peng , Shen , Pan : Reconstruction of a directed acyclic graph with intervention</title>
    <dc:date>2020-11-18T21:01:14+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.ejs/1605582080</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Identification of causal relations among variables is central to many scientific investigations, as in regulatory network analysis of gene interactions and brain network analysis of effective connectivity of causal relations between regions of interest. Statistically, causal relations are often modeled by a directed acyclic graph (DAG), and hence that reconstruction of a DAG’s structure leads to the discovery of causal relations. Yet, reconstruction of a DAG’s structure from observational data is impossible because a DAG Gaussian model is usually not identifiable with unequal error variances. In this article, we reconstruct a DAG’s structure with the help of interventional data. Particularly, we construct a constrained likelihood to regularize intervention in addition to adjacency matrices to identify a DAG’s structure, subject to an error variance constraint to further reinforce the model identifiability. Theoretically, we show that the proposed constrained likelihood leads to identifiable models, thus correct reconstruction of a DAG’s structure through parameter estimation even with unequal error variances. Computationally, we design efficient algorithms for the proposed method. In simulations, we show that the proposed method enables to produce a higher accuracy of reconstruction with the help of interventional observations."]]></description>
<dc:subject>to:NB causal_discovery graphical_models experiments statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:278069bb5857/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experiments"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://ieeexplore.ieee.org/document/8804234">
    <title>Semidefinite Tests for Latent Causal Structures - IEEE Journals &amp; Magazine</title>
    <dc:date>2020-11-16T16:04:42+00:00</dc:date>
    <link>https://ieeexplore.ieee.org/document/8804234</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Testing whether a probability distribution is compatible with a given Bayesian network is a fundamental task in the field of causal inference, where Bayesian networks model causal relations. Here we consider the class of causal structures where all correlations between observed quantities are solely due to the influence from latent variables. We show that each model of this type imposes a certain signature on the observable covariance matrix in terms of a particular decomposition into positive semidefinite components. This signature, and thus the underlying hypothetical latent structure, can be tested in a computationally efficient manner via semidefinite programming. This stands in stark contrast with the algebraic geometric tools required if the full observable probability distribution is taken into account. The semidefinite test is compared with tests based on entropic inequalities."]]></description>
<dc:subject>to:NB causal_discovery graphical_models statistics hypothesis_testing inference_to_latent_objects</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9caefd16483a/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2009.12246">
    <title>[2009.12246] Message passing for probabilistic models on networks with loops</title>
    <dc:date>2020-10-23T19:29:52+00:00</dc:date>
    <link>https://arxiv.org/abs/2009.12246</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we extend a recently proposed framework for message passing on "loopy" networks to the solution of probabilistic models. We derive a self-consistent set of message passing equations that allow for fast computation of probability distributions in systems that contain short loops, potentially with high density, as well as expressions for the entropy and partition function of such systems, which are notoriously difficult quantities to compute. Using the Ising model as an example, we show that our solutions are asymptotically exact on certain classes of networks with short loops and offer a good approximation on more general networks, improving significantly on results derived from standard belief propagation. We also discuss potential applications of our method to a variety of other problems."]]></description>
<dc:subject>to:NB graphical_models newman.mark to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3f47c41c9119/</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:newman.mark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.03662">
    <title>[1903.03662] A Potential Outcomes Calculus for Identifying Conditional Path-Specific Effects</title>
    <dc:date>2020-07-28T15:15:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.03662</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The do-calculus is a well-known deductive system for deriving connections between interventional and observed distributions, and has been proven complete for a number of important identifiability problems in causal inference. Nevertheless, as it is currently defined, the do-calculus is inapplicable to causal problems that involve complex nested counterfactuals which cannot be expressed in terms of the "do" operator. Such problems include analyses of path-specific effects and dynamic treatment regimes. In this paper we present the potential outcome calculus (po-calculus), a natural generalization of do-calculus for arbitrary potential outcomes. We thereby provide a bridge between identification approaches which have their origins in artificial intelligence and statistics, respectively. We use po-calculus to give a complete identification algorithm for conditional path-specific effects with applications to problems in mediation analysis and algorithmic fairness."]]></description>
<dc:subject>to:NB causality causal_inference graphical_models malinsky.daniel richardson.thomas shpitser.ilya</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cd3dd9da34d7/</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:causality"/>
	<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:li rdf:resource="https://pinboard.in/u:cshalizi/t:malinsky.daniel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:richardson.thomas"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:shpitser.ilya"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/chapter/10.1007/978-94-011-5014-9_16">
    <title>Asymptotic Model Selection for Directed Networks with Hidden Variables | SpringerLink</title>
    <dc:date>2020-05-16T18:08:16+00:00</dc:date>
    <link>https://link.springer.com/chapter/10.1007/978-94-011-5014-9_16</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We extend the Bayesian Information Criterion (BIC), an asymptotic approximation for the marginal likelihood, to Bayesian networks with hidden variables. This approximation can be used to select models given large samples of data. The standard BIC as well as our extension punishes the complexity of a model according to the dimension of its parameters. We argue that the dimension of a Bayesian network with hidden variables is the rank of the Jacobian matrix of the transformation between the parameters of the network and the parameters of the observable variables. We compute the dimensions of several networks including the naive Bayes model with a hidden root node.
"This manuscript was previously published in The Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence, 1996, Morgan Kaufmann."]]></description>
<dc:subject>to:NB have_read to_reread information_criteria information_geometry statistics likelihood graphical_models inference_to_latent_objects re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2a65e9c78eb7/</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:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_reread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_criteria"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1023/A:1009602825894">
    <title>An Axiomatic Characterization of Causal Counterfactuals | SpringerLink</title>
    <dc:date>2020-05-16T17:44:25+00:00</dc:date>
    <link>https://link.springer.com/article/10.1023/A:1009602825894</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper studies the causal interpretation of counterfactual sentences using a modifiable structural equation model. It is shown that two properties of counterfactuals, namely, composition and effectiveness, are sound and complete relative to this interpretation, when recursive (i.e., feedback-less) models are considered. Composition and effectiveness also hold in Lewis's closest-world semantics, which implies that for recursive models the causal interpretation imposes no restrictions beyond those embodied in Lewis's framework. A third property, called reversibility, holds in nonrecursive causal models but not in Lewis's closest-world semantics, which implies that Lewis's axioms do not capture some properties of systems with feedback. Causal inferences based on counterfactual analysis are exemplified and compared to those based on graphical models."]]></description>
<dc:subject>to:NB causality graphical_models have_read pearl.judea galles.david</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:63ec3efb9a57/</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:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:pearl.judea"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:galles.david"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2004.10984">
    <title>[2004.10984] A Complete Characterization of Projectivity for Statistical Relational Models</title>
    <dc:date>2020-04-26T17:24:03+00:00</dc:date>
    <link>https://arxiv.org/abs/2004.10984</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A generative probabilistic model for relational data consists of a family of probability distributions for relational structures over domains of different sizes. In most existing statistical relational learning (SRL) frameworks, these models are not projective in the sense that the marginal of the distribution for size-n structures on induced sub-structures of size k<n is equal to the given distribution for size-k structures. Projectivity is very beneficial in that it directly enables lifted inference and statistically consistent learning from sub-sampled relational structures. In earlier work some simple fragments of SRL languages have been identified that represent projective models. However, no complete characterization of, and representation framework for projective models has been given. In this paper we fill this gap: exploiting representation theorems for infinite exchangeable arrays we introduce a class of directed graphical latent variable models that precisely correspond to the class of projective relational models. As a by-product we also obtain a characterization for when a given distribution over size-k structures is the statistical frequency distribution of size-k sub-structures in much larger size-n structures. These results shed new light onto the old open problem of how to apply Halpern et al.'s "random worlds approach" for probabilistic inference to general relational signatures."]]></description>
<dc:subject>to:NB to_read relational_learning graphical_models re:your_favorite_ergm_sucks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8fbc31e54fec/</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:relational_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:your_favorite_ergm_sucks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11229-018-02014-7">
    <title>A new proposal how to handle counterexamples to Markov causation à la Cartwright, or: fixing the chemical factory | SpringerLink</title>
    <dc:date>2020-04-17T15:54:19+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11229-018-02014-7</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Cartwright (Synthese 121(1/2):3–27, 1999a; The dappled world, Cambridge University Press, Cambridge, 1999b) attacked the view that causal relations conform to the Markov condition by providing a counterexample in which a common cause does not screen off its effects: the prominent chemical factory. In this paper we suggest a new way to handle counterexamples to Markov causation such as the chemical factory. We argue that Cartwright’s as well as similar scenarios (such as decay processes, EPR/B experiments, or spontaneous macro breaking processes) feature a certain kind of non-causal dependence that kicks in once the common cause occurs. We then develop a representation of this specific kind of non-causal dependence that allows for modeling the problematic scenarios in such a way that the Markov condition is not violated anymore."]]></description>
<dc:subject>to:NB causality graphical_models philosophy_of_science</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0ff441c15352/</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:causality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:philosophy_of_science"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11336-017-9557-x">
    <title>Generalized Network Psychometrics: Combining Network and Latent Variable Models | SpringerLink</title>
    <dc:date>2020-01-26T16:32:39+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11336-017-9557-x</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce the network model as a formal psychometric model, conceptualizing the covariance between psychometric indicators as resulting from pairwise interactions between observable variables in a network structure. This contrasts with standard psychometric models, in which the covariance between test items arises from the influence of one or more common latent variables. Here, we present two generalizations of the network model that encompass latent variable structures, establishing network modeling as parts of the more general framework of structural equation modeling (SEM). In the first generalization, we model the covariance structure of latent variables as a network. We term this framework latent network modeling (LNM) and show that, with LNM, a unique structure of conditional independence relationships between latent variables can be obtained in an explorative manner. In the second generalization, the residual variance–covariance structure of indicators is modeled as a network. We term this generalization residual network modeling (RNM) and show that, within this framework, identifiable models can be obtained in which local independence is structurally violated. These generalizations allow for a general modeling framework that can be used to fit, and compare, SEM models, network models, and the RNM and LNM generalizations. This methodology has been implemented in the free-to-use software package lvnet, which contains confirmatory model testing as well as two exploratory search algorithms: stepwise search algorithms for low-dimensional datasets and penalized maximum likelihood estimation for larger datasets. We show in simulation studies that these search algorithms perform adequately in identifying the structure of the relevant residual or latent networks. We further demonstrate the utility of these generalizations in an empirical example on a personality inventory dataset."]]></description>
<dc:subject>to:NB factor_analysis graphical_models borsboom.denny psychometrics inference_to_latent_objects statistics re:g_paper re:major_depression_qu'est-ce_que_c'est have_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e10094c749c8/</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:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:borsboom.denny"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:g_paper"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:major_depression_qu'est-ce_que_c'est"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.08364">
    <title>[1801.08364] Model selection and local geometry</title>
    <dc:date>2020-01-12T22:32:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.08364</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider problems in model selection caused by the geometry of models close to their points of intersection. In some cases---including common classes of causal or graphical models, as well as time series models---distinct models may nevertheless have identical tangent spaces. This has two immediate consequences: first, in order to obtain constant power to reject one model in favour of another we need local alternative hypotheses that decrease to the null at a slower rate than the usual parametric n−1/2 (typically we will require n−1/4 or slower); in other words, to distinguish between the models we need large effect sizes or very large sample sizes. Second, we show that under even weaker conditions on their tangent cones, models in these classes cannot be made simultaneously convex by a reparameterization.
"This shows that Bayesian network models, amongst others, cannot be learned directly with a convex method similar to the graphical lasso. However, we are able to use our results to suggest methods for model selection that learn the tangent space directly, rather than the model itself. In particular, we give a generic algorithm for learning Bayesian network models."]]></description>
<dc:subject>model_selection statistics graphical_models causal_discovery in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9050bf866786/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1911.10114">
    <title>[1911.10114] Interventional Markov Equivalence for Mixed Graph Models</title>
    <dc:date>2020-01-12T22:21:53+00:00</dc:date>
    <link>https://arxiv.org/abs/1911.10114</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the problem of characterizing Markov equivalence of graphical models under general interventions. For DAGs, this problem is solved using data from an interventional setting to refine MECs of DAGs into smaller, interventional MECs. A recent graphical characterization of interventional MECs of DAGs relates to their global Markov property. Motivated by this, we generalize interventional MECs to all loopless mixed graphs via their global Markov property and generalize the graphical characterization given for DAGs to ancestral graphs. We also extend the notion of interventional Markov equivalence probabilistically: via invariance properties of distributions Markov to acyclic directed mixed graphs (ADMGs). We show that this generalization aligns with the standard causal interpretation of ADMGs. Finally, we show the two generalizations coincide at their intersection, thereby completely generalizing the characterization for DAGs to directed ancestral graphs."]]></description>
<dc:subject>to:NB graphical_models causal_inference statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1a1753eead81/</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:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/biomet/article-abstract/106/4/973/5573229">
    <title>On causal discovery with an equal-variance assumption | Biometrika | Oxford Academic</title>
    <dc:date>2019-12-03T19:43:35+00:00</dc:date>
    <link>https://academic.oup.com/biomet/article-abstract/106/4/973/5573229</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Prior work has shown that causal structure can be uniquely identified from observational data when these follow a structural equation model whose error terms have equal variance. We show that this fact is implied by an ordering among conditional variances. We demonstrate that ordering estimates of these variances yields a simple yet state-of-the-art method for causal structure learning that is readily extendable to high-dimensional problems."]]></description>
<dc:subject>causal_discovery drton.mathias graphical_models in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c9d0cec37d70/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:drton.mathias"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1911.02700">
    <title>[1911.02700] Uncertainty relations and fluctuation theorems for Bayes nets</title>
    <dc:date>2019-11-11T15:12:39+00:00</dc:date>
    <link>https://arxiv.org/abs/1911.02700</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The pioneering paper [Ito and Sagawa, 2013] analyzed the non-equilibrium statistical physics of a set of multiple interacting systems, S, whose joint discrete-time evolution is specified by a Bayesian network. The major result of [Ito and Sagawa, 2013] was an integral fluctuation theorem (IFT) governing the sum of two quantities: the entropy production (EP) of an arbitrary single v in S, and the transfer entropy from v to the other systems. Here I extend the analysis in [Ito and Sagawa, 2013]. I derive several detailed fluctuation theorems (DFTs), concerning arbitrary subsets of all the systems (including the full set). I also derive several associated IFTs, concerning an arbitrary subset of the systems, thereby extending the IFT in [Ito and Sagawa, 2013]. In addition I derive "conditional" DFTs and IFTs, involving conditional probability distributions rather than (as in conventional fluctuation theorems) unconditioned distributions. I then derive thermodynamic uncertainty relations relating the total EP of the Bayes net to the set of all the precisions of probability currents within the individual systems. I end with an example of that uncertainty relation."]]></description>
<dc:subject>graphical_models fluctuation-response stochastic_processes wolpert.david in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9000814a5906/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fluctuation-response"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolpert.david"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.12993">
    <title>[1910.12993] Characterizing Distribution Equivalence for Cyclic and Acyclic Directed Graphs</title>
    <dc:date>2019-10-30T13:39:42+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.12993</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The main way for defining equivalence among acyclic directed graphs is based on the conditional independencies of the distributions that they can generate. However, it is known that when cycles are allowed in the structure, conditional independence is not a suitable notion for equivalence of two structures, as it does not reflect all the information in the distribution that can be used for identification of the underlying structure. In this paper, we present a general, unified notion of equivalence for linear Gaussian directed graphs. Our proposed definition for equivalence is based on the set of distributions that the structure is able to generate. We take a first step towards devising methods for characterizing the equivalence of two structures, which may be cyclic or acyclic. Additionally, we propose a score-based method for learning the structure from observational data."]]></description>
<dc:subject>to:NB graphical_models causal_discovery zhang.kun statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2dd402192493/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:zhang.kun"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.10134">
    <title>[1901.10134] Identifiability of Gaussian Structural Equation Models with Homogeneous and Heterogeneous Error Variances</title>
    <dc:date>2019-10-22T13:47:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.10134</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this work, we consider the identifiability assumption of Gaussian linear structural equation models (SEMs) in which each variable is determined by a linear function of its parents plus normally distributed error. It has been shown that linear Gaussian structural equation models are fully identifiable if all error variances are the same or known. Hence, this work proves the identifiability of Gaussian SEMs with both homogeneous and heterogeneous unknown error variances. Our new identifiability assumption exploits not only error variances, but edge weights; hence, it is strictly milder than prior work on the identifiability result. We further provide a structure learning algorithm that is statistically consistent and computationally feasible, based on our new assumption. The proposed algorithm assumes that all relevant variables are observed, while it does not assume causal minimality and faithfulness. We verify our theoretical findings through simulations and real multivariate data, and compare our algorithm to state-of-the-art PC, GES and GDS algorithms."]]></description>
<dc:subject>to:NB graphical_models causal_inference statistics identifiability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5fe1f546dce1/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:identifiability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.02997">
    <title>[1910.02997] Identifying causal effects in maximally oriented partially directed acyclic graphs</title>
    <dc:date>2019-10-11T22:22:58+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.02997</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We develop a necessary and sufficient causal identification criterion for maximally oriented partially directed acyclic graphs (MPDAGs). MPDAGs as a class of graphs include directed acyclic graphs (DAGs), completed partially directed acyclic graphs (CPDAGs), and CPDAGs with added background knowledge. As such, they represent the type of graph that can be learned from observational data and background knowledge under the assumption of no latent variables.
"Our identification criterion can be seen as a generalization of the g-formula of Robins (1986). We further obtain the generalization of the truncated factorization formula for DAGs (Pearl, 2009) and compare our criterion to the generalized adjustment criterion of Perković et al. (2017)."]]></description>
<dc:subject>to:NB causal_inference graphical_models statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0281b0d61af2/</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:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1807.02877">
    <title>[1807.02877] Moderated Network Models</title>
    <dc:date>2019-10-02T15:49:23+00:00</dc:date>
    <link>https://arxiv.org/abs/1807.02877</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Pairwise network models such as the Gaussian Graphical Model (GGM) are a powerful and intuitive way to analyze dependencies in multivariate data. A key assumption of the GGM is that each pairwise interaction is independent of the values of all other variables. However, in psychological research this is often implausible. In this paper, we extend the GGM by allowing each pairwise interaction between two variables to be moderated by (a subset of) all other variables in the model, and thereby introduce a Moderated Network Model (MNM). We show how to construct the MNM and propose an L1-regularized nodewise regression approach to estimate it. We provide performance results in a simulation study and show that MNMs outperform the split-sample based methods Network Comparison Test (NCT) and Fused Graphical Lasso (FGL) in detecting moderation effects. Finally, we provide a fully reproducible tutorial on how to estimate MNMs with the R-package mgm and discuss possible issues with model misspecification."]]></description>
<dc:subject>to:NB graphical_models statistics borsboom.denny</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1de588ac00e9/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:borsboom.denny"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.13186">
    <title>[1909.13186] Causal screening for dynamical systems</title>
    <dc:date>2019-10-01T16:19:21+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.13186</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many classical algorithms output graphical representations of causal structures by testing conditional independence among a set of random variables. In dynamical systems, local independence can be used analogously as a testable implication of the underlying data-generating process. We suggest some inexpensive methods for causal screening which provide output with a sound causal interpretation under the assumption of ancestral faithfulness. The popular model class of linear Hawkes processes is used to provide an example of a dynamical causal model. We argue that for sparse causal graphs the output will often be close to complete. We give examples of this framework and apply it to a challenging biological system."]]></description>
<dc:subject>to:NB time_series causal_discovery graphical_models point_processes statistics to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:71e9331e2bf9/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:point_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.13189">
    <title>[1909.13189] Learning Sparse Nonparametric DAGs</title>
    <dc:date>2019-10-01T16:16:54+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.13189</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We develop a framework for learning sparse nonparametric directed acyclic graphs (DAGs) from data. Our approach is based on a recent algebraic characterization of DAGs that led to the first fully continuous optimization for score-based learning of DAG models parametrized by a linear structural equation model (SEM). We extend this algebraic characterization to nonparametric SEM by leveraging nonparametric sparsity based on partial derivatives, resulting in a continuous optimization problem that can be applied to a variety of nonparametric and semiparametric models including GLMs, additive noise models, and index models as special cases. We also explore the use of neural networks and orthogonal basis expansions to model nonlinearities for general nonparametric models. Extensive empirical study confirms the necessity of nonlinear dependency and the advantage of continuous optimization for score-based learning."]]></description>
<dc:subject>causal_discovery graphical_models optimization statistics ravikumar.pradeep xing.eric sparsity to_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e6bdf1913768/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ravikumar.pradeep"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:xing.eric"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sparsity"/>
	<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/1909.09141">
    <title>[1909.09141] Causal Modeling for Fairness in Dynamical Systems</title>
    <dc:date>2019-09-26T18:36:19+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.09141</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this work, we present causal directed acyclic graphs (DAGs) as a unifying framework for the recent literature on fairness in dynamical systems. We advocate for the use of causal DAGs as a tool in both designing equitable policies and estimating their impacts. By visualizing models of dynamic unfairness graphically, we expose implicit causal assumptions which can then be more easily interpreted and scrutinized by domain experts. We demonstrate that this method of reinterpretation can be used to critique the robustness of an existing model/policy, or uncover new policy evaluation questions. Causal models also enable a rich set of options for evaluating a new candidate policy without incurring the risk of implementing the policy in the real world. We close the paper with causal analyses of several models from the recent literature, and provide an in-depth case study to demonstrate the utility of causal DAGs for modeling fairness in dynamical systems."]]></description>
<dc:subject>graphical_models algorithmic_fairness in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bb077be7c3c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algorithmic_fairness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.07186">
    <title>[1909.07186] Graph learning: How humans infer and represent networks</title>
    <dc:date>2019-09-25T04:07:58+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.07186</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Humans communicate, receive, and store information using sequences of items -- from words in a sentence or notes in music to abstract concepts in lectures and books. The networks formed by these items (nodes) and the sequential transitions between them (edges) encode important structural features of human communication and knowledge. But how do humans learn the networks of probabilistic transitions that underlie sequences of items? Moreover, what do people's internal maps of these networks look like? Here, we introduce graph learning, a growing and interdisciplinary field focused on studying how humans learn and represent networks in the world around them. We begin by describing established results from statistical learning showing that humans are adept at detecting differences in the transition probabilities between items in a sequence. We next present recent experiments that directly control for differences in transition probabilities, demonstrating that human behavior also depends critically on the abstract network structure of transitions. Finally, we present computational models that researchers have proposed to explain the effects of network structure on human behavior and cognition. Throughout, we highlight a number of exciting open questions in the study of graph learning that will require creative insights from cognitive scientists and network scientists alike."]]></description>
<dc:subject>to:NB graphical_models cognitive_science psychology psychology_by_physicists color_me_skeptical bassett.danielle_s.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8733bccd2647/</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:cognitive_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychology_by_physicists"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bassett.danielle_s."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.09596#">
    <title>[1909.09596] Non-Parametric Structure Learning on Hidden Tree-Shaped Distributions</title>
    <dc:date>2019-09-25T03:27:14+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.09596#</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We provide high probability sample complexity guarantees for non-parametric structure learning of tree-shaped graphical models whose nodes are discrete random variables with a finite or countable alphabet, both in the noiseless and noisy regimes. First, we introduce a new, fundamental quantity called the (noisy) information threshold, which arises naturally from the error analysis of the Chow-Liu algorithm and characterizes not only the sample complexity, but also the inherent impact of the noise on the structure learning task, without explicit assumptions on the distribution of the model. This allows us to present the first non-parametric, high-probability finite sample complexity bounds on tree-structure learning from potentially noise-corrupted data. In particular, for number of nodes p, success rate 1−δ, and a fixed value of the information threshold, our sample complexity bounds for exact structure recovery are of the order of (log1+ζ(p/δ)), for all ζ>0, for both noiseless and noisy settings. Subsequently, we apply our results on two classes of hidden models, namely, the M-ary erasure channel and the generalized symmetric channel, illustrating the usefulness and importance of our framework. As a byproduct of our analysis, this paper resolves the open problem of tree structure learning in the presence of non-identically distributed observation noise, providing explicit conditions on the convergence of the Chow-Liu algorithm under this setting as well."]]></description>
<dc:subject>to:NB graphical_models chow-liu_trees statistics sarwate.anand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d6cc6279d578/</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:chow-liu_trees"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sarwate.anand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.06282">
    <title>[1812.06282] A Generalization of Hierarchical Exchangeability on Trees to Directed Acyclic Graphs</title>
    <dc:date>2019-09-23T14:17:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.06282</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A random array indexed by the paths of an infinitely-branching rooted tree of finite depth is hierarchically exchangeable if its joint distribution is invariant under rearrangements that preserve the tree structure underlying the index set. Austin and Panchenko (2014) prove that such arrays have de Finetti-type representations, and moreover, that an array indexed by a finite collection of such trees has an Aldous-Hoover-type representation.
"Motivated by the problem of designing inference-friendly Bayesian nonparametric models in probabilistic programming languages, we generalize hierarchical exchangeability to a new kind of partial exchangeability for random arrays which we call DAG-exchangeability. In our setting a random array is indexed by N^|V| for some DAG G=(V,E), and its exchangeability structure is governed by the edge set E. We prove a representation theorem for such arrays which generalizes the Aldous-Hoover and Austin-Panchenko representation theorems."]]></description>
<dc:subject>to:NB graphical_models probability exchangeability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:485f7baffd8e/</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:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:exchangeability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.03586">
    <title>[1909.03586] Curve Fitting from Probabilistic Emissions and Applications to Dynamic Item Response Theory</title>
    <dc:date>2019-09-15T14:25:29+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.03586</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Item response theory (IRT) models are widely used in psychometrics and educational measurement, being deployed in many high stakes tests such as the GRE aptitude test. IRT has largely focused on estimation of a single latent trait (e.g. ability) that remains static through the collection of item responses. However, in contemporary settings where item responses are being continuously collected, such as Massive Open Online Courses (MOOCs), interest will naturally be on the dynamics of ability, thus complicating usage of traditional IRT models. We propose DynAEsti, an augmentation of the traditional IRT Expectation Maximization algorithm that allows ability to be a continuously varying curve over time. In the process, we develop CurvFiFE, a novel non-parametric continuous-time technique that handles the curve-fitting/regression problem extended to address more general probabilistic emissions (as opposed to simply noisy data points). Furthermore, to accomplish this, we develop a novel technique called grafting, which can successfully approximate distributions represented by graphical models when other popular techniques like Loopy Belief Propogation (LBP) and Variational Inference (VI) fail. The performance of DynAEsti is evaluated through simulation, where we achieve results comparable to the optimal of what is observed in the static ability scenario. Finally, DynAEsti is applied to a longitudinal performance dataset (80-years of competitive golf at the 18-hole Masters Tournament) to demonstrate its ability to recover key properties of human performance and the heterogeneous characteristics of the different holes. Python code for CurvFiFE and DynAEsti is publicly available at this http URL. This is the full version of our ICDM 2019 paper."]]></description>
<dc:subject>to:NB inference_to_latent_objects graphical_models statistics psychometrics non-stationarity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5b52b9085c6c/</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:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:psychometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-stationarity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/0804.4451">
    <title>[0804.4451] Dependence Structure Estimation via Copula</title>
    <dc:date>2019-09-15T14:23:29+00:00</dc:date>
    <link>https://arxiv.org/abs/0804.4451</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Dependence strucuture estimation is one of the important problems in machine learning domain and has many applications in different scientific areas. In this paper, a theoretical framework for such estimation based on copula and copula entropy -- the probabilistic theory of representation and measurement of statistical dependence, is proposed. Graphical models are considered as a special case of the copula framework. A method of the framework for estimating maximum spanning copula is proposed. Due to copula, the method is irrelevant to the properties of individual variables, insensitive to outlier and able to deal with non-Gaussianity. Experiments on both simulated data and real dataset demonstrated the effectiveness of the proposed method."

--- How does this differ from the "nonparanormal" models we know and love around here?]]></description>
<dc:subject>to:NB causal_discovery copulas statistics graphical_models color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:16fb254fdc52/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:copulas"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<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/1909.05418">
    <title>[1909.05418] The Global Markov Property for a Mixture of DAGs</title>
    <dc:date>2019-09-13T13:18:47+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.05418</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Real causal processes may contain feedback loops and change over time. In this paper, we model cycles and non-stationary distributions using a mixture of directed acyclic graphs (DAGs). We then study the conditional independence (CI) relations induced by a density that factorizes according to a mixture of DAGs in two steps. First, we generalize d-separation for a single DAG to mixture d-separation for a mixture of DAGs. We then utilize the mixture d-separation criterion to derive a global Markov property that allows us to read off the CI relations induced by a mixture of DAGs using a particular summary graph. This result has potentially far reaching applications in algorithm design for causal discovery."]]></description>
<dc:subject>to:NB causal_discovery graphical_models statistics color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ddc3bb1cc66d/</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_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<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/1709.01577">
    <title>[1709.01577] Auto-G-Computation of Causal Effects on a Network</title>
    <dc:date>2019-08-26T23:46:23+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.01577</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Methods for inferring average causal effects have traditionally relied on two key assumptions: (i) the intervention received by one unit cannot causally influence the outcome of another; and (ii) units can be organized into non-overlapping groups such that outcomes of units in separate groups are independent. In this paper, we develop new statistical methods for causal inference based on a single realization of a network of connected units for which neither assumption (i) nor (ii) holds. The proposed approach allows both for arbitrary forms of interference, whereby the outcome of a unit may depend on interventions received by other units with whom a network path through connected units exists; and long range dependence, whereby outcomes for any two units likewise connected by a path in the network may be dependent. Under network versions of consistency and no unobserved confounding, inference is made tractable by an assumption that the network's outcome, treatment and covariate vectors are a single realization of a certain chain graph model. This assumption allows inferences about various network causal effects via the auto-g-computation algorithm, a network generalization of Robins' well-known g-computation algorithm previously described for causal inference under assumptions (i) and (ii)."

--- I feel like I've read something very similar in another paper by Ilya & Eric, but maybe I just heard them talk about it?]]></description>
<dc:subject>to:NB graphical_models causal_inference network_data_analysis statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e0ce00880176/</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:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>