<?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://faculty.washington.edu/yenchic/short_note/note_MoM.pdf"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2501.07772"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2308.03296"/>
	<rdf:li rdf:resource="https://www.nber.org/papers/w32906"/>
	<rdf:li rdf:resource="https://osf.io/7vy2f/"/>
	<rdf:li rdf:resource="https://academic.oup.com/ej/article-abstract/127/605/F236/5069452?login=false"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/physics/0001019"/>
	<rdf:li rdf:resource="https://journals.aps.org/pre/abstract/10.1103/PhysRevE.51.3871"/>
	<rdf:li rdf:resource="https://www.jstor.org/stable/2336834"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12661?campaign=wolacceptedarticle"/>
	<rdf:li rdf:resource="https://research.google/pubs/pub49197/"/>
	<rdf:li rdf:resource="https://direct.mit.edu/rest/article-abstract/101/5/743/58556/Choosing-among-Regularized-Estimators-in-Empirical?redirectedFrom=fulltext"/>
	<rdf:li rdf:resource="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3557282"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2102.05802"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.03826"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1701.01207"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.08766"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.04390"/>
	<rdf:li rdf:resource="https://ieeexplore.ieee.org/document/9387338"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-040720-024710"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/10.1111/sjos.12530?af=R"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.03167"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2103.01604"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.04416"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.15678"/>
	<rdf:li rdf:resource="https://doi.org/10.1093/imaiai/iaz025"/>
	<rdf:li rdf:resource="https://academic.oup.com/imaiai/article-abstract/9/4/813/5627733"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.09874"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-031219-041228"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.09422"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.07167"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.14999"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.06838"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.14762"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.10240"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/full/10.1080/01621459.2020.1773832"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1581930134"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1594972829"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.08511"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2010.13687"/>
	<rdf:li rdf:resource="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0235318"/>
	<rdf:li rdf:resource="http://papers.nips.cc/paper/3693-asymptotically-optimal-regularization-in-smooth-parametric-models"/>
	<rdf:li rdf:resource="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=917901"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1911.01483"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.11540"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1602.02201"/>
	<rdf:li rdf:resource="https://www.mitpressjournals.org/doi/abs/10.1162/rest_a_00795"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.08390"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.09457"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.07185"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.09965"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1904.03313"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.10828"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.09336"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.05582"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.08109"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.00579"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.06163"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1302.0890"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.00555"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.04748"/>
	<rdf:li rdf:resource="https://global.oup.com/academic/product/non-standard-parametric-statistical-inference-9780198505044?cc=us&amp;lang=en#"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.00598"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.00310"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1510.00551"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.08283"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1712.07248"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.05944"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1805.07454"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.06576"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://faculty.washington.edu/yenchic/short_note/note_MoM.pdf">
    <title>A short note on the median-of-means estimator (Yen-Chi Chen, 2020)</title>
    <dc:date>2026-04-23T16:43:42+00:00</dc:date>
    <link>https://faculty.washington.edu/yenchic/short_note/note_MoM.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Very nice.]]></description>
<dc:subject>to:NB have_read statistics heavy_tails estimation empirical_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ee5135168ce3/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heavy_tails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2501.07772">
    <title>[2501.07772] Bridging Root-$n$ and Non-standard Asymptotics: Dimension-agnostic Adaptive Inference in M-Estimation</title>
    <dc:date>2025-03-24T00:12:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2501.07772</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This manuscript studies a general approach to construct confidence sets for the solution of population-level optimization, commonly referred to as M-estimation. Statistical inference for M-estimation poses significant challenges due to the non-standard limiting behaviors of the corresponding estimator, which arise in settings with increasing dimension of parameters, non-smooth objectives, or constraints. We propose a simple and unified method that guarantees validity in both regular and irregular cases. Moreover, we provide a comprehensive width analysis of the proposed confidence set, showing that the convergence rate of the diameter is adaptive to the unknown degree of instance-specific regularity. We apply the proposed method to several high-dimensional and irregular statistical problems."]]></description>
<dc:subject>to:NB statistics estimation kuchibhotla.arun_kmar re:HEAS via:lal.apoorva</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:493622f19ddd/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kuchibhotla.arun_kmar"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:lal.apoorva"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2308.03296">
    <title>[2308.03296] Studying Large Language Model Generalization with Influence Functions</title>
    <dc:date>2025-03-10T15:14:03+00:00</dc:date>
    <link>https://arxiv.org/abs/2308.03296</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which training examples most contribute to a given behavior? Influence functions aim to answer a counterfactual: how would the model's parameters (and hence its outputs) change if a given sequence were added to the training set? While influence functions have produced insights for small models, they are difficult to scale to large language models (LLMs) due to the difficulty of computing an inverse-Hessian-vector product (IHVP). We use the Eigenvalue-corrected Kronecker-Factored Approximate Curvature (EK-FAC) approximation to scale influence functions up to LLMs with up to 52 billion parameters. In our experiments, EK-FAC achieves similar accuracy to traditional influence function estimators despite the IHVP computation being orders of magnitude faster. We investigate two algorithmic techniques to reduce the cost of computing gradients of candidate training sequences: TF-IDF filtering and query batching. We use influence functions to investigate the generalization patterns of LLMs, including the sparsity of the influence patterns, increasing abstraction with scale, math and programming abilities, cross-lingual generalization, and role-playing behavior. Despite many apparently sophisticated forms of generalization, we identify a surprising limitation: influences decay to near-zero when the order of key phrases is flipped. Overall, influence functions give us a powerful new tool for studying the generalization properties of LLMs."]]></description>
<dc:subject>in_NB have_read optimization statistics computational_statistics neural_networks large_language_models_(so_called) estimation re:large_language_models_in_statistical_perspective feral_library_catalogs re:gopnikism to_teach:statistics_and_generative_ai</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3b2888a6a8c1/</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:have_read"/>
	<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:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_language_models_(so_called)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:large_language_models_in_statistical_perspective"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:feral_library_catalogs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:gopnikism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_and_generative_ai"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nber.org/papers/w32906">
    <title>Adapting to Misspecification | NBER</title>
    <dc:date>2025-03-08T21:25:44+00:00</dc:date>
    <link>https://www.nber.org/papers/w32906</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Empirical research typically involves a robustness-efficiency tradeoff. A researcher seeking to estimate a scalar parameter can invoke strong assumptions to motivate a restricted estimator that is precise but may be heavily biased, or they can relax some of these assumptions to motivate a more robust, but variable, unrestricted estimator. When a bound on the bias of the restricted estimator is available, it is optimal to shrink the unrestricted estimator towards the restricted estimator. For settings where a bound on the bias of the restricted estimator is unknown, we propose adaptive estimators that minimize the percentage increase in worst case risk relative to an oracle that knows the bound. We show that adaptive estimators solve a weighted convex minimax problem and provide lookup tables facilitating their rapid computation. Revisiting some well known empirical studies where questions of model specification arise, we examine the advantages of adapting to—rather than testing for—misspecification."

--- TODO: See if they mention Hjort & Claesken's "focused information criterion", which is at least similar in inspiration; re-read H&C on this point.]]></description>
<dc:subject>to:NB estimation misspecification statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:87581585e77d/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:misspecification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://osf.io/7vy2f/">
    <title>OSF Preprints | Quantitative Political Science Research is Greatly Underpowered</title>
    <dc:date>2023-05-02T20:12:17+00:00</dc:date>
    <link>https://osf.io/7vy2f/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We analyze the statistical power of political science research by collating over 16,000 hypothesis tests from about 2,000 articles. Even with generous assumptions, the median analysis has about 10% power, and only about 1 in 10 tests have at least 80% power to detect the consensus effects reported in the literature. There is also substantial heterogeneity in tests across research areas, with some being characterized by high-power but most having very low power. To contextualize our findings, we survey political methodologists to assess their expectations about power levels. Most methodologists greatly overestimate the statistical power of political science research."]]></description>
<dc:subject>to:NB to_read political_science social_science_methodology statistics hypothesis_testing estimation re:neutral_model_of_inquiry</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c31528a09f2b/</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:political_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_science_methodology"/>
	<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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:neutral_model_of_inquiry"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/ej/article-abstract/127/605/F236/5069452?login=false">
    <title>Power of Bias in Economics Research | The Economic Journal | Oxford Academic</title>
    <dc:date>2023-05-02T20:10:08+00:00</dc:date>
    <link>https://academic.oup.com/ej/article-abstract/127/605/F236/5069452?login=false</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We investigate two critical dimensions of the credibility of empirical economics research: statistical power and bias. We survey 159 empirical economics literatures that draw upon 64,076 estimates of economic parameters reported in more than 6,700 empirical studies. Half of the research areas have nearly 90% of their results under‐powered. The median statistical power is 18%, or less. A simple weighted average of those reported results that are adequately powered (power ≥ 80%) reveals that nearly 80% of the reported effects in these empirical economics literatures are exaggerated; typically, by a factor of two and with one‐third inflated by a factor of four or more."

--- Power's really a function, not a number, so where's "18%" come from?  Is that the power to detect an effect of the magnitude estimated (a little weirdly recursive...), or some standard-size magnitude?
--- ETA after reading: Yes, for each area of economics they do a supposedly-robust meta-estimate of the effect size, and try to work out the power to detect an effect that big.]]></description>
<dc:subject>to:NB economics econometrics statistics hypothesis_testing re:neutral_model_of_inquiry estimation have_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2c2f32247eac/</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:econometrics"/>
	<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:re:neutral_model_of_inquiry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/physics/0001019">
    <title>[physics/0001019] Approaching the parameter estimation quality of maximum likelihood via generalized moments</title>
    <dc:date>2023-05-01T20:12:15+00:00</dc:date>
    <link>https://arxiv.org/abs/physics/0001019</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A simple criterion is presented for a practical construction of generalized moments that allow one to approach the theoretical Rao-Cramer limit for parameter estimation while avoiding the complexity of the maximum likelihood method in the cases of complicated probability distributions and/or very large event samples."

--- To summarize: (1) maximimizing the MLE is equivalent to finding the parameter value where the mean of the gradient of the log-likelihood is zero.  (This is what Anglophone statistics calls the "score function", which is a horribly opaque name.)  (2) If we replace the gradient of the log-likelihood by a function that's close to it, but more tractable, setting _its_ mean to zero gives us estimates that are almost as efficient as the MLE.  (FVT works out the Taylor series.)  (3) The functions only have to be close in regions of high (true) probability.  I don't think this is as radical as the author did (it's just another Z estimator and I don't see how it helps when the true pdf is really intractable), but it's clever and illuminating and potentially helpful.]]></description>
<dc:subject>in_NB have_read likelihood estimation statistics 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:418dde8076ff/</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:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<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://journals.aps.org/pre/abstract/10.1103/PhysRevE.51.3871">
    <title>Phys. Rev. E 51, 3871 (1995) - Symbol sequence statistics in noisy chaotic signal reconstruction</title>
    <dc:date>2023-04-24T21:48:32+00:00</dc:date>
    <link>https://journals.aps.org/pre/abstract/10.1103/PhysRevE.51.3871</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A method is discussed for reconstructing chaotic systems from noisy signals using a symbolic approach. The state space of the dynamical system is partitioned into subregions and a symbol is assigned to each subregion. Consequently, an orbit in a continuous state space is converted into a long symbol string. The probabilities of occurrence for different symbol sequences constitute the symbol sequence statistics. The symbol sequence statistics are easily measured from the signal output and are used as the target for reconstruction (i.e., for assessing the goodness of fit of proposed models). Reliable reconstructions were achieved given a noisy chaotic signal, provided the general class of the model of the underlying dynamics is known. Both observational and dynamical noise were considered, and they were not limited to small amplitudes. Substantial noise produces a strong bias in the symbol sequence statistics, but such bias can be tracked and effectively eliminated by including the noise characteristics in the model. This is demonstrated by the robust reconstruction of the Hénon and Ikeda maps even when the signal to noise ratio is ≊1. Applications of this method include extracting control parameters for nonlinear dynamical systems and nonlinear model evaluation from experimental data."]]></description>
<dc:subject>symbolic_dynamics dynamical_systems time_series statistical_inference_for_stochastic_processes cleaning_out_the_filing_cabinet_for_the_first_time_since_2005 have_read re:dissertation estimation in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:04d216b60071/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:symbolic_dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamical_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cleaning_out_the_filing_cabinet_for_the_first_time_since_2005"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:dissertation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.jstor.org/stable/2336834">
    <title>Parameter-Based Asymptotics on JSTOR</title>
    <dc:date>2023-04-24T21:32:07+00:00</dc:date>
    <link>https://www.jstor.org/stable/2336834</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In certain cases statistical methods based on standard maximum likelihood asymptotics become valid as the true parameter value approaches a boundary of the parameter space. Examples are given which motivate a general parameter-based asymptotic theory, and a result is obtained which covers such situations. Of particular interest are applications to stochastic process models."]]></description>
<dc:subject>to_reread estimation statistics cleaning_out_the_filing_cabinet_for_the_first_time_since_2005 likelihood statistical_inference_for_stochastic_processes re:HEAS in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5c278c6fcc6d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_reread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cleaning_out_the_filing_cabinet_for_the_first_time_since_2005"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12661?campaign=wolacceptedarticle">
    <title>Higher order asymptotics of minimax estimators for time series - Xu - - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2022-06-28T18:35:06+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12661?campaign=wolacceptedarticle</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the minimax estimation of time series in view of higher order asymptotic theory. Under the framework of Bayesian inference, we focus on the Bayes estimator and the Bayesian Whittle estimator for parameter estimation. It is shown that these estimators are minimax with respect to the Bayes risk of higher order bias appeared in their asymptotic expansion. The minimax problem in the boundary issue with parameter on the boundary of parameter space is also discussed. Our theoretical discovery is justified by simulation studies even when the sample size is small."]]></description>
<dc:subject>to:NB time_series minimax estimation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0abb8bc64211/</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:minimax"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://research.google/pubs/pub49197/">
    <title>Predictive State Propensity Subclassification (PSPS): A causal inference method for optimal data-driven propensity score stratification – Google Research</title>
    <dc:date>2022-03-16T14:27:13+00:00</dc:date>
    <link>https://research.google/pubs/pub49197/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce Predictive State Propensity Subclassification (PSPS), a novel estimation method for undertaking causal inference from observational studies. The methodology applies to both discrete and continuous treatments and can estimate unit-level and population-level average treatment effects. PSPS combines propensity and outcome models into one encompassing probabilistic model, which can be jointly estimated using maximum likelihood or Bayesian inference. We give a detailed overview on the TensorFlow implementation for likelihood optimization and show via large-scale simulations that it outperforms several state of the art methods -- both in terms of bias and variance for average as well as unit-level treatment effects. Finally we illustrate the methodology and algorithms on standard datasets in the literature."

--- Forthcoming, CLeaR 2022 [https://www.cclear.cc/Acceptedpapers]; obviously I wasn't involved in the refereeing because GMG was my Ph.D. student.]]></description>
<dc:subject>to:NB causal_inference statistics estimation prediction_processes kith_and_kin goerg.georg_m.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:07155ec09ca0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goerg.georg_m."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://direct.mit.edu/rest/article-abstract/101/5/743/58556/Choosing-among-Regularized-Estimators-in-Empirical?redirectedFrom=fulltext">
    <title>Choosing among Regularized Estimators in Empirical Economics: The Risk of Machine Learning | The Review of Economics and Statistics | MIT Press</title>
    <dc:date>2022-03-14T18:19:21+00:00</dc:date>
    <link>https://direct.mit.edu/rest/article-abstract/101/5/743/58556/Choosing-among-Regularized-Estimators-in-Empirical?redirectedFrom=fulltext</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many settings in empirical economics involve estimation of a large number of parameters. In such settings, methods that combine regularized estimation and data-driven choices of regularization parameters are useful. We provide guidance to applied researchers on the choice between regularized estimators and data-driven selection of regularization parameters. We characterize the risk and relative performance of regularized estimators as a function of the data-generating process and show that data-driven choices of regularization parameters yield estimators with risk uniformly close to the risk attained under the optimal (unfeasible) choice of regularization parameters. We illustrate using examples from empirical economics."]]></description>
<dc:subject>to:NB econometrics estimation statistics learning_theory to_teach:childs_garden_of_statistical_learning_theory re:HEAS downloaded cross-validation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:765356ad4562/</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:econometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:childs_garden_of_statistical_learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:downloaded"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3557282">
    <title>Inference for Ranks with Applications to Mobility across Neighborhoods and Academic Achievement across Countries by Magne Mogstad, Joseph P. Romano, Azeem Shaikh, Daniel Wilhelm :: SSRN</title>
    <dc:date>2021-12-07T14:28:12+00:00</dc:date>
    <link>https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3557282</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["It is often desired to rank different populations according to the value of some feature of each population. For example, it may be desired to rank neighborhoods according to some measure of intergenerational mobility or countries according to some measure of academic achievement. These rankings are invariably computed using estimates rather than the true values of these features. As a result, there may be considerable uncertainty concerning the rank of each population. In this paper, we consider the problem of accounting for such uncertainty by constructing confidence sets for the rank of each population. We consider both the problem of constructing marginal confidence sets for the rank of a particular population as well as simultaneous confidence sets for the ranks of all populations. We show how to construct such confidence sets under weak assumptions. An important feature of all of our constructions is that they remain computationally feasible even when the number of populations is very large. We apply our theoretical results to re-examine the rankings of both neighborhoods in the United States in terms of intergenerational mobility and developed countries in terms of academic achievement. The conclusions about which countries do best and worst at reading, math, and science are fairly robust to accounting for uncertainty. By comparison, several celebrated findings about intergenerational mobility in the United states are not robust to taking uncertainty into account."]]></description>
<dc:subject>confidence_sets ranking estimation statistics transmission_of_inequality to_teach:statistics_of_inequality_and_discrimination via:civilstat in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:462588e9a47e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ranking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:transmission_of_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:via:civilstat"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2102.05802">
    <title>[2102.05802] Fisher Information and Mutual Information Constraints</title>
    <dc:date>2021-07-12T14:50:43+00:00</dc:date>
    <link>https://arxiv.org/abs/2102.05802</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the processing of statistical samples X∼Pθ by a channel p(y|x), and characterize how the statistical information from the samples for estimating the parameter θ∈ℝd can scale with the mutual information or capacity of the channel. We show that if the statistical model has a sub-Gaussian score function, then the trace of the Fisher information matrix for estimating θ from Y can scale at most linearly with the mutual information between X and Y. We apply this result to obtain minimax lower bounds in distributed statistical estimation problems, and obtain a tight preconstant for Gaussian mean estimation. We then show how our Fisher information bound can also imply mutual information or Jensen-Shannon divergence based distributed strong data processing inequalities."]]></description>
<dc:subject>to:NB information_theory estimation minimax re:HEAS statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:172027cea48f/</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:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:minimax"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.03826">
    <title>[2107.03826] Asymptotic normality of robust $M$-estimators with convex penalty</title>
    <dc:date>2021-07-11T05:57:15+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.03826</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper develops asymptotic normality results for individual coordinates of robust M-estimators with convex penalty in high-dimensions, where the dimension p is at most of the same order as the sample size n, i.e, p/n≤γ for some fixed constant γ>0. The asymptotic normality requires a bias correction and holds for most coordinates of the M-estimator for a large class of loss functions including the Huber loss and its smoothed versions regularized with a strongly convex penalty.
"The asymptotic variance that characterizes the width of the resulting confidence intervals is estimated with data-driven quantities. This estimate of the variance adapts automatically to low (p/n→0) or high (p/n≤γ) dimensions and does not involve the proximal operators seen in previous works on asymptotic normality of M-estimators. For the Huber loss, the estimated variance has a simple expression involving an effective degrees-of-freedom as well as an effective sample size. The case of the Huber loss with Elastic-Net penalty is studied in details and a simulation study confirms the theoretical findings. The asymptotic normality results follow from Stein formulae for high-dimensional random vectors on the sphere developed in the paper which are of independent interest."]]></description>
<dc:subject>to:NB estimation re:HEAS statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4d4a323ea84c/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1701.01207">
    <title>[1701.01207] Learning Semidefinite Regularizers</title>
    <dc:date>2021-06-10T02:08:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1701.01207</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Regularization techniques are widely employed in optimization-based approaches for solving ill-posed inverse problems in data analysis and scientific computing. These methods are based on augmenting the objective with a penalty function, which is specified based on prior domain-specific expertise to induce a desired structure in the solution. We consider the problem of learning suitable regularization functions from data in settings in which precise domain knowledge is not directly available. Previous work under the title of `dictionary learning' or `sparse coding' may be viewed as learning a regularization function that can be computed via linear programming. We describe generalizations of these methods to learn regularizers that can be computed and optimized via semidefinite programming. Our framework for learning such semidefinite regularizers is based on obtaining structured factorizations of data matrices, and our algorithmic approach for computing these factorizations combines recent techniques for rank minimization problems along with an operator analog of Sinkhorn scaling. Under suitable conditions on the input data, our algorithm provides a locally linearly convergent method for identifying the correct regularizer that promotes the type of structure contained in the data. Our analysis is based on the stability properties of Operator Sinkhorn scaling and their relation to geometric aspects of determinantal varieties (in particular tangent spaces with respect to these varieties). The regularizers obtained using our framework can be employed effectively in semidefinite programming relaxations for solving inverse problems."

--- Last tag because learning "the type of structure contained in the data" _is_ the problem of induction!  So my suspicion, based on no more than the abstract and philosophical prejudice, is that they have pre-judged what types of structure they will find, and may have an effective way of fine-tuning it.]]></description>
<dc:subject>to:NB optimization statistics estimation color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d03e0ef626e9/</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:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.08766">
    <title>[2105.08766] The Minimax Estimator of the Average Treatment Effect, among Linear Combinations of Conditional Average Treatment Effects Estimators</title>
    <dc:date>2021-05-20T16:53:06+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.08766</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["I consider the estimation of the average treatment effect (ATE), in a population that can be divided into G groups, and such that one has unbiased and uncorrelated estimators of the conditional average treatment effect (CATE) in each group. These conditions are for instance met in stratified randomized experiments. I first assume that the outcome is homoscedastic, and that each CATE is bounded in absolute value by B standard deviations of the outcome, for some known constant B. I derive, across all linear combinations of the CATEs' estimators, the estimator of the ATE with the lowest worst-case mean-squared error. This optimal estimator assigns a weight equal to group g's share in the population to the most precisely estimated CATEs, and a weight proportional to one over the CATE's variance to the least precisely estimated CATEs. This optimal estimator is feasible: the weights only depend on known quantities. I then allow for heteroskedasticity and for positive correlations between the estimators. This latter condition is often met in differences-in-differences designs, where the CATEs are estimators of the effect of having been treated for a certain number of time periods. In that case, the optimal estimator is no longer feasible, as it depends on unknown quantities, but a feasible estimator can easily be constructed by replacing those unknown quantities by estimators."]]></description>
<dc:subject>to:NB causal_inference estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cd393cf47264/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.04390">
    <title>[2105.04390] Statistical inference for continuous-time locally stationary processes using stationary approximations</title>
    <dc:date>2021-05-12T18:16:26+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.04390</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We establish asymptotic properties of M-estimators, defined in terms of a contrast function and observations from a continuous-time locally stationary process. Using the stationary approximation of the sequence, θ-weak dependence, and hereditary properties, we give sufficient conditions on the contrast function that ensure consistency and asymptotic normality of the M-estimator. As an example, we obtain consistency and asymptotic normality of a localized least squares estimator for observations from a sequence of time-varying Lévy-driven Ornstein-Uhlenbeck processes. Furthermore, for a sequence of time-varying Lévy-driven state space models, we show consistency of a localized Whittle estimator and an M-estimator that is based on a quasi maximum likelihood contrast. Simulation studies show the applicability of the estimation procedures."]]></description>
<dc:subject>to:NB estimation time_series statistics non-stationarity statistical_inference_for_stochastic_processes re:codename:catherine_wheel</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:df61a132f071/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-stationarity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:codename:catherine_wheel"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://ieeexplore.ieee.org/document/9387338">
    <title>The Rate-Distortion Risk in Estimation From Compressed Data | IEEE Journals &amp; Magazine | IEEE Xplore</title>
    <dc:date>2021-04-23T03:04:08+00:00</dc:date>
    <link>https://ieeexplore.ieee.org/document/9387338</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Consider the problem of estimating a latent signal from a lossy compressed version of the data when the compressor is agnostic to the relation between the signal and the data. This situation arises in a host of modern applications when data is transmitted or stored prior to determining the downstream inference task. Given a bitrate constraint and a distortion measure between the data and its compressed version, let us consider the joint distribution achieving Shannon’s rate-distortion (RD) function. Given an estimator and a loss function associated with the downstream inference task, define the RD risk as the expected loss under the RD-achieving distribution. We provide general conditions under which the operational risk in estimating from the compressed data is asymptotically equivalent to the RD risk. The main theoretical tools to prove this equivalence are transportation-cost inequalities in conjunction with properties of compression codes achieving Shannon’s RD function. Whenever such equivalence holds, a recipe for designing estimators from datasets undergoing lossy compression without specifying the actual compression technique emerges: design the estimator to minimize the RD risk. Our conditions are simplified in the special cases of discrete memoryless or multivariate normal data. For these scenarios, we derive explicit expressions for the RD risk of several estimators and compare them to the optimal source coding performance associated with full knowledge of the relation between the latent signal and the data."]]></description>
<dc:subject>to:NB information_theory estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7b324e2b2317/</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:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-040720-024710">
    <title>A Review of Empirical Likelihood | Annual Review of Statistics and Its Application</title>
    <dc:date>2021-04-15T14:57:59+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-040720-024710</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Empirical likelihood is a popular nonparametric analog of the usual parametric likelihood, inheriting many of the large-sample properties of the latter construct. This article presents a review of the empirical likelihood approach from its introduction 30 years ago, up to recent theoretical developments. Aspects of computation and connections between empirical likelihood and other likelihood-type quantities are also explored. The article ends with a discussion of some directions for future research."]]></description>
<dc:subject>empirical_likelihood likelihood hypothesis_testing estimation statistics lazar.nicole in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9fb214584349/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lazar.nicole"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/10.1111/sjos.12530?af=R">
    <title>Combining Information Across Diverse Sources: The II‐CC‐FF Paradigm - Cunen - - Scandinavian Journal of Statistics - Wiley Online Library</title>
    <dc:date>2021-04-14T14:43:00+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/10.1111/sjos.12530?af=R</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce and develop a general paradigm for combining information across diverse data sources. In broad terms, suppose &ip.phi; is a parameter of interest, built up via components ψ1,...,ψk from data sources 1,...,k. The proposed scheme has three steps. First, the Independent Inspection (II) step amounts to investigating each separate data source, translating statistical information to a confidence distribution Cj(ψj) for the relevant focus parameter ψj associated with data source j. Second, Confidence Conversion (CC) techniques are used to translate the confidence distributions to confidence log‐likelihood functions. Finally, the Focused Fusion (FF) step uses relevant and context‐driven techniques to construct a confidence distribution for the primary focus parameter &ip.phi; = &ip.phi; (ψ1,...,ψk), acting on the combined confidence log‐likelihood. In traditional setups, the II‐CC‐FF strategy amounts to versions of meta‐analysis, and turns out to be competitive against state‐of‐the‐art methods. Its potential lies in applications to harder problems, however. Illustrations are presented, related to actual applications."]]></description>
<dc:subject>to:NB statistics estimation meta-analysis confidence_sets hjort.nils_lid</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d81d256994c7/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:meta-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hjort.nils_lid"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.03167">
    <title>[2104.03167] Random graphs with node and block effects: models, goodness-of-fit tests, and applications to biological networks</title>
    <dc:date>2021-04-12T17:06:07+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.03167</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many popular models from the networks literature can be viewed through a common lens. We describe it here and call the class of models log-linear ERGMs. It includes degree-based models, stochastic blockmodels, and combinations of these. Given the interest in combined node and block effects in network formation mechanisms, we introduce a general directed relative of the degree-corrected stochastic blockmodel: an exponential family model we call p1-SBM. It is a generalization of several well-known variants of the blockmodel.
"We study the problem of testing model fit for the log-linear ERGM class.
"The model fitting approach we take, through the use of quick estimation algorithms borrowed from the contingency table literature and effective sampling methods rooted in graph theory and algebraic statistics, results in an exact test whose p-value can be approximated efficiently in networks of moderate sizes.
"We showcase the performance of the method on two data sets from biology: the connectome of \emph{C. elegans} and the interactome of \emph{Arabidopsis thaliana}. These two networks, a neuronal network and a protein-protein interaction network, have been popular examples in the network science literature, but a model-based approach to studying them has been missing thus far."]]></description>
<dc:subject>to:NB stochastic_block_models network_data_analysis estimation exponential_family_random_graphs hypothesis_testing algebraic_statistics goodness-of-fit</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3dc0c1b71041/</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:stochastic_block_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:exponential_family_random_graphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algebraic_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goodness-of-fit"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2103.01604">
    <title>[2103.01604] Theory of Low Frequency Contamination from Nonstationarity and Misspecification: Consequences for HAR Inference</title>
    <dc:date>2021-04-12T03:19:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2103.01604</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We establish theoretical and analytical results about the low frequency contamination induced by general nonstationarity for estimates such as the sample autocovariance and the periodogram, and deduce consequences for heteroskedasticity and autocorrelation robust (HAR) inference. We show that for short memory nonstationarity data these estimates exhibit features akin to long memory. We present explicit expressions for the asymptotic bias of these estimates. This bias increases with the degree of heterogeneity. in the data and is responsible for generating low frequency contamination or simply making the time series exhibiting long memory features. The sample autocovariances display hyperbolic rather than exponential decay while the periodogram becomes unbounded near the origin. We distinguish cases where this contamination only occurs as a small-sample problem and cases where the contamination continues to hold asymptotically. We show theoretically that nonparametric smoothing over time is robust to low frequency this http URL that the sample local autocovariance and the local periodogram are unlikely to exhibit long memory features. Simulations confirm that our theory provides useful approximations. Since the autocovariances and the periodogram are key elements for HAR inference, our results provide new insights on the debate between consistent versus inconsistent small versus long/fixed-b bandwidths for long-run variance (LRV) estimation-based inference."]]></description>
<dc:subject>to:NB statistics estimation time_series long-range_dependence non-stationarity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:736ebd960279/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:long-range_dependence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-stationarity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.04416">
    <title>[2104.04416] Concentration study of M-estimators using the influence function</title>
    <dc:date>2021-04-12T02:18:49+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.04416</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We present a new finite-sample analysis of M-estimators of locations in ℝd using the tool of the influence function. In particular, we show that the deviations of an M-estimator can be controlled thanks to its influence function (or its score function) and then, we use concentration inequality on M-estimators to investigate the robust estimation of the mean in high dimension in a corrupted setting (adversarial corruption setting) for bounded and unbounded score functions. For a sample of size n and covariance matrix Σ, we attain the minimax speed Tr(Σ)/n‾‾‾‾‾‾‾√+‖Σ‖oplog(1/δ)/n‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾√ with probability larger than 1−δ in a heavy-tailed setting. One of the major advantages of our approach compared to others recently proposed is that our estimator is tractable and fast to compute even in very high dimension with a complexity of O(ndlog(Tr(Σ))) where n is the sample size and Σ is the covariance matrix of the inliers. In practice, the code that we make available for this article proves to be very fast."]]></description>
<dc:subject>to:NB estimation heavy_tails statistics learning_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d69a7cca59f9/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heavy_tails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.15678">
    <title>[2012.15678] On Gaussian Approximation for M-Estimator</title>
    <dc:date>2021-01-03T20:05:42+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.15678</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This study develops a non-asymptotic Gaussian approximation theory for distributions of M-estimators, which are defined as maximizers of empirical criterion functions. In existing mathematical statistics literature, numerous studies have focused on approximating the distributions of the M-estimators for statistical inference. In contrast to the existing approaches, which mainly focus on limiting behaviors, this study employs a non-asymptotic approach, establishes abstract Gaussian approximation results for maximizers of empirical criteria, and proposes a Gaussian multiplier bootstrap approximation method. Our developments can be considered as an extension of the seminal works (Chernozhukov, Chetverikov and Kato (2013, 2014, 2015)) on the approximation theory for distributions of suprema of empirical processes toward their maximizers. Through this work, we shed new lights on the statistical theory of M-estimators. Our theory covers not only regular estimators, such as the least absolute deviations, but also some non-regular cases where it is difficult to derive or to approximate numerically the limiting distributions such as non-Donsker classes and cube root estimators."]]></description>
<dc:subject>to:NB central_limit_theorem estimation statistics empirical_processes re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:580f8c5bf237/</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:central_limit_theorem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://doi.org/10.1093/imaiai/iaz025">
    <title>Concentration inequalities for the empirical distribution of discrete distributions: beyond the method of types | Information and Inference: A Journal of the IMA | Oxford Academic</title>
    <dc:date>2020-12-24T02:08:19+00:00</dc:date>
    <link>https://doi.org/10.1093/imaiai/iaz025</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study concentration inequalities for the Kullback–Leibler (KL) divergence between the empirical distribution and the true distribution. Applying a recursion technique, we improve over the method of types bound uniformly in all regimes of sample size nn and alphabet size kk⁠, and the improvement becomes more significant when kk is large. We discuss the applications of our results in obtaining tighter concentration inequalities for L1L1 deviations of the empirical distribution from the true distribution, and the difference between concentration around the expectation or zero. We also obtain asymptotically tight bounds on the variance of the KL divergence between the empirical and true distribution, and demonstrate their quantitatively different behaviours between small and large sample sizes compared to the alphabet size."]]></description>
<dc:subject>to:NB concentration_of_measure information_theory estimation large_deviations</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:de268154829f/</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:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/imaiai/article-abstract/9/4/813/5627733">
    <title>Concentration inequalities for the empirical distribution of discrete distributions: beyond the method of types | Information and Inference: A Journal of the IMA | Oxford Academic</title>
    <dc:date>2020-12-24T02:08:06+00:00</dc:date>
    <link>https://academic.oup.com/imaiai/article-abstract/9/4/813/5627733</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study concentration inequalities for the Kullback–Leibler (KL) divergence between the empirical distribution and the true distribution. Applying a recursion technique, we improve over the method of types bound uniformly in all regimes of sample size nn and alphabet size kk⁠, and the improvement becomes more significant when kk is large. We discuss the applications of our results in obtaining tighter concentration inequalities for L1L1 deviations of the empirical distribution from the true distribution, and the difference between concentration around the expectation or zero. We also obtain asymptotically tight bounds on the variance of the KL divergence between the empirical and true distribution, and demonstrate their quantitatively different behaviours between small and large sample sizes compared to the alphabet size."]]></description>
<dc:subject>to:NB concentration_of_measure information_theory estimation large_deviations</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:82e00f75769c/</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:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.09874">
    <title>[2012.09874] Simple and statistically sound strategies for analysing physical theories</title>
    <dc:date>2020-12-21T04:37:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.09874</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Physical theories that depend on many parameters or are tested against data from many different experiments pose unique challenges to parameter estimation. Many models in particle physics, astrophysics and cosmology fall into one or both of these categories. These issues are often sidestepped with very simplistic and statistically unsound ad hoc methods, involving naive intersection of parameter intervals estimated by multiple experiments, and random or grid sampling of model parameters. Whilst these methods are easy to apply, they exhibit pathologies even in low-dimensional parameter spaces, and quickly become problematic to use and interpret in higher dimensions. In this article we give clear guidance for going beyond these rudimentary procedures, suggesting some simple methods for performing statistically sound inference, and recommendations of readily-available software tools and standards that can assist in doing so. Our aim is to provide physicists with recommendations for reaching correct scientific conclusions, with only a modest increase in analysis burden."]]></description>
<dc:subject>to:NB statistics estimation meta-analysis physics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ae0ca7299e90/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:meta-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:physics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-031219-041228">
    <title>Distance-Based Statistical Inference | Annual Review of Statistics and Its Application</title>
    <dc:date>2020-12-18T18:49:05+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-statistics-031219-041228</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Statistical distances, divergences, and similar quantities have an extensive history and play an important role in the statistical and related scientific literature. This role shows up in estimation, where we often use estimators based on minimizing a distance. Distances also play a prominent role in hypothesis testing and in model selection. We review the statistical properties of distances that are often used in scientific work, present their properties, and show how they compare to each other. We discuss an approximation framework for model-based inference using statistical distances. Emphasis is placed on identifying in what sense and which statistical distances can be interpreted as loss functions and used for model assessment. We review a special class of distances, the class of quadratic distances, connect it with the classical goodness-of-fit paradigm, and demonstrate its use in the problem of assessing model fit. These methods can be used in analyzing very large samples."]]></description>
<dc:subject>to:NB statistics estimation re:codename:catherine_wheel</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5bb05e1ad2e5/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:codename:catherine_wheel"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.09422">
    <title>[2012.09422] The Variational Method of Moments</title>
    <dc:date>2020-12-18T10:34:37+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.09422</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The conditional moment problem is a powerful formulation for describing structural causal parameters in terms of observables, a prominent example being instrumental variable regression. A standard approach is to reduce the problem to a finite set of marginal moment conditions and apply the optimally weighted generalized method of moments (OWGMM), but this requires we know a finite set of identifying moments, can still be inefficient even if identifying, or can be unwieldy and impractical if we use a growing sieve of moments. Motivated by a variational minimax reformulation of OWGMM, we define a very general class of estimators for the conditional moment problem, which we term the variational method of moments (VMM) and which naturally enables controlling infinitely-many moments. We provide a detailed theoretical analysis of multiple VMM estimators, including based on kernel methods and neural networks, and provide appropriate conditions under which these estimators are consistent, asymptotically normal, and semiparametrically efficient in the full conditional moment model. This is in contrast to other recently proposed methods for solving conditional moment problems based on adversarial machine learning, which do not incorporate optimal weighting, do not establish asymptotic normality, and are not semiparametrically efficient."]]></description>
<dc:subject>to:NB estimation re:codename:catherine_wheel</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:361066f8a023/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:codename:catherine_wheel"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.07167">
    <title>[2012.07167] Pseudo-likelihood-based $M$-estimation of random graphs with dependent edges and parameter vectors of increasing dimension</title>
    <dc:date>2020-12-15T13:02:25+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.07167</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["An important question in statistical network analysis is how to construct and estimate models of dependent network data without sacrificing computational scalability and statistical guarantees. We demonstrate that scalable estimation of random graph models with dependent edges is possible, by establishing the first consistency results and convergence rates for pseudo-likelihood-based M-estimators for parameter vectors of increasing dimension based on a single observation of dependent random variables. The main results cover models of dependent random variables with countable sample spaces, and may be of independent interest. To showcase consistency results and convergence rates, we introduce a novel class of generalized β-models with dependent edges and parameter vectors of increasing dimension.We establish consistency results and convergence rates for pseudo-likelihood-based M-estimators of generalized β-models with dependent edges, in dense- and sparse-graph settings."]]></description>
<dc:subject>to:NB estimation likelihood network_data_analysis statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fd6e1a018f40/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:likelihood"/>
	<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>
<item rdf:about="https://arxiv.org/abs/2011.14999">
    <title>[2011.14999] An Automatic Finite-Sample Robustness Metric: Can Dropping a Little Data Change Conclusions?</title>
    <dc:date>2020-12-03T16:13:23+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.14999</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a method to assess the sensitivity of econometric analyses to the removal of a small fraction of the sample. Analyzing all possible data subsets of a certain size is computationally prohibitive, so we provide a finite-sample metric to approximately compute the number (or fraction) of observations that has the greatest influence on a given result when dropped. We call our resulting metric the Approximate Maximum Influence Perturbation. Our approximation is automatically computable and works for common estimators (including OLS, IV, GMM, MLE, and variational Bayes). We provide explicit finite-sample error bounds on our approximation for linear and instrumental variables regressions. At minimal computational cost, our metric provides an exact finite-sample lower bound on sensitivity for any estimator, so any non-robustness our metric finds is conclusive. We demonstrate that the Approximate Maximum Influence Perturbation is driven by a low signal-to-noise ratio in the inference problem, is not reflected in standard errors, does not disappear asymptotically, and is not a product of misspecification. Several empirical applications show that even 2-parameter linear regression analyses of randomized trials can be highly sensitive. While we find some applications are robust, in others the sign of a treatment effect can be changed by dropping less than 1% of the sample even when standard errors are small."]]></description>
<dc:subject>to:NB statistics robustness estimation to_read linear_regression to_teach:linear_models to_teach:undergrad-ADA</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bc72bd101639/</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:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:linear_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.06838">
    <title>[1810.06838] Finite-sample analysis of M-estimators using self-concordance</title>
    <dc:date>2020-12-02T15:58:13+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.06838</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The classical asymptotic theory for parametric M-estimators guarantees that, in the limit of infinite sample size, the excess risk has a chi-square type distribution, even in the misspecified case. We demonstrate how self-concordance of the loss allows to characterize the critical sample size sufficient to guarantee a chi-square type in-probability bound for the excess risk. Specifically, we consider two classes of losses: (i) self-concordant losses in the classical sense of Nesterov and Nemirovski, i.e., whose third derivative is uniformly bounded with the 3/2 power of the second derivative; (ii) pseudo self-concordant losses, for which the power is removed. These classes contain losses corresponding to several generalized linear models, including the logistic loss and pseudo-Huber losses. Our basic result under minimal assumptions bounds the critical sample size by O(d⋅deff), where d the parameter dimension and deff the effective dimension that accounts for model misspecification. In contrast to the existing results, we only impose local assumptions that concern the population risk minimizer θ∗. Namely, we assume that the calibrated design, i.e., design scaled by the square root of the second derivative of the loss, is subgaussian at θ∗. Besides, for type-ii losses we require boundedness of a certain measure of curvature of the population risk at θ∗.Our improved result bounds the critical sample size from above as O(max{deff,dlogd}) under slightly stronger assumptions. Namely, the local assumptions must hold in the neighborhood of θ∗ given by the Dikin ellipsoid of the population risk. Interestingly, we find that, for logistic regression with Gaussian design, there is no actual restriction of conditions: the subgaussian parameter and curvature measure remain near-constant over the Dikin ellipsoid. Finally, we extend some of these results to ℓ1-penalized estimators in high dimensions."]]></description>
<dc:subject>to:NB estimation statistics re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e17d20d51133/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.14762">
    <title>[2011.14762] Testing for Uniqueness of Estimators</title>
    <dc:date>2020-12-02T01:49:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.14762</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Uniqueness of the population value of an estimated descriptor is a standard assumption in asymptotic theory. However, m-estimation problems often allow for local minima of the sample estimating function, which may stem from multiple global minima of the underlying population estimating function. In the present article, we provide tools to systematically determine for a given sample whether the underlying population estimating function may have multiple global minima. To achieve this goal, we develop asymptotic theory for non-unique minimizers and introduce asymptotic tests using the bootstrap. We discuss three applications of our tests to data, each of which presents a typical scenario in which non-uniqueness of descriptors may occur. These model scenarios are the mean on a non-euclidean space, non-linear regression and Gaussian mixture clustering."]]></description>
<dc:subject>to:NB statistics optimization estimation re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b0af4daf0a0e/</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:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.10240">
    <title>[2011.10240] Reconstruct Kaplan--Meier Estimator as M-estimator and Its Confidence Band</title>
    <dc:date>2020-11-23T17:44:03+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.10240</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The Kaplan--Meier (KM) estimator, which provides a nonparametric estimate of a survival function for time-to-event data, has wide application in clinical studies, engineering, economics and other fields. The theoretical properties of the KM estimator including its consistency and asymptotic distribution have been extensively studied. We reconstruct the KM estimator as an M-estimator by maximizing a quadratic M-function based on concordance, which can be computed using the expectation--maximization (EM) algorithm. It is shown that the convergent point of the EM algorithm coincides with the traditional KM estimator, offering a new interpretation of the KM estimator as an M-estimator. Theoretical properties including the large-sample variance and limiting distribution of the KM estimator are established using M-estimation theory. Simulations and application on two real datasets demonstrate that the proposed M-estimator is exactly equivalent to the KM estimator, while the confidence interval and band can be derived as well."]]></description>
<dc:subject>to:NB survival_analysis estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bc9164ed9839/</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:survival_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.tandfonline.com/doi/full/10.1080/01621459.2020.1773832">
    <title>Optimal Distributed Subsampling for Maximum Quasi-Likelihood Estimators With Massive Data: Journal of the American Statistical Association: Vol 0, No 0</title>
    <dc:date>2020-11-20T15:34:26+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/full/10.1080/01621459.2020.1773832</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Nonuniform subsampling methods are effective to reduce computational burden and maintain estimation efficiency for massive data. Existing methods mostly focus on subsampling with replacement due to its high computational efficiency. If the data volume is so large that nonuniform subsampling probabilities cannot be calculated all at once, then subsampling with replacement is infeasible to implement. This article solves this problem using Poisson subsampling. We first derive optimal Poisson subsampling probabilities in the context of quasi-likelihood estimation under the A- and L-optimality criteria. For a practically implementable algorithm with approximated optimal subsampling probabilities, we establish the consistency and asymptotic normality of the resultant estimators. To deal with the situation that the full data are stored in different blocks or at multiple locations, we develop a distributed subsampling framework, in which statistics are computed simultaneously on smaller partitions of the full data. Asymptotic properties of the resultant aggregated estimator are investigated. We illustrate and evaluate the proposed strategies through numerical experiments on simulated and real datasets."]]></description>
<dc:subject>to:NB computational_statistics estimation statistics random_projections</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9d6a370bded6/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_projections"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1581930134">
    <title>Chen , Lee , Tong , Zhang : Statistical inference for model parameters in stochastic gradient descent</title>
    <dc:date>2020-11-19T04:42:45+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1581930134</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The stochastic gradient descent (SGD) algorithm has been widely used in statistical estimation for large-scale data due to its computational and memory efficiency. While most existing works focus on the convergence of the objective function or the error of the obtained solution, we investigate the problem of statistical inference of true model parameters based on SGD when the population loss function is strongly convex and satisfies certain smoothness conditions.
"Our main contributions are twofold. First, in the fixed dimension setup, we propose two consistent estimators of the asymptotic covariance of the average iterate from SGD: (1) a plug-in estimator, and (2) a batch-means estimator, which is computationally more efficient and only uses the iterates from SGD. Both proposed estimators allow us to construct asymptotically exact confidence intervals and hypothesis tests.
"Second, for high-dimensional linear regression, using a variant of the SGD algorithm, we construct a debiased estimator of each regression coefficient that is asymptotically normal. This gives a one-pass algorithm for computing both the sparse regression coefficients and confidence intervals, which is computationally attractive and applicable to online data."]]></description>
<dc:subject>stochastic_gradient_descent optimization statistics estimation in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6b5200a14eac/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_gradient_descent"/>
	<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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1594972829">
    <title>Biau , Cadre , Sangnier , Tanielian : Some theoretical properties of GANS</title>
    <dc:date>2020-11-18T21:50:42+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1594972829</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the-art samples, especially in the domain of image creation. The fundamental principle of GANs is to approximate the unknown distribution of a given data set by optimizing an objective function through an adversarial game between a family of generators and a family of discriminators. In this paper, we offer a better theoretical understanding of GANs by analyzing some of their mathematical and statistical properties. We study the deep connection between the adversarial principle underlying GANs and the Jensen–Shannon divergence, together with some optimality characteristics of the problem. An analysis of the role of the discriminator family via approximation arguments is also provided. In addition, taking a statistical point of view, we study the large sample properties of the estimated distribution and prove in particular a central limit theorem. Some of our results are illustrated with simulated examples."]]></description>
<dc:subject>to:NB statistics estimation your_favorite_deep_neural_network_sucks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c35ca832e623/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:your_favorite_deep_neural_network_sucks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.08511">
    <title>[1710.08511] An Expectation Maximization Framework for Yule-Simon Preferential Attachment Models</title>
    <dc:date>2020-11-18T17:18:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.08511</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper we develop an Expectation Maximization(EM) algorithm to estimate the parameter of a Yule-Simon distribution. The Yule-Simon distribution exhibits the "rich get richer" effect whereby an 80-20 type of rule tends to dominate. These distributions are ubiquitous in industrial settings. The EM algorithm presented provides both frequentist and Bayesian estimates of the λ parameter. By placing the estimation method within the EM framework we are able to derive Standard errors of the resulting estimate. Additionally, we prove convergence of the Yule-Simon EM algorithm and study the rate of convergence. An explicit, closed form solution for the rate of convergence of the algorithm is given. Applications including graph node degree distribution estimation are listed."]]></description>
<dc:subject>to:NB estimation em_algorithm heavy_tails statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b20d7aa0a1ee/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:em_algorithm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heavy_tails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2010.13687">
    <title>[2010.13687] A General Approach for Simulation-based Bias Correction in High Dimensional Settings</title>
    <dc:date>2020-11-18T17:16:05+00:00</dc:date>
    <link>https://arxiv.org/abs/2010.13687</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["An important challenge in statistical analysis lies in controlling the bias of estimators due to the ever-increasing data size and model complexity. Approximate numerical methods and data features like censoring and misclassification often result in analytical and/or computational challenges when implementing standard estimators. As a consequence, consistent estimators may be difficult to obtain, especially in complex and/or high dimensional settings. In this paper, we study the properties of a general simulation-based estimation framework that allows to construct bias corrected consistent estimators. We show that the considered approach leads, under more general conditions, to stronger bias correction properties compared to alternative methods. Besides its bias correction advantages, the considered method can be used as a simple strategy to construct consistent estimators in settings where alternative methods may be challenging to apply. Moreover, the considered framework can be easily implemented and is computationally efficient. These theoretical results are highlighted with simulation studies of various commonly used models, including the negative binomial regression (with and without censoring) and the logistic regression (with and without misclassification errors). Additional numerical illustrations are provided in the supplementary materials."]]></description>
<dc:subject>to:NB simulation estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e3587dcd66c8/</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:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0235318">
    <title>Systematic review of the use of “magnitude-based inference” in sports science and medicine</title>
    <dc:date>2020-07-13T16:43:55+00:00</dc:date>
    <link>https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0235318</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Magnitude-based inference (MBI) is a controversial statistical method that has been used in hundreds of papers in sports science despite criticism from statisticians. To better understand how this method has been applied in practice, we systematically reviewed 232 papers that used MBI. We extracted data on study design, sample size, and choice of MBI settings and parameters. Median sample size was 10 per group (interquartile range, IQR: 8–15) for multi-group studies and 14 (IQR: 10–24) for single-group studies; few studies reported a priori sample size calculations (15%). Authors predominantly applied MBI’s default settings and chose “mechanistic/non-clinical” rather than “clinical” MBI even when testing clinical interventions (only 16 studies out of 232 used clinical MBI). Using these data, we can estimate the Type I error rates for the typical MBI study. Authors frequently made dichotomous claims about effects based on the MBI criterion of a “likely” effect and sometimes based on the MBI criterion of a “possible” effect. When the sample size is n = 8 to 15 per group, these inferences have Type I error rates of 12%-22% and 22%-45%, respectively. High Type I error rates were compounded by multiple testing: Authors reported results from a median of 30 tests related to outcomes; and few studies specified a primary outcome (14%). We conclude that MBI has promoted small studies, promulgated a “black box” approach to statistics, and led to numerous papers where the conclusions are not supported by the data. Amidst debates over the role of p-values and significance testing in science, MBI also provides an important natural experiment: we find no evidence that moving researchers away from p-values or null hypothesis significance testing makes them less prone to dichotomization or over-interpretation of findings."

--- I hadn't heard of this particular little cult, but sheesh.  (The last sentence of the abstract it the key.)]]></description>
<dc:subject>to:NB have_read bad_data_analysis statistics why_oh_why_cant_we_have_a_better_academic_publishing_system hypothesis_testing estimation trapped_in_plutos_republic</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:47bc87dbe9e7/</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:bad_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_academic_publishing_system"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:trapped_in_plutos_republic"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://papers.nips.cc/paper/3693-asymptotically-optimal-regularization-in-smooth-parametric-models">
    <title>Asymptotically Optimal Regularization in Smooth Parametric Models</title>
    <dc:date>2020-05-16T18:08:57+00:00</dc:date>
    <link>http://papers.nips.cc/paper/3693-asymptotically-optimal-regularization-in-smooth-parametric-models</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Many types of regularization schemes have been employed in statistical learning, each one motivated by some assumption about the problem domain. In this paper, we present a unified asymptotic analysis of smooth regularizers, which allows us to see how the validity of these assumptions impacts the success of a particular regularizer. In addition, our analysis motivates an algorithm for optimizing regularization parameters, which in turn can be analyzed within our framework. We apply our analysis to several examples, including hybrid generative-discriminative learning and multi-task learning."]]></description>
<dc:subject>to:NB statistics estimation learning_theory to_read re:HEAS to_teach:childs_garden_of_statistical_learning_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:453fbf1714bd/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:childs_garden_of_statistical_learning_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=917901">
    <title>Empirical Likelihood Methods in Econometrics: Theory and Practice by Yuichi Kitamura :: SSRN</title>
    <dc:date>2020-05-16T18:01:29+00:00</dc:date>
    <link>https://papers.ssrn.com/sol3/papers.cfm?abstract_id=917901</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recent developments in empirical likelihood (EL) methods are reviewed. First, to put the method in perspective, two interpretations of empirical likelihood are presented, one as a nonparametric maximum likelihood estimation method (NPMLE) and the other as a generalized minimum contrast estimator (GMC). The latter interpretation provides a clear connection between EL, GMM, GEL and other related estimators. Second, EL is shown to have various advantages over other methods. The theory of large deviations demonstrates that EL emerges naturally in achieving asymptotic optimality both for estimation and testing. Interestingly, higher order asymptotic analysis also suggests that EL is generally a preferred method. Third, extensions of EL are discussed in various settings, including estimation of conditional moment restriction models, nonparametric specification testing and time series models. Finally, practical issues in applying EL to real data, such as computational algorithms for EL, are discussed. Numerical examples to illustrate the efficacy of the method are presented."]]></description>
<dc:subject>to:NB statistics estimation hypothesis_testing likelihood empirical_likelihood large_deviations re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d0c1ac40de03/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1911.01483">
    <title>[1911.01483] Statistical Inference for Model Parameters in Stochastic Gradient Descent via Batch Means</title>
    <dc:date>2019-11-09T23:33:31+00:00</dc:date>
    <link>https://arxiv.org/abs/1911.01483</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Statistical inference of true model parameters based on stochastic gradient descent (SGD) has started receiving attention in recent years. In this paper, we study a simple algorithm to construct asymptotically valid confidence regions for model parameters using the batch means method. The main idea is to cancel out the covariance matrix which is hard/costly to estimate. In the process of developing the algorithm, we establish process-level function central limit theorem for Polyak-Ruppert averaging based SGD estimators. We also extend the batch means method to accommodate more general batch size specifications."]]></description>
<dc:subject>to:NB optimization estimation statistics re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a44533e10261/</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:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.11540">
    <title>[1910.11540] Descriptive Dimensionality and Its Characterization of MDL-based Learning and Change Detection</title>
    <dc:date>2019-10-29T14:24:18+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.11540</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper introduces a new notion of dimensionality of probabilistic models from an information-theoretic view point. We call it the "descriptive dimension"(Ddim). We show that Ddim coincides with the number of independent parameters for the parametric class, and can further be extended to real-valued dimensionality when a number of models are mixed. The paper then derives the rate of convergence of the MDL (Minimum Description Length) learning algorithm which outputs a normalized maximum likelihood (NML) distribution with model of the shortest NML codelength. The paper proves that the rate is governed by Ddim. The paper also derives error probabilities of the MDL-based test for multiple model change detection. It proves that they are also governed by Ddim. Through the analysis, we demonstrate that Ddim is an intrinsic quantity which characterizes the performance of the MDL-based learning and change detection."

]]></description>
<dc:subject>to:NB minimum_description_length statistics estimation prediction change-point_problem</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5c50517054ec/</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:minimum_description_length"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:change-point_problem"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1602.02201">
    <title>[1602.02201] The Rate-Distortion Risk in Estimation from Compressed Data</title>
    <dc:date>2019-10-25T14:46:27+00:00</dc:date>
    <link>https://arxiv.org/abs/1602.02201</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of estimating a latent signal from a lossy compressed version of the data. We assume that the data is generated by an underlying signal and compressed using a lossy compression scheme that is agnostic to this signal. In reconstruction, the underlying signal is estimated so as to minimize a prescribed loss measure. For the above setting and an arbitrary distortion measure between the data and its compressed version, we define the rate-distortion (RD) risk of an estimator as its risk with respect to the distribution achieving Shannon's RD function with respect to this distortion. We derive conditions under which the RD risk describes the risk in estimating from the compressed data. The main theoretical tools to obtain these conditions are transportation-cost inequalities in conjunction with properties of source codes achieving Shannon's RD function. We show that these conditions hold in various settings, including settings where the alphabet of the underlying signal is finite or when the RD achieving distribution is multivariate normal. We evaluate the RD risk in special cases under these settings. This risk provides an achievable loss in compress-and-estimate settings, i.e., when the data is first compressed, communicated or stored using a procedure that is agnostic to the underlying signal, which is later estimated from the compressed version of the data. Our results imply the following general procedure for designing estimators from datasets undergoing lossy compression without specifying the actual compression technique; train the estimator based on a perturbation of the data according to the RD achieving distribution. Under general conditions, this estimator achieves the RD risk when applied to the lossy compressed version of the data."]]></description>
<dc:subject>to:NB estimation information_theory compression statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:949016946f05/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:compression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.mitpressjournals.org/doi/abs/10.1162/rest_a_00795">
    <title>How to Use Economic Theory to Improve Estimators: Shrinking Toward Theoretical Restrictions | The Review of Economics and Statistics | MIT Press Journals</title>
    <dc:date>2019-10-24T15:01:31+00:00</dc:date>
    <link>https://www.mitpressjournals.org/doi/abs/10.1162/rest_a_00795</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose to use economic theories to construct shrinkage estimators that perform well when the theories' empirical implications are approximately correct but perform no worse than unrestricted estimators when the theories' implications do not hold. We implement this construction in various settings, including labor demand and wage inequality, and estimation of consumer demand. We provide asymptotic and finite sample characterizations of the behavior of the proposed estimators. Our approach is an alternative to the use of theory as something to be tested or to be imposed on estimates. Our approach complements uses of theory for identification and extrapolation."]]></description>
<dc:subject>to:NB economics econometrics statistics estimation shrinkage</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:384ae1da5083/</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:econometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:shrinkage"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.08390">
    <title>[1910.08390] Finite sample deviation and variance bounds for first order autoregressive processes</title>
    <dc:date>2019-10-22T13:52:31+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.08390</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we study finite-sample properties of the least squares estimator in first order autoregressive processes. By leveraging a result from decoupling theory, we derive upper bounds on the probability that the estimate deviates by at least a positive ε from its true value. Our results consider both stable and unstable processes. Afterwards, we obtain problem-dependent non-asymptotic bounds on the variance of this estimator, valid for sample sizes greater than or equal to seven. Via simulations we analyze the conservatism of our bounds, and show that they reliably capture the true behavior of the quantities of interest."]]></description>
<dc:subject>to:NB statistics deviation_inequalities time_series estimation to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0fbea03e7f65/</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:deviation_inequalities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.09457">
    <title>[1910.09457] Aleatoric and Epistemic Uncertainty in Machine Learning: A Tutorial Introduction</title>
    <dc:date>2019-10-22T13:46:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.09457</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often refereed to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of hitherto attempts at handling uncertainty in general and formalizing this distinction in particular."]]></description>
<dc:subject>prediction estimation uncertainty_for_neural_networks statistics in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c45bebcfc6ae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:uncertainty_for_neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.07185">
    <title>[1910.07185] Identifying relationships between cognitive processes across tasks, contexts, and time</title>
    <dc:date>2019-10-17T14:09:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.07185</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["It is commonly assumed that a specific testing occasion (task, design, procedure, etc.) provides insight into psychological phenomena that generalise to other, related testing occasions. However, this assumption is rarely tested in data. When it is tested, the two existing methods of comparison have one of the following two shortcomings: they either correlate summary statistics like mean response time or accuracy, which does not provide insight into relationships between latent psychological processes, or they first assume independence in cognitive processes across tasks and then, in a second step, test whether there is in fact a relationship. Our article develops a statistically principled method to directly estimate the correlation between latent components of cognitive processing across tasks, contexts, and time. Our method simultaneously estimates individual participant parameters of a cognitive model at each testing occasion, group-level parameters representing across-participant parameter averages and variances, and across-task covariances, i.e., correlations. The approach provides a natural way to "borrow" data across testing occasions, which increases the precision of parameter estimates across all testing occasions provided there is a non-zero relationship between some of the latent processes of the model. We illustrate the method in two applications in decision making contexts. The first assesses the effect of the neural scanning environment on model parameters, and the second assesses relationships between latent processes underlying performance of three different tasks. We conclude by highlighting the potential of the parameter-correlation method to provide an "assumption-light" tool for estimating the relatedness of cognitive processes across tasks, contexts, and time."]]></description>
<dc:subject>to:NB cognitive_science psychometrics statistics estimation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a6e899fb508c/</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:psychometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.09965">
    <title>[1703.09965] Estimable group effects for strongly correlated variables in linear models</title>
    <dc:date>2019-10-17T14:08:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.09965</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["It is well known that parameters for strongly correlated predictor variables in a linear model cannot be accurately estimated. We look for linear combinations of these parameters that can be. Under a uniform model, we find such linear combinations in a neighborhood of a simple variability weighted average of these parameters. Surprisingly, this variability weighted average is more accurately estimated when the variables are more strongly correlated, and it is the only linear combination with this property. It can be easily computed for strongly correlated predictor variables in all linear models and has applications in inference and estimation concerning parameters of such variables."]]></description>
<dc:subject>to:NB linear_regression estimation statistics to_teach:linear_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cb8ae8464bab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:linear_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1904.03313">
    <title>[1904.03313] On the computational tractability of statistical estimation on amenable graphs</title>
    <dc:date>2019-09-26T18:35:37+00:00</dc:date>
    <link>https://arxiv.org/abs/1904.03313</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of estimating a vector of discrete variables (θ1,⋯,θn), based on noisy observations Yuv of the pairs (θu,θv) on the edges of a graph G=([n],E). This setting comprises a broad family of statistical estimation problems, including group synchronization on graphs, community detection, and low-rank matrix estimation.
"A large body of theoretical work has established sharp thresholds for weak and exact recovery, and sharp characterizations of the optimal reconstruction accuracy in such models, focusing however on the special case of Erdös--Rényi-type random graphs. The single most important finding of this line of work is the ubiquity of an information-computation gap. Namely, for many models of interest, a large gap is found between the optimal accuracy achievable by any statistical method, and the optimal accuracy achieved by known polynomial-time algorithms. Moreover, this gap is generally believed to be robust to small amounts of additional side information revealed about the θi's.
"How does the structure of the graph G affect this picture? Is the information-computation gap a general phenomenon or does it only apply to specific families of graphs?
"We prove that the picture is dramatically different for graph sequences converging to amenable graphs (including, for instance, d-dimensional grids). We consider a model in which an arbitrarily small fraction of the vertex labels is revealed, and show that a linear-time local algorithm can achieve reconstruction accuracy that is arbitrarily close to the information-theoretic optimum. We contrast this to the case of random graphs. Indeed, focusing on group synchronization on random regular graphs, we prove that the information-computation gap still persists even when a small amount of side information is revealed."]]></description>
<dc:subject>to:NB network_data_analysis estimation statistics theoretical_computer_science minimax graph_limits</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e7979f915817/</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:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:theoretical_computer_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:minimax"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_limits"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.10828">
    <title>[1909.10828] Double-estimation-friendly inference for high-dimensional misspecified models</title>
    <dc:date>2019-09-26T18:02:05+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.10828</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["All models may be wrong---but that is not necessarily a problem for inference. Consider the standard t-test for the significance of a variable X for predicting response Y whilst controlling for p other covariates Z in a random design linear model. This yields correct asymptotic type~I error control for the null hypothesis that X is conditionally independent of Y given Z under an \emph{arbitrary} regression model of Y on (X,Z), provided that a linear regression model for X on Z holds. An analogous robustness to misspecification, which we term the "double-estimation-friendly" (DEF) property, also holds for Wald tests in generalised linear models, with some small modifications.
"In this expository paper we explore this phenomenon, and propose methodology for high-dimensional regression settings that respects the DEF property. We advocate specifying (sparse) generalised linear regression models for both Y and the covariate of interest X; our framework gives valid inference for the conditional independence null if either of these hold. In the special case where both specifications are linear, our proposal amounts to a small modification of the popular debiased Lasso test. We also investigate constructing confidence intervals for the regression coefficient of X via inverting our tests; these have coverage guarantees even in partially linear models where the contribution of Z to Y can be arbitrary. Numerical experiments demonstrate the effectiveness of the methodology."]]></description>
<dc:subject>to:NB misspecification estimation high-dimensional_statistics buhlmann.peter statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ae504d441d08/</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:misspecification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:high-dimensional_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:buhlmann.peter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.09336">
    <title>[1909.09336] Applications of Generalized Maximum Likelihood Estimators to stratified sampling and post-stratification with many unobserved strata</title>
    <dc:date>2019-09-23T14:18:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.09336</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Consider the problem of estimating a weighted average of the means of n strata, based on a random sample with realized Ki observations from stratum i,i=1,...,n.
"This task is non-trivial in cases where for a significant portion of the strata the corresponding Ki=0. Such a situation may happen in post-stratification, when it is desired to have very fine stratification. A fine stratification could be desired in order that assumptions, or, approximations, like Missing At Random conditional on strata, will be appealing. Fine stratification could also be desired in observational studies, when it is desired to estimate average treatment effect, by averaging the effects in small and homogenous strata.
"Our approach is based on applying Generalized Maximum Likelihood Estimators (GMLE), and ideas that are related to Non-Parametric Empirical Bayes, in order to estimate the means of strata i with corresponding Ki=0. There are no assumptions about a relation between the means of the unobserved strata (i.e., with Ki=0) and those of the observed strata.
"The performance of our approach is demonstrated both in simulations and on a real data set. Some consistency and asymptotic results are also provided."]]></description>
<dc:subject>to:NB missing_data statistics estimation surveys</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ce530ec2b34b/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:surveys"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.05582">
    <title>[1909.05582] A taxonomy of estimator consistency on discrete estimation problems</title>
    <dc:date>2019-09-13T13:03:59+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.05582</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We describe a four-level hierarchy mapping both all discrete estimation problems and all estimators on these problems, such that the hierarchy describes each estimator's consistency guarantees on each problem class. We show that no estimator is consistent for all estimation problems, but that some estimators, such as Maximum A Posteriori, are consistent for the widest possible class of discrete estimation problems. For Maximum Likelihood and Approximate Maximum Likelihood estimators we show that they do not provide consistency on as wide a class, but define a sub-class of problems characterised by their consistency. Lastly, we show that some popular estimators, specifically Strict Minimum Message Length, do not provide consistency guarantees even within the sub-class."]]></description>
<dc:subject>to:NB statistics estimation model_selection</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:34bd01754668/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.08109">
    <title>[1702.08109] Variational Analysis of Constrained M-Estimators</title>
    <dc:date>2019-09-12T16:24:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.08109</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a unified framework for establishing existence of nonparametric M-estimators, computing the corresponding estimates, and proving their strong consistency when the class of functions is exceptionally rich. In particular, the framework addresses situations where the class of functions is complex involving information and assumptions about shape, pointwise bounds, location of modes, height at modes, location of level-sets, values of moments, size of subgradients, continuity, distance to a "prior" function, multivariate total positivity, and any combination of the above. The class might be engineered to perform well in a specific setting even in the presence of little data. The framework views the class of functions as a subset of a particular metric space of upper semicontinuous functions under the Attouch-Wets distance. In addition to allowing a systematic treatment of numerous M-estimators, the framework yields consistency of plug-in estimators of modes of densities, maximizers of regression functions, level-sets of classifiers, and related quantities, and also enables computation by means of approximating parametric classes. We establish consistency through a one-sided law of large numbers, here extended to sieves, that relaxes assumptions of uniform laws, while ensuring global approximations even under model misspecification."]]></description>
<dc:subject>to:NB estimation empirical_processes statistics nonparametrics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e5d16319e505/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.00579">
    <title>[1909.00579] Asymptotic linear expansion of regularized M-estimators</title>
    <dc:date>2019-09-04T15:19:57+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.00579</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Parametric high-dimensional regression analysis requires the usage of regularization terms to get interpretable models. The respective estimators can be regarded as regularized M-functionals which are naturally highly nonlinear. We study under which conditions these M-functionals are compactly differentiable, so that the corresponding estimators admit an asymptotically linear expansion. In a one-step construction, for a suitably consistent starting estimator, this linearization replaces solving optimization problems by evaluating the corresponding influence curves at the given data points. We show under which conditions the asymptotic linear expansion is valid and provide concrete examples of machine learning algorithms that fit into this framework."]]></description>
<dc:subject>to:NB estimation statistics re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cce2a10774d2/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.06163">
    <title>[1607.06163] Indirect Inference With(Out) Constraints</title>
    <dc:date>2019-08-21T13:13:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.06163</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Indirect Inference (I-I) estimation of structural parameters θ {requires matching observed and simulated statistics, which are most often generated using an auxiliary model that depends on instrumental parameters β.} {The estimators of the instrumental parameters will encapsulate} the statistical information used for inference about the structural parameters. As such, artificially constraining these parameters may restrict the ability of the auxiliary model to accurately replicate features in the structural data, which may lead to a range of issues, such as, a loss of identification. However, in certain situations the parameters β naturally come with a set of q restrictions. Examples include settings where β must be estimated subject to q possibly strict inequality constraints g(β)>0, such as, when I-I is based on GARCH auxiliary models. In these settings we propose a novel I-I approach that uses appropriately modified unconstrained auxiliary statistics, which are simple to compute and always exists. We state the relevant asymptotic theory for this I-I approach without constraints and show that it can be reinterpreted as a standard implementation of I-I through a properly modified binding function. Several examples that have featured in the literature illustrate our approach."]]></description>
<dc:subject>to:NB indirect_inference estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b22c43eccb9f/</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:indirect_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1302.0890">
    <title>[1302.0890] Local Log-linear Models for Capture-Recapture</title>
    <dc:date>2019-08-20T14:10:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1302.0890</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Log-linear models are often used to estimate the size of a closed population using capture-recapture data. When capture probabilities are related to auxiliary covariates, one may select a separate model based on each of several post-strata. We extend post-stratification to its logical extreme by selecting a local log-linear model for each observed unit, while smoothing to achieve stability. Our local models serve a dual purpose: In addition to estimating the size of the population, we estimate the rate of missingness as a function of covariates. A simulation demonstrates the superiority of our method when the generating model varies over the covariate space. Data from the Breeding Bird Survey is used to illustrate the method."

--- When did the title change from "Smooth Poststratification"?]]></description>
<dc:subject>to:NB have_read surveys smoothing statistics estimation kurtz.zachary kith_and_kin</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:509f22ef5f94/</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:surveys"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:smoothing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kurtz.zachary"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.00555">
    <title>[1901.00555] An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation</title>
    <dc:date>2019-08-19T13:25:06+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.00555</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Information theory plays an indispensable role in the development of algorithm-independent impossibility results, both for communication problems and for seemingly distinct areas such as statistics and machine learning. While numerous information-theoretic tools have been proposed for this purpose, the oldest one remains arguably the most versatile and widespread: Fano's inequality. In this chapter, we provide a survey of Fano's inequality and its variants in the context of statistical estimation, adopting a versatile framework that covers a wide range of specific problems. We present a variety of key tools and techniques used for establishing impossibility results via this approach, and provide representative examples covering group testing, graphical model selection, sparse linear regression, density estimation, and convex optimization."]]></description>
<dc:subject>information_theory minimax statistics estimation in_NB have_read re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7f6e296ba272/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:minimax"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.04748">
    <title>[1908.04748] Optimal Estimation of Generalized Average Treatment Effects using Kernel Optimal Matching</title>
    <dc:date>2019-08-14T19:19:35+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.04748</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In causal inference, a variety of causal effect estimands have been studied, including the sample, uncensored, target, conditional, optimal subpopulation, and optimal weighted average treatment effects. Ad-hoc methods have been developed for each estimand based on inverse probability weighting (IPW) and on outcome regression modeling, but these may be sensitive to model misspecification, practical violations of positivity, or both. The contribution of this paper is twofold. First, we formulate the generalized average treatment effect (GATE) to unify these causal estimands as well as their IPW estimates. Second, we develop a method based on Kernel Optimal Matching (KOM) to optimally estimate GATE and to find the GATE most easily estimable by KOM, which we term the Kernel Optimal Weighted Average Treatment Effect. KOM provides uniform control on the conditional mean squared error of a weighted estimator over a class of models while simultaneously controlling for precision. We study its theoretical properties and evaluate its comparative performance in a simulation study. We illustrate the use of KOM for GATE estimation in two case studies: comparing spine surgical interventions and studying the effect of peer support on people living with HIV."]]></description>
<dc:subject>to:NB causal_inference estimation matching statistics kernel_smoothing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c8e1a84e8445/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:matching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kernel_smoothing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://global.oup.com/academic/product/non-standard-parametric-statistical-inference-9780198505044?cc=us&amp;lang=en#">
    <title>Non-Standard Parametric Statistical Inference - Russell Cheng - Oxford University Press</title>
    <dc:date>2019-08-05T18:37:11+00:00</dc:date>
    <link>https://global.oup.com/academic/product/non-standard-parametric-statistical-inference-9780198505044?cc=us&amp;lang=en#</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This book discusses the fitting of parametric statistical models to data samples. Emphasis is placed on: (i) how to recognize situations where the problem is non-standard when parameter estimates behave unusually, and (ii) the use of parametric bootstrap resampling methods in analyzing such problems.
"A frequentist likelihood-based viewpoint is adopted, for which there is a well-established and very practical theory. The standard situation is where certain widely applicable regularity conditions hold. However, there are many apparently innocuous situations where standard theory breaks down, sometimes spectacularly. Most of the departures from regularity are described geometrically, with only sufficient mathematical detail to clarify the non-standard nature of a problem and to allow formulation of practical solutions.
"The book is intended for anyone with a basic knowledge of statistical methods, as is typically covered in a university statistical inference course, wishing to understand or study how standard methodology might fail. Easy to understand statistical methods are presented which overcome these difficulties, and demonstrated by detailed examples drawn from real applications. Simple and practical model-building is an underlying theme.
"Parametric bootstrap resampling is used throughout for analyzing the properties of fitted models, illustrating its ease of implementation even in non-standard situations. Distributional properties are obtained numerically for estimators or statistics not previously considered in the literature because their theoretical distributional properties are too hard to obtain theoretically. Bootstrap results are presented mainly graphically in the book, providing an accessible demonstration of the sampling behaviour of estimators."]]></description>
<dc:subject>to:NB bootstrap estimation hypothesis_testing statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3db28c9164d7/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.00598">
    <title>[1908.00598] Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation</title>
    <dc:date>2019-08-05T12:49:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.00598</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one can trust predictions on new data. Recently promising works were proposed using noise injection combined with Monte-Carlo sampling at inference time to estimate this quantity (e.g. Monte-Carlo dropout). Our main contribution is an approximation of the epistemic uncertainty estimated by these methods that does not require sampling, thus notably reducing the computational overhead. We apply our approach to large-scale visual tasks (i.e., semantic segmentation and depth regression) to demonstrate the advantages of our method compared to sampling-based approaches in terms of quality of the uncertainty estimates as well as of computational overhead."

--- Prediction before scanning the paper: It's the delta method (which I learned as "propagation of error" in physics lab).

--- And on p. 2, start of sec. 3, we read "At its core our method uses error propagation [25], commonly used in physics, where the error is equivalent to the variance".  (Well, at least they know that!)]]></description>
<dc:subject>neural_networks estimation statistics propagation_of_error everything_old_is_new_again uncertainty_for_neural_networks have_read in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8a98269b714d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:propagation_of_error"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:everything_old_is_new_again"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:uncertainty_for_neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.00310">
    <title>[1908.00310] Maximum likelihood estimation of power-law degree distributions using friendship paradox based sampling</title>
    <dc:date>2019-08-02T13:19:22+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.00310</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper considers the problem of estimating a power-law degree distribution of an undirected network. Even though power-law degree distributions are ubiquitous in nature, the widely used parametric methods for estimating them (e.g. linear regression on double-logarithmic axes, maximum likelihood estimation with uniformly sampled nodes) suffer from the large variance introduced by the lack of data-points from the tail portion of the power-law degree distribution. As a solution, we present a novel maximum likelihood estimation approach that exploits the friendship paradox to sample more efficiently from the tail of the degree distribution. We analytically show that the proposed method results in a smaller bias, variance and a Cramer-Rao lower bound compared to the maximum-likelihood estimate obtained with uniformly sampled nodes (which is the most commonly used method in literature). Detailed simulation results are presented to illustrate the performance of the proposed method under different conditions and how it compares with alternative methods."]]></description>
<dc:subject>to:NB network_data_analysis heavy_tails estimation statistics color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:58d86ca6973c/</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:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heavy_tails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<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/1510.00551">
    <title>[1510.00551] Investigation of Parameter Uncertainty in Clustering Using a Gaussian Mixture Model Via Jackknife, Bootstrap and Weighted Likelihood Bootstrap</title>
    <dc:date>2019-07-24T13:59:14+00:00</dc:date>
    <link>https://arxiv.org/abs/1510.00551</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Mixture models are a popular tool in model-based clustering. Such a model is often fitted by a procedure that maximizes the likelihood, such as the EM algorithm. At convergence, the maximum likelihood parameter estimates are typically reported, but in most cases little emphasis is placed on the variability associated with these estimates. In part this may be due to the fact that standard errors are not directly calculated in the model-fitting algorithm, either because they are not required to fit the model, or because they are difficult to compute. The examination of standard errors in model-based clustering is therefore typically neglected. The widely used R package mclust has recently introduced bootstrap and weighted likelihood bootstrap methods to facilitate standard error estimation. This paper provides an empirical comparison of these methods (along with the jackknife method) for producing standard errors and confidence intervals for mixture parameters. These methods are illustrated and contrasted in both a simulation study and in the traditional Old Faithful data set and Thyroid data set."]]></description>
<dc:subject>to:NB statistics estimation mixture_models confidence_sets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c84a3e095cf8/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixture_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.08283">
    <title>[1906.08283] Minimum Stein Discrepancy Estimators</title>
    <dc:date>2019-06-23T17:35:41+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.08283</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["When maximum likelihood estimation is infeasible, one often turns to score matching, contrastive divergence, or minimum probability flow learning to obtain tractable parameter estimates. We provide a unifying perspective of these techniques as minimum Stein discrepancy estimators and use this lens to design new diffusion kernel Stein discrepancy (DKSD) and diffusion score matching (DSM) estimators with complementary strengths. We establish the consistency, asymptotic normality, and robustness of DKSD and DSM estimators, derive stochastic Riemannian gradient descent algorithms for their efficient optimization, and demonstrate their advantages over score matching in models with non-smooth densities or heavy tailed distributions."]]></description>
<dc:subject>to:NB statistics estimation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:935c44965417/</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:estimation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1712.07248">
    <title>[1712.07248] Towards a General Large Sample Theory for Regularized Estimators</title>
    <dc:date>2019-06-21T15:43:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1712.07248</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We present a general framework for studying regularized estimators; such estimators are pervasive in estimation problems wherein "plug-in" type estimators are either ill-defined or ill-behaved. Within this framework, we derive, under primitive conditions, consistency and a generalization of the asymptotic linearity property. We also provide data-driven methods for choosing tuning parameters that, under some conditions, achieve the aforementioned properties. We illustrate the scope of our approach by studying a wide range of applications, revisiting known results and deriving new ones."]]></description>
<dc:subject>statistics estimation optimization to_read in_NB re:HEAS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:54557552758c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<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:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:HEAS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.05944">
    <title>[1906.05944] Statistical Inference for Generative Models with Maximum Mean Discrepancy</title>
    <dc:date>2019-06-19T15:50:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.05944</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["While likelihood-based inference and its variants provide a statistically efficient and widely applicable approach to parametric inference, their application to models involving intractable likelihoods poses challenges. In this work, we study a class of minimum distance estimators for intractable generative models, that is, statistical models for which the likelihood is intractable, but simulation is cheap. The distance considered, maximum mean discrepancy (MMD), is defined through the embedding of probability measures into a reproducing kernel Hilbert space. We study the theoretical properties of these estimators, showing that they are consistent, asymptotically normal and robust to model misspecification. A main advantage of these estimators is the flexibility offered by the choice of kernel, which can be used to trade-off statistical efficiency and robustness. On the algorithmic side, we study the geometry induced by MMD on the parameter space and use this to introduce a novel natural gradient descent-like algorithm for efficient implementation of these estimators. We illustrate the relevance of our theoretical results on several classes of models including a discrete-time latent Markov process and two multivariate stochastic differential equation models."]]></description>
<dc:subject>simulation statistics estimation hilbert_space simulation-based_inference in_NB to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:148889e70eec/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hilbert_space"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:simulation-based_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1805.07454">
    <title>[1805.07454] Fisher Efficient Inference of Intractable Models</title>
    <dc:date>2019-05-29T21:13:23+00:00</dc:date>
    <link>https://arxiv.org/abs/1805.07454</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Maximum Likelihood Estimators (MLE) has many good properties. For example, the asymptotic variance of MLE solution attains equality of the asymptotic Cram{é}r-Rao lower bound (efficiency bound), which is the minimum possible variance for an unbiased estimator. However, obtaining such MLE solution requires calculating the likelihood function which may not be tractable due to the normalization term of the density model. In this paper, we derive a Discriminative Likelihood Estimator (DLE) from the Kullback-Leibler divergence minimization criterion implemented via density ratio estimation procedure and Stein operator. We study the problem of model inference using DLE. We prove its consistency and show the asymptotic variance of its solution can also attain the equality of the efficiency bound under mild regularity conditions. We also propose a dual formulation of DLE which can be easily optimized. Numerical studies validate our asymptotic theorems and we give an example where DLE successfully estimates an intractable model constructed using a pre-trained deep neural network."]]></description>
<dc:subject>to:NB likelihood estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d647f388c259/</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:likelihood"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.06576">
    <title>[1903.06576] A nonasymptotic law of iterated logarithm for general M-estimators</title>
    <dc:date>2019-05-27T15:06:29+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.06576</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["M-estimators are ubiquitous in machine learning and statistical learning theory. They are used both for defining prediction strategies and for evaluating their precision. In this paper, we propose the first non-asymptotic "any-time" deviation bounds for general M-estimators, where "any-time" means that the bound holds with a prescribed probability for every sample size. These bounds are nonasymptotic versions of the law of iterated logarithm. They are established under general assumptions such as Lipschitz continuity of the loss function and (local) curvature of the population risk. These conditions are satisfied for most examples used in machine learning, including those ensuring robustness to outliers and to heavy tailed distributions. As an example of application, we consider the problem of best arm identification in a parametric stochastic multi-arm bandit setting. We show that the established bound can be converted into a new algorithm, with provably optimal theoretical guarantees. Numerical experiments illustrating the validity of the algorithm are reported."]]></description>
<dc:subject>to:NB estimation deviation_inequalities statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8e1762700ea4/</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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:deviation_inequalities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>