<?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://arxiv.org/abs/2511.05733"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12739"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/full/10.1111/jtsa.12295"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2402.13622"/>
	<rdf:li rdf:resource="https://projecteuclid.org/journals/annals-of-statistics/volume-21/issue-4/Comparing-Nonparametric-Versus-Parametric-Regression-Fits/10.1214/aos/1176349403.full"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1411.5279"/>
	<rdf:li rdf:resource="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/A-causal-bootstrap/10.1214/20-AOS2009.short"/>
	<rdf:li rdf:resource="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/Bootstrap-long-memory-processes-in-the-frequency-domain/10.1214/20-AOS2006.short"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.09736"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.05918"/>
	<rdf:li rdf:resource="https://doi.org/10.1111/jtsa.12573"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.04134"/>
	<rdf:li rdf:resource="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-2/Empirical-process-results-for-exchangeable-arrays/10.1214/20-AOS1981.short"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.04716"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2103.10720"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.12312"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2009.06170"/>
	<rdf:li rdf:resource="https://academic.oup.com/biomet/article-abstract/107/3/753/5831314"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2004.06615"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.03562"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.ejs/1609902193"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.09513"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.08223"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.02097"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12573"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.11248"/>
	<rdf:li rdf:resource="https://www.tandfonline.com/doi/full/10.1080/10618600.2020.1714633"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1581930135"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1594972834"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1597370678"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.07664"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.ejs/1569895283"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2004.08935"/>
	<rdf:li rdf:resource="https://academic.oup.com/biomet/article-abstract/106/4/781/5566518"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.09695"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1909.02662"/>
	<rdf:li rdf:resource="https://www.annualreviews.org/doi/abs/10.1146/annurev-economics-080218-025651"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.03180"/>
	<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/1907.12116"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.ejs/1561687408"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11222-016-9655-0"/>
	<rdf:li rdf:resource="https://academic.oup.com/biomet/article-abstract/106/2/385/5431311"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1903.05403"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.00696"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1305292042"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11222-016-9717-3"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s11222-016-9712-8?"/>
	<rdf:li rdf:resource="https://www.nature.com/articles/s41586-018-0043-0"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12296"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.05401"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12275/abstract"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12270/abstract"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.02834"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.00813"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12256/abstract"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12221/abstract"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/113/51/14668.abstract"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1311.4555"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1311.5828"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12214/abstract"/>
	<rdf:li rdf:resource="http://www.mlgworkshop.org/2016/paper/MLG2016_paper_32.pdf"/>
	<rdf:li rdf:resource="http://projecteuclid.org/euclid.aos/1176348120"/>
	<rdf:li rdf:resource="http://link.springer.com/article/10.1007/s11203-015-9120-2?wt_mc=alerts.TOCjournals"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1601.00934"/>
	<rdf:li rdf:resource="http://onlinelibrary.wiley.com/doi/10.3982/ECTA6474/abstract"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.05034"/>
	<rdf:li rdf:resource="http://www.jstor.org/stable/1390820"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1506.02326"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1506.05779"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/2511.05733">
    <title>[2511.05733] Nonparametric Block Bootstrap Kolmogorov-Smirnov Goodness-of-Fit Test</title>
    <dc:date>2026-05-28T13:18:20+00:00</dc:date>
    <link>https://arxiv.org/abs/2511.05733</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The Kolmogorov--Smirnov (KS) test is a widely used statistical test that assesses the conformity of a sample to a specified distribution. Its efficacy, however, diminishes with serially dependent data and when parameters within the hypothesized distribution are unknown. For independent data, parametric and nonparametric bootstrap procedures are available to adjust for estimated parameters. For serially dependent stationary data, parametric bootstrap has been developed with a working serial dependence structure. A counterpart for the nonparametric bootstrap approach, which needs a bias correction, has not been studied. Addressing this gap, our study introduces a bias correction method employing a nonparametric block bootstrap, which approximates the distribution of the KS statistic in assessing the goodness-of-fit of the marginal distribution of a stationary series, accounting for unspecified serial dependence and unspecified parameters. We assess its effectiveness through simulations, scrutinizing both its size and power. The practicality of our method is further illustrated with an examination of stock returns from the S\&P 500 index, showcasing its utility in real-world applications."

--- Gated: [https://doi.org/10.1080/00031305.2025.2588131]]]></description>
<dc:subject>in_NB goodness-of-fit time_series bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:568f300920e5/</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:goodness-of-fit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12739">
    <title>Bootstrap prediction inference of nonlinear autoregressive models - Wu - 2024 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2024-08-06T13:38:09+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12739</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The nonlinear autoregressive (NLAR) model plays an important role in modeling and predicting time series. One-step ahead prediction is straightforward using the NLAR model, but the multi-step ahead prediction is cumbersome. For instance, iterating the one-step ahead predictor is a convenient strategy for linear autoregressive (LAR) models, but it is suboptimal under NLAR. In this article, we first propose a simulation and/or bootstrap algorithm to construct optimal point predictors under an $L_1$ or $L_2$ loss criterion. In addition, we construct bootstrap prediction intervals in the multi-step ahead prediction problem; in particular, we develop an asymptotically valid quantile prediction interval as well as a pertinent prediction interval for future values. To correct the undercoverage of prediction intervals with finite samples, we further employ predictive – as opposed to fitted – residuals in the bootstrap process. Simulation and empirical studies are also given to substantiate the finite sample performance of our methods."]]></description>
<dc:subject>to:NB bootstrap time_series prediction confidence_sets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e607b65db0c4/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/full/10.1111/jtsa.12295">
    <title>Robust Regression on Stationary Time Series: A Self‐Normalized Resampling Approach - Akashi - 2018 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2024-06-21T19:21:38+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/full/10.1111/jtsa.12295</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This article extends the self-normalized subsampling method of Bai et al. (2016) to the M-estimation of linear regression models, where the covariate and the noise are stationary time series which may have long-range dependence or heavy tails. The method yields an asymptotic confidence region for the unknown coefficients of the linear regression. The determination of these regions does not involve unknown parameters such as the intensity of the dependence or the heaviness of the distributional tail of the time series. Additional simulations can be found in a supplement. The computer codes are available from the authors."]]></description>
<dc:subject>to:NB to_read bootstrap time_series heavy_tails</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7bc4befcee95/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heavy_tails"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2402.13622">
    <title>[2402.13622] Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression</title>
    <dc:date>2024-02-27T20:02:23+00:00</dc:date>
    <link>https://arxiv.org/abs/2402.13622</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We investigate popular resampling methods for estimating the uncertainty of statistical models, such as subsampling, bootstrap and the jackknife, and their performance in high-dimensional supervised regression tasks. We provide a tight asymptotic description of the biases and variances estimated by these methods in the context of generalized linear models, such as ridge and logistic regression, taking the limit where the number of samples n and dimension d of the covariates grow at a comparable fixed rate α=n/d. Our findings are three-fold: i) resampling methods are fraught with problems in high dimensions and exhibit the double-descent-like behavior typical of these situations; ii) only when α is large enough do they provide consistent and reliable error estimations (we give convergence rates); iii) in the over-parametrized regime α<1 relevant to modern machine learning practice, their predictions are not consistent, even with optimal regularization."

--- Not surprising but good to have confirmed?]]></description>
<dc:subject>to:NB high-dimensional_statistics regression bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0dd2f2285d46/</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:high-dimensional_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/journals/annals-of-statistics/volume-21/issue-4/Comparing-Nonparametric-Versus-Parametric-Regression-Fits/10.1214/aos/1176349403.full">
    <title>Comparing Nonparametric Versus Parametric Regression Fits</title>
    <dc:date>2023-05-01T19:55:30+00:00</dc:date>
    <link>https://projecteuclid.org/journals/annals-of-statistics/volume-21/issue-4/Comparing-Nonparametric-Versus-Parametric-Regression-Fits/10.1214/aos/1176349403.full</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In general, there will be visible differences between a parametric and a nonparametric curve estimate. It is therefore quite natural to compare these in order to decide whether the parametric model could be justified. An asymptotic quantification is the distribution of the integrated squared difference between these curves. We show that the standard way of bootstrapping this statistic fails. We use and analyse a different form of bootstrapping for this task. We call this method the wild bootstrap and apply it to fitting Engel curves in expenditure data analysis."]]></description>
<dc:subject>regression goodness-of-fit model_checking nonparametrics bootstrap hardle.wolfgang re:ADAfaEPoV cleaning_out_the_filing_cabinet_for_the_first_time_since_2005 in_NB have_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7023957251ed/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goodness-of-fit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_checking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hardle.wolfgang"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
	<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:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1411.5279">
    <title>[1411.5279] What Teachers Should Know about the Bootstrap: Resampling in the Undergraduate Statistics Curriculum</title>
    <dc:date>2021-09-17T14:09:40+00:00</dc:date>
    <link>https://arxiv.org/abs/1411.5279</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["I have three goals in this article: (1) To show the enormous potential of bootstrapping and permutation tests to help students understand statistical concepts including sampling distributions, standard errors, bias, confidence intervals, null distributions, and P-values. (2) To dig deeper, understand why these methods work and when they don't, things to watch out for, and how to deal with these issues when teaching. (3) To change statistical practice---by comparing these methods to common t tests and intervals, we see how inaccurate the latter are; we confirm this with asymptotics. n >= 30 isn't enough---think n >= 5000. Resampling provides diagnostics, and more accurate alternatives. Sadly, the common bootstrap percentile interval badly under-covers in small samples; there are better alternatives. The tone is informal, with a few stories and jokes."]]></description>
<dc:subject>have_read statistics teaching bootstrap to_teach:undergrad-ADA to_teach:statistics_of_inequality_and_discrimination in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:39c04c330c50/</dc:identifier>
<taxo:topics><rdf:Bag>	<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:teaching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<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:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/A-causal-bootstrap/10.1214/20-AOS2009.short">
    <title>A causal bootstrap</title>
    <dc:date>2021-08-10T14:03:05+00:00</dc:date>
    <link>https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/A-causal-bootstrap/10.1214/20-AOS2009.short</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The bootstrap, introduced by The Jackknife, the Bootstrap and Other Resampling Plans ((1982), SIAM), has become a very popular method for estimating variances and constructing confidence intervals. A key insight is that one can approximate the properties of estimators by using the empirical distribution function of the sample as an approximation for the true distribution function. This approach views the uncertainty in the estimator as coming exclusively from sampling uncertainty. We argue that for causal estimands the uncertainty arises entirely, or partially, from a different source, corresponding to the stochastic nature of the treatment received. We develop a bootstrap procedure for inference regarding the average treatment effect that accounts for this uncertainty, and compare its properties to that of the classical bootstrap. We consider completely randomized and observational designs as well as designs with imperfect compliance."

--- Efron's 1982 book did not, of course, introduce the bootstrap.

]]></description>
<dc:subject>to:NB to_read causal_inference bootstrap re:ADAfaEPoV statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0c2720997f44/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/Bootstrap-long-memory-processes-in-the-frequency-domain/10.1214/20-AOS2006.short">
    <title>Bootstrap long memory processes in the frequency domain</title>
    <dc:date>2021-08-09T16:23:20+00:00</dc:date>
    <link>https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-3/Bootstrap-long-memory-processes-in-the-frequency-domain/10.1214/20-AOS2006.short</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The aim of the paper is to describe a bootstrap, contrary to the sieve bootstrap, valid under either long memory (LM) or short memory (SM) dependence. One of the reasons of the failure of the sieve bootstrap in our context is that under LM dependence, the sieve bootstrap may not be able to capture the true covariance structure of the original data. We also describe and examine the validity of the bootstrap scheme for the least squares estimator of the parameter in a regression model and for model specification. The motivation for the latter example comes from the observation that the asymptotic distribution of the test is intractable."]]></description>
<dc:subject>to:NB bootstrap time_series fourier_analysis long-range_dependence statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fbc234c66157/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fourier_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:long-range_dependence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.09736">
    <title>[2107.09736] Recent Developments in Inference: Practicalities for Applied Economics</title>
    <dc:date>2021-07-23T02:52:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.09736</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We provide a review of recent developments in the calculation of standard errors and test statistics for statistical inference. While much of the focus of the last two decades in economics has been on generating unbiased coefficients, recent years has seen a variety of advancements in correcting for non-standard standard errors. We synthesize these recent advances in addressing challenges to conventional inference, like heteroskedasticity, clustering, serial correlation, and testing multiple hypotheses. We also discuss recent advancements in numerical methods, such as the bootstrap, wild bootstrap, and randomization inference. We make three specific recommendations. First, applied economists need to clearly articulate the challenges to statistical inference that are present in data as well as the source of those challenges. Second, modern computing power and statistical software means that applied economists have no excuse for not correctly calculating their standard errors and test statistics. Third, because complicated sampling strategies and research designs make it difficult to work out the correct formula for standard errors and test statistics, we believe that in the applied economics profession it should become standard practice to rely on asymptotic refinements to the distribution of an estimator or test statistic via bootstrapping. Throughout, we reference built-in and user-written Stata commands that allow one to quickly calculate accurate standard errors and relevant test statistics."]]></description>
<dc:subject>to:NB statistics econometrics bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f27367abbbc8/</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:econometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.05918">
    <title>[2106.05918] Bias, Consistency, and Alternative Perspectives of the Infinitesimal Jackknife</title>
    <dc:date>2021-06-24T20:42:42+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.05918</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Though introduced nearly 50 years ago, the infinitesimal jackknife (IJ) remains a popular modern tool for quantifying predictive uncertainty in complex estimation settings. In particular, when supervised learning ensembles are constructed via bootstrap samples, recent work demonstrated that the IJ estimate of variance is particularly convenient and useful. However, despite the algebraic simplicity of its final form, its derivation is rather complex. As a result, studies clarifying the intuition behind the estimator or rigorously investigating its properties have been severely lacking. This work aims to take a step forward on both fronts. We demonstrate that surprisingly, the exact form of the IJ estimator can be obtained via a straightforward linear regression of the individual bootstrap estimates on their respective weights or via the classical jackknife. The latter realization is particularly useful as it allows us to formally investigate the bias of the IJ variance estimator and better characterize the settings in which its use is appropriate. Finally, we extend these results to the case of U-statistics where base models are constructed via subsampling rather than bootstrapping and provide a consistent estimate of the resulting variance."]]></description>
<dc:subject>to:NB bootstrap confidence_sets ensemble_methods statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a62e1cc12b78/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://doi.org/10.1111/jtsa.12573">
    <title>Quasi‐maximum likelihood and the kernel block bootstrap for nonlinear dynamic models - Parente - 2021 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2021-06-08T13:38:30+00:00</dc:date>
    <link>https://doi.org/10.1111/jtsa.12573</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This article applies a novel bootstrap method, the kernel block bootstrap (KBB), to quasi-maximum likelihood (QML) estimation of dynamic models with stationary strong mixing data. The method first kernel weights the components comprising the quasi-log likelihood function in an appropriate way and then samples the resultant transformed components using the standard ‘m out of n’ bootstrap. We investigate the first-order asymptotic properties of the KBB method for QML demonstrating, in particular, its consistency and the first-order asymptotic validity of the bootstrap approximation to the distribution of the QML estimator. A set of simulation experiments for the mean regression model illustrates the efficacy of the kernel block bootstrap for QML estimation."

--- Feel like I might have already bookmarked an earlier version of this...]]></description>
<dc:subject>to:NB bootstrap time_series statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d75dde2352c8/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.04134">
    <title>[2105.04134] Bagging cross-validated bandwidth selection in nonparametric regression estimation with applications to large-sized samples</title>
    <dc:date>2021-05-12T18:15:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.04134</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Cross-validation is a well-known and widely used bandwidth selection method in nonparametric regression estimation. However, this technique has two remarkable drawbacks: (i) the large variability of the selected bandwidths, and (ii) the inability to provide results in a reasonable time for very large sample sizes. To overcome these problems, bagging cross-validation bandwidths are analyzed in this paper. This approach consists in computing the cross-validation bandwidths for a finite number of subsamples and then rescaling the averaged smoothing parameters to the original sample size. Under a random-design regression model, asymptotic expressions up to a second-order for the bias and variance of the leave-one-out cross-validation bandwidth for the Nadaraya--Watson estimator are obtained. Subsequently, the asymptotic bias and variance and the limit distribution are derived for the bagged cross-validation selector. Suitable choices of the number of subsamples and the subsample size lead to an n−1/2 rate for the convergence in distribution of the bagging cross-validation selector, outperforming the rate n−3/10 of leave-one-out cross-validation. Several simulations and an illustration on a real dataset related to the COVID-19 pandemic show the behavior of our proposal and its better performance, in terms of statistical efficiency and computing time, when compared to leave-one-out cross-validation."]]></description>
<dc:subject>to:NB cross-validation ensemble_methods bootstrap to_teach:data-mining kernel_smoothing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f2a3494ec6a3/</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:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kernel_smoothing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-2/Empirical-process-results-for-exchangeable-arrays/10.1214/20-AOS1981.short">
    <title>Empirical process results for exchangeable arrays</title>
    <dc:date>2021-04-14T15:55:48+00:00</dc:date>
    <link>https://projecteuclid.org/journals/annals-of-statistics/volume-49/issue-2/Empirical-process-results-for-exchangeable-arrays/10.1214/20-AOS1981.short</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Exchangeable arrays are natural tools to model common forms of dependence between units of a sample. Jointly exchangeable arrays are well suited to dyadic data, where observed random variables are indexed by two units from the same population. Examples include trade flows between countries or relationships in a network. Separately exchangeable arrays are well suited to multiway clustering, where units sharing the same cluster (e.g., geographical areas or sectors of activity when considering individual wages) may be dependent in an unrestricted way. We prove uniform laws of large numbers and central limit theorems for such exchangeable arrays. We obtain these results under the same moment restrictions and conditions on the class of functions as those typically assumed with i.i.d. data. We also show the convergence of bootstrap processes adapted to such arrays."]]></description>
<dc:subject>to:NB graphons exchangeability empirical_processes bootstrap re:network_bootstraps to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:704083f7b44d/</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:graphons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:exchangeability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_bootstraps"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.04716">
    <title>[2104.04716] Analytic and Bootstrap-after-Cross-Validation Methods for Selecting Penalty Parameters of High-Dimensional M-Estimators</title>
    <dc:date>2021-04-13T04:01:37+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.04716</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We develop two new methods for selecting the penalty parameter for the ℓ1-penalized high-dimensional M-estimator, which we refer to as the analytic and bootstrap-after-cross-validation methods. For both methods, we derive nonasymptotic error bounds for the corresponding ℓ1-penalized M-estimator and show that the bounds converge to zero under mild conditions, thus providing a theoretical justification for these methods. We demonstrate via simulations that the finite-sample performance of our methods is much better than that of previously available and theoretically justified methods."]]></description>
<dc:subject>to:NB lasso bootstrap cross-validation model_selection</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1598c1a5531e/</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:lasso"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2103.10720">
    <title>[2103.10720] Gaussian approximation and spatially dependent wild bootstrap for high-dimensional spatial data</title>
    <dc:date>2021-04-12T03:17:19+00:00</dc:date>
    <link>https://arxiv.org/abs/2103.10720</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we establish a high-dimensional CLT for the sample mean of p-dimensional spatial data observed over irregularly spaced sampling sites in ℝd, allowing the dimension p to be much larger than the sample size n. We adopt a stochastic sampling scheme that can generate irregularly spaced sampling sites in a flexible manner and include both pure increasing domain and mixed increasing domain frameworks. To facilitate statistical inference, we develop the spatially dependent wild bootstrap (SDWB) and justify its asymptotic validity in high dimensions by deriving error bounds that hold almost surely conditionally on the stochastic sampling sites. Our dependence conditions on the underlying random field cover a wide class of random fields such as Gaussian random fields and continuous autoregressive moving average random fields. Through numerical simulations and a real data analysis, we demonstrate the usefulness of our bootstrap-based inference in several applications, including joint confidence interval construction for high-dimensional spatial data and change-point detection for spatio-temporal data."]]></description>
<dc:subject>to:NB spatial_statistics spatio-temporal_statistics bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4c43cd6479ca/</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:spatial_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spatio-temporal_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.12312">
    <title>[2101.12312] The Bootstrap for Network Dependent Processes</title>
    <dc:date>2021-04-12T03:06:39+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.12312</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper focuses on the bootstrap for network dependent processes under the conditional ψ-weak dependence. Such processes are distinct from other forms of random fields studied in the statistics and econometrics literature so that the existing bootstrap methods cannot be applied directly. We propose a block-based approach and a modification of the dependent wild bootstrap for constructing confidence sets for the mean of a network dependent process. In addition, we establish the consistency of these methods for the smooth function model and provide the bootstrap alternatives to the network heteroskedasticity-autocorrelation consistent (HAC) variance estimator. We find that the modified dependent wild bootstrap and the corresponding variance estimator are consistent under weaker conditions relative to the block-based method, which makes the former approach preferable for practical implementation."]]></description>
<dc:subject>to:NB network_data_analysis bootstrap re:network_bootstraps</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:60ae477624f9/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_bootstraps"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2009.06170">
    <title>[2009.06170] Trading off Accuracy for Speedup: Multiplier Bootstraps for Subgraph Counts</title>
    <dc:date>2021-04-10T03:59:14+00:00</dc:date>
    <link>https://arxiv.org/abs/2009.06170</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a new class of multiplier bootstraps for count functionals. We consider bootstrap procedures with linear and quadratic weights. These correspond to the first and second-order terms of the Hoeffding decomposition of the bootstrapped statistic arising from the multiplier bootstrap, respectively. We show that the quadratic bootstrap procedure achieves higher-order correctness for appropriately sparse graphs. The linear bootstrap procedure requires fewer estimated network statistics, leading to improved accuracy over its higher-order correct counterpart in sparser regimes. To improve the computational properties of the linear bootstrap further, we consider fast sketching methods to conduct approximate subgraph counting and establish consistency of the resulting bootstrap procedure. We complement our theoretical results with a simulation study and real data analysis and verify that our procedure offers state-of-the-art performance for several functionals."]]></description>
<dc:subject>to:NB bootstrap network_data_analysis kith_and_kin lunde.robert sarkar.purnamrita</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:076aecc8b7a2/</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:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lunde.robert"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sarkar.purnamrita"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/biomet/article-abstract/107/3/753/5831314">
    <title>Bootstrapping M-estimators in generalized autoregressive conditional heteroscedastic models | Biometrika | Oxford Academic</title>
    <dc:date>2021-03-17T20:26:44+00:00</dc:date>
    <link>https://academic.oup.com/biomet/article-abstract/107/3/753/5831314</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the weighted bootstrap approximation to the distribution of a class of M-estimators for the parameters of the generalized autoregressive conditional heteroscedastic model. We prove that the bootstrap distribution, given the data, is a consistent estimate in probability of the distribution of the M-estimator, which is asymptotically normal. We propose an algorithm for the computation of M-estimates which at the same time is useful for computing bootstrap replicates from the given data. Our simulation study indicates superior coverage rates for various weighted bootstrap schemes compared with the rates based on the normal approximation and existing bootstrap methods for the generalized autoregressive conditional heteroscedastic model, such as percentile tt-subsampling schemes. Since some familiar bootstrap schemes are special cases of the weighted bootstrap, this paper thus provides a unified theory and algorithm for bootstrapping in generalized autoregressive conditional heteroscedastic models."]]></description>
<dc:subject>to:NB time_series bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7d2916856e13/</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:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2004.06615">
    <title>[2004.06615] Edgeworth expansions for network moments</title>
    <dc:date>2021-01-22T17:42:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2004.06615</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Network method of moments arXiv:1202.5101 is an important tool for nonparametric network inference. However, there has been little investigation on accurate descriptions of the sampling distributions of network moment statistics. In this paper, we present the first higher-order accurate approximation to the sampling CDF of a studentized network moment by Edgeworth expansion. In sharp contrast to classical literature on noiseless U-statistics, we show that the Edgeworth expansion of a network moment statistic as a noisy U-statistic can achieve higher-order accuracy without non-lattice or smoothness assumptions but just requiring weak regularity conditions. Behind this result is our surprising discovery that the two typically-hated factors in network analysis, namely, sparsity and edge-wise observational errors, jointly play a blessing role, contributing a crucial self-smoothing effect in the network moment statistic and making it analytically tractable. Our assumptions match the minimum requirements in related literature. For sparse networks, our theory shows a simple normal approximation achieves a gradually depreciating Berry-Esseen bound as the network becomes sparser. This result also refines the best previous theoretical result.
"For practitioners, our empirical Edgeworth expansion is highly accurate, fast and easy to implement. We demonstrate the clear advantage of our method by comprehensive simulation studies.
"We showcase three applications of our results in network inference. We prove, to our knowledge, the first theoretical guarantee of higher-order accuracy for some network bootstrap schemes, and moreover, the first theoretical guidance for selecting the sub-sample size for network sub-sampling. We also derive one-sample test and Cornish-Fisher confidence interval for a given moment with higher-order accurate controls of confidence level and type I error, respectively."

--- Had a very enjoyable conversation with Y.Z. about this yesterday in conjunction with talking "at" OSU, and am eager to read this.]]></description>
<dc:subject>to:NB to_read network_data_analysis bootstrap confidence_sets graphons re:network_bootstraps</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:87a62cf37bec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_bootstraps"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.03562">
    <title>[2101.03562] Bootstrapping Non-Stationary Stochastic Volatility</title>
    <dc:date>2021-01-12T22:40:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.03562</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper we investigate how the bootstrap can be applied to time series regressions when the volatility of the innovations is random and non-stationary. The volatility of many economic and financial time series displays persistent changes and possible non-stationarity. However, the theory of the bootstrap for such models has focused on deterministic changes of the unconditional variance and little is known about the performance and the validity of the bootstrap when the volatility is driven by a non-stationary stochastic process. This includes near-integrated volatility processes as well as near-integrated GARCH processes. This paper develops conditions for bootstrap validity in time series regressions with non-stationary, stochastic volatility. We show that in such cases the distribution of bootstrap statistics (conditional on the data) is random in the limit. Consequently, the conventional approaches to proving bootstrap validity, involving weak convergence in probability of the bootstrap statistic, fail to deliver the required results. Instead, we use the concept of `weak convergence in distribution' to develop and establish novel conditions for validity of the wild bootstrap, conditional on the volatility process. We apply our results to several testing problems in the presence of non-stationary stochastic volatility, including testing in a location model, testing for structural change and testing for an autoregressive unit root. Sufficient conditions for bootstrap validity include the absence of statistical leverage effects, i.e., correlation between the error process and its future conditional variance. The results are illustrated using Monte Carlo simulations, which indicate that the wild bootstrap leads to size control even in small samples."]]></description>
<dc:subject>to:NB bootstrap non-stationarity time_series statistical_inference_for_stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f290a00d25d5/</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:non-stationarity"/>
	<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:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.ejs/1609902193">
    <title>Wang , Politis : Asymptotic validity of bootstrap confidence intervals in nonparametric regression without an additive model</title>
    <dc:date>2021-01-06T17:11:51+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.ejs/1609902193</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Bootstrap for nonparametric regression has been around for more than 30 years. Nevertheless, most results are based on assuming an additive regression model with respect to independent and identical (i.i.d.) errors. An exception is the Local Bootstrap of Shi [23] for which, however, no bootstrap consistency results are available. We attempt to remedy this here while at the same time showing bootstrap consistency for a more general class of methods that fall under the heading of Model-free Bootstrap of Politis [18]."]]></description>
<dc:subject>to:NB regression confidence_sets statistics bootstrap politis.dmitris</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c00814bcd3a3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:politis.dmitris"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.09513">
    <title>[2012.09513] Nearly optimal central limit theorem and bootstrap approximations in high dimensions</title>
    <dc:date>2020-12-18T10:33:42+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.09513</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we derive new, nearly optimal bounds for the Gaussian approximation to scaled averages of n independent high-dimensional centered random vectors X1,…,Xn over the class of rectangles in the case when the covariance matrix of the scaled average is non-degenerate. In the case of bounded Xi's, the implied bound for the Kolmogorov distance between the distribution of the scaled average and the Gaussian vector takes the form
C(B2nlog3d/n)1/2logn,
where d is the dimension of the vectors and Bn is a uniform envelope constant on components of Xi's. This bound is sharp in terms of d and Bn, and is nearly (up to logn) sharp in terms of the sample size n. In addition, we show that similar bounds hold for the multiplier and empirical bootstrap approximations. Moreover, we establish bounds that allow for unbounded Xi's, formulated solely in terms of moments of Xi's. Finally, we demonstrate that the bounds can be further improved in some special smooth and zero-skewness cases."]]></description>
<dc:subject>to:NB high-dimensional_probability central_limit_theorem bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:98fe00635045/</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:high-dimensional_probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:central_limit_theorem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.08223">
    <title>[2012.08223] Long-term prediction intervals with many covariates</title>
    <dc:date>2020-12-16T16:04:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.08223</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Accurate forecasting is one of the fundamental focus in the literature of econometric time-series. Often practitioners and policy makers want to predict outcomes of an entire time horizon in the future instead of just a single k-step ahead prediction. These series, apart from their own possible non-linear dependence, are often also influenced by many external predictors. In this paper, we construct prediction intervals of time-aggregated forecasts in a high-dimensional regression setting. Our approach is based on quantiles of residuals obtained by the popular LASSO routine. We allow for general heavy-tailed, long-memory, and nonlinear stationary error process and stochastic predictors. Through a series of systematically arranged consistency results we provide theoretical guarantees of our proposed quantile-based method in all of these scenarios. After validating our approach using simulations we also propose a novel bootstrap based method that can boost the coverage of the theoretical intervals. Finally analyzing the EPEX Spot data, we construct prediction intervals for hourly electricity prices over horizons spanning 17 weeks and contrast them to selected Bayesian and bootstrap interval forecasts."]]></description>
<dc:subject>to:NB time_series prediction confidence_sets bootstrap lasso wu.wei_biao to_read to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:51b8eb54be2f/</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:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lasso"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wu.wei_biao"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<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/2002.02097">
    <title>[2002.02097] Dependence-Robust Inference Using Resampled Statistics</title>
    <dc:date>2020-12-02T15:27:48+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.02097</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We develop inference procedures robust to general forms of weak dependence. The procedures use test statistics constructed by resampling data in a manner that does not depend on the unknown correlation structure of the data. We prove that the statistics are asymptotically normal under the weak requirement that the target parameter can be consistently estimated at the parametric rate. This holds for regular estimators under many well-known forms of weak dependence and justifies the claim of dependence-robustness. We consider applications to settings with unknown or complicated forms of dependence, with various forms of network dependence as leading examples. We develop tests for both moment equalities and inequalities."]]></description>
<dc:subject>to:NB bootstrap time_series network_data_analysis to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f5e0aa17b665/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12573">
    <title>Quasi‐Maximum Likelihood and The Kernel Block Bootstrap for Nonlinear Dynamic Models - Parente - - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2020-11-30T06:16:20+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12573</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper applies a novel bootstrap method, the kernel block bootstrap, to quasi‐maximum likelihood estimation of dynamic models with stationary strong mixing data. The method first kernel weights the components comprising the quasi‐log likelihood function in an appropriate way and then samples the resultant transformed components using the standard “m out of n" bootstrap. We investigate the first order asymptotic properties of the kernel block bootstrap method for quasi‐maximum likelihood demonstrating, in particular, its consistency and the first‐order asymptotic validity of the bootstrap approximation to the distribution of the quasi‐maximum likelihood estimator. A set of simulation experiments for the mean regression model illustrates the efficacy of the kernel block bootstrap for quasi‐maximum likelihood estimation."]]></description>
<dc:subject>to:NB bootstrap time_series statistical_inference_for_stochastic_processes likelihood statistics kernel_smoothing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fd258f2ba0b0/</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: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:likelihood"/>
	<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://arxiv.org/abs/2011.11248">
    <title>[2011.11248] Asymptotics of the Empirical Bootstrap Method Beyond Asymptotic Normality</title>
    <dc:date>2020-11-25T14:38:48+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.11248</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["One of the most commonly used methods for forming confidence intervals for statistical inference is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown. However, despite its ubiquitous role, its theoretical properties are still not well understood for non-asymptotically normal estimators. In this paper, under stability conditions, we establish the limiting distribution of the empirical bootstrap estimator, derive tight conditions for it to be asymptotically consistent, and quantify the speed of convergence. Moreover, we propose three alternative ways to use the bootstrap method to build confidence intervals with coverage guarantees. Finally, we illustrate the generality and tightness of our results by a series of examples, including uniform confidence bands, two-sample kernel tests, minmax stochastic programs and the empirical risk of stacked estimators."]]></description>
<dc:subject>to:NB bootstrap confidence_sets statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ec4d2c655c06/</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:confidence_sets"/>
	<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/10.1080/10618600.2020.1714633">
    <title>The Automatic Construction of Bootstrap Confidence Intervals: Journal of Computational and Graphical Statistics: Vol 29, No 3</title>
    <dc:date>2020-11-20T04:04:12+00:00</dc:date>
    <link>https://www.tandfonline.com/doi/full/10.1080/10618600.2020.1714633</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The standard intervals, for example, θˆ±1.96σˆθ̂±1.96σ̂ for nominal 95% two-sided coverage, are familiar and easy to use, but can be of dubious accuracy in regular practice. Bootstrap confidence intervals offer an order of magnitude improvement—from first order to second order accuracy. This article introduces a new set of algorithms that automate the construction of bootstrap intervals, substituting computer power for the need to individually program particular applications. The algorithms are described in terms of the underlying theory that motivates them, along with examples of their application. They are implemented in the R package bcaboot. Supplementary materials for this article are available online."]]></description>
<dc:subject>to:NB bootstrap confidence_sets efron.bradley computational_statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:832a6641bb4b/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:efron.bradley"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1581930135">
    <title>Lee , Yang : Bootstrap confidence regions based on M-estimators under nonstandard conditions</title>
    <dc:date>2020-11-19T04:43:33+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1581930135</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Suppose that a confidence region is desired for a subvector θθ of a multidimensional parameter ξ=(θ,ψ)ξ=(θ,ψ), based on an M-estimator ξ̂ n=(θ̂ n,ψ̂ n)ξ^n=(θ^n,ψ^n) calculated from a random sample of size nn. Under nonstandard conditions ξ̂ nξ^n often converges at a nonregular rate rnrn, in which case consistent estimation of the distribution of rn(θ̂ n−θ)rn(θ^n−θ), a pivot commonly chosen for confidence region construction, is most conveniently effected by the mm out of nn bootstrap. The above choice of pivot has three drawbacks: (i) the shape of the region is either subjectively prescribed or controlled by a computationally intensive depth function; (ii) the region is not transformation equivariant; (iii) ξ̂ nξ^n may not be uniquely defined. To resolve the above difficulties, we propose a one-dimensional pivot derived from the criterion function, and prove that its distribution can be consistently estimated by the mm out of nn bootstrap, or by a modified version of the perturbation bootstrap. This leads to a new method for constructing confidence regions which are transformation equivariant and have shapes driven solely by the criterion function. A subsampling procedure is proposed for selecting mm in practice. Empirical performance of the new method is illustrated with examples drawn from different nonstandard M-estimation settings. Extension of our theory to row-wise independent triangular arrays is also explored."]]></description>
<dc:subject>to:NB confidence_sets bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7252a9d94161/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1594972834">
    <title>Chen , Zhou : Robust inference via multiplier bootstrap</title>
    <dc:date>2020-11-18T22:42:34+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1594972834</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper investigates the theoretical underpinnings of two fundamental statistical inference problems, the construction of confidence sets and large-scale simultaneous hypothesis testing, in the presence of heavy-tailed data. With heavy-tailed observation noise, finite sample properties of the least squares-based methods, typified by the sample mean, are suboptimal both theoretically and empirically. In this paper, we demonstrate that the adaptive Huber regression, integrated with the multiplier bootstrap procedure, provides a useful robust alternative to the method of least squares. Our theoretical and empirical results reveal the effectiveness of the proposed method, and highlight the importance of having inference methods that are robust to heavy tailedness."]]></description>
<dc:subject>to:NB heavy_tails regression bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c728abbec666/</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:heavy_tails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1597370678">
    <title>Meyer , Paparoditis , Kreiss : Extending the validity of frequency domain bootstrap methods to general stationary processes</title>
    <dc:date>2020-11-18T21:45:05+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1597370678</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Existing frequency domain methods for bootstrapping time series have a limited range. Essentially, these procedures cover the case of linear time series with independent innovations, and some even require the time series to be Gaussian. In this paper we propose a new frequency domain bootstrap method—the hybrid periodogram bootstrap (HPB)—which is consistent for a much wider range of stationary, even nonlinear, processes and which can be applied to a large class of periodogram-based statistics. The HPB is designed to combine desirable features of different frequency domain techniques while overcoming their respective limitations. It is capable to imitate the weak dependence structure of the periodogram by invoking the concept of convolved subsampling in a novel way that is tailor-made for periodograms. We show consistency for the HPB procedure for a general class of stationary time series, ranging clearly beyond linear processes, and for spectral means and ratio statistics on which we mainly focus. The finite sample performance of the new bootstrap procedure is illustrated via simulations."]]></description>
<dc:subject>to:NB bootstrap fourier_analysis time_series statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3940b85192f9/</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:fourier_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.07664">
    <title>[2011.07664] Robust bootstrap prediction intervals for univariate and multivariate autoregressive time series models</title>
    <dc:date>2020-11-18T17:19:11+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.07664</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The bootstrap procedure has emerged as a general framework to construct prediction intervals for future observations in autoregressive time series models. Such models with outlying data points are standard in real data applications, especially in the field of econometrics. These outlying data points tend to produce high forecast errors, which reduce the forecasting performances of the existing bootstrap prediction intervals calculated based on non-robust estimators. In the univariate and multivariate autoregressive time series, we propose a robust bootstrap algorithm for constructing prediction intervals and forecast regions. The proposed procedure is based on the weighted likelihood estimates and weighted residuals. Its finite sample properties are examined via a series of Monte Carlo studies and two empirical data examples."]]></description>
<dc:subject>to:NB prediction bootstrap time_series to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:eef355e6ea71/</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:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<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://projecteuclid.org/euclid.ejs/1569895283">
    <title>El Ktaibi , Ivanoff : Bootstrapping the empirical distribution of a stationary process with change-point</title>
    <dc:date>2020-11-16T16:16:30+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.ejs/1569895283</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["When detecting a change-point in the marginal distribution of a stationary time series, bootstrap techniques are required to determine critical values for the tests when the pre-change distribution is unknown. In this paper, we propose a sequential moving block bootstrap and demonstrate its validity under a converging alternative. Furthermore, we demonstrate that power is still achieved by the bootstrap under a non-converging alternative. We follow the approach taken by Peligrad in [14], and avoid assumptions of mixing, association or near epoch dependence. These results are applied to a linear process and are shown to be valid under very mild conditions on the existence of any moment of the innovations and a corresponding condition of summability of the coefficients."]]></description>
<dc:subject>to:NB time_series change-point_problem bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9625106f5da9/</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:change-point_problem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2004.08935">
    <title>[2004.08935] On the Theoretical Properties of the Network Jackknife</title>
    <dc:date>2020-05-01T20:16:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2004.08935</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the properties of a leave-node-out jackknife procedure for network data. Under the sparse graphon model, we prove an Efron-Stein-type inequality, showing that the network jackknife leads to conservative estimates of the variance (in expectation) for any network functional that is invariant to node permutation. For a general class of count functionals, we also establish consistency of the network jackknife. We complement our theoretical analysis with a range of simulated and real-data examples and show that the network jackknife offers competitive performance in cases where other resampling methods are known to be valid. In fact, for several network statistics, we see that the jackknife provides more accurate inferences compared to related methods such as subsampling."]]></description>
<dc:subject>to:NB to_read network_data_analysis statistics bootstrap jackknife lunde.robert sarkar.purnamrita kith_and_kin re:network_bootstraps</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:66c9dce190b5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jackknife"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lunde.robert"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sarkar.purnamrita"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_bootstraps"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/biomet/article-abstract/106/4/781/5566518">
    <title>Bootstrapping spectral statistics in high dimensions | Biometrika | Oxford Academic</title>
    <dc:date>2019-12-02T14:07:21+00:00</dc:date>
    <link>https://academic.oup.com/biomet/article-abstract/106/4/781/5566518</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Statistics derived from the eigenvalues of sample covariance matrices are called spectral statistics, and they play a central role in multivariate testing. Although bootstrap methods are an established approach to approximating the laws of spectral statistics in low-dimensional problems, such methods are relatively unexplored in the high-dimensional setting. The aim of this article is to focus on linear spectral statistics as a class of prototypes for developing a new bootstrap in high dimensions, a method we refer to as the spectral bootstrap. In essence, the proposed method originates from the parametric bootstrap and is motivated by the fact that in high dimensions it is difficult to obtain a nonparametric approximation to the full data-generating distribution. From a practical standpoint, the method is easy to use and allows the user to circumvent the difficulties of complex asymptotic formulas for linear spectral statistics. In addition to proving the consistency of the proposed method, we present encouraging empirical results in a variety of settings. Lastly, and perhaps most interestingly, we show through simulations that the method can be applied successfully to statistics outside the class of linear spectral statistics, such as the largest sample eigenvalue and others."]]></description>
<dc:subject>to:NB spectral_methods bootstrap high-dimensional_statistics statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f1cec27767d9/</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:spectral_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:high-dimensional_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.09695">
    <title>[1910.09695] Confidence intervals centred on bootstrap smoothed estimators: an impossibility result</title>
    <dc:date>2019-10-24T13:59:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.09695</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recently, Kabaila and Wijethunga assessed the performance of a confidence interval centred on a bootstrap smoothed estimator, with width proportional to an estimator of Efron's delta method approximation to the standard deviation of this estimator. They used a testbed situation consisting of two nested linear regression models, with error variance assumed known, and model selection using a preliminary hypothesis test. This assessment was in terms of coverage and scaled expected length, where the scaling is with respect to the expected length of the usual confidence interval with the same minimum coverage probability. They found that this confidence interval has scaled expected length that (a) has a maximum value that may be much greater than 1 and (b) is greater than a number slightly less than 1 when the simpler model is correct. We therefore ask the following question. For a confidence interval, centred on the bootstrap smoothed estimator, does there exist a formula for its data-based width such that, in this testbed situation, it has the desired minimum coverage and scaled expected length that (a) has a maximum value that is not too much larger than 1 and (b) is substantially less than 1 when the simpler model is correct? Using a recent decision-theoretic performance bound due to Kabaila and Kong, it is shown that the answer to this question is `no' for a wide range of scenarios."]]></description>
<dc:subject>to:NB confidence_sets bootstrap smoothing statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2c70d1488b3a/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:smoothing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1909.02662">
    <title>[1909.02662] Block bootstrap optimality for density estimation with dependent data</title>
    <dc:date>2019-09-09T03:48:14+00:00</dc:date>
    <link>https://arxiv.org/abs/1909.02662</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Accurate approximation of the sampling distribution of nonparametric kernel density estimators is crucial for many statistical inference problems. Since these estimators have complex asymptotic distributions, bootstrap methods are often used for this purpose. With i.i.d. observations, a large literature exists concerning optimal bootstrap methods which achieve the fastest possible convergence rate of the bootstrap estimator of the sampling distribution of the kernel density estimator. With dependent data, such an optimality theory is an important open problem. We establish a general theory of optimality of the block bootstrap for kernel density estimation under weak dependence assumptions which are satisfied by many important time series models. We propose a unified framework for a theoretical study of a rich class of bootstrap methods which include as special cases subsampling, Kunsch's moving block bootstrap, Hall's under-smoothing (UNS) as well as approaches incorporating no (NBC) or explicit bias correction (EBC). Moreover, we consider their accuracy under a broad spectrum of choices of the bandwidth h, which include as an important special case the MSE-optimal choice, as well as other under-smoothed choices. Under each choice of h, we derive the optimal tuning parameters and compare optimal performances between the main subclasses (EBC, NBC, UNS) of the bootstrap methods."]]></description>
<dc:subject>to:NB bootstrap time_series density_estimation statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3a0b7b2a417e/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:density_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-economics-080218-025651">
    <title>Bootstrap Methods in Econometrics | Annual Review of Economics</title>
    <dc:date>2019-08-26T23:51:42+00:00</dc:date>
    <link>https://www.annualreviews.org/doi/abs/10.1146/annurev-economics-080218-025651</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The bootstrap is a method for estimating the distribution of an estimator or test statistic by resampling one's data or a model estimated from the data. Under conditions that hold in a wide variety of econometric applications, the bootstrap provides approximations to distributions of statistics, coverage probabilities of confidence intervals, and rejection probabilities of hypothesis tests that are more accurate than the approximations of first-order asymptotic distribution theory. The reductions in the differences between true and nominal coverage or rejection probabilities can be very large. In addition, the bootstrap provides a way to carry out inference in certain settings where obtaining analytic distributional approximations is difficult or impossible. This article explains the usefulness and limitations of the bootstrap in contexts of interest in econometrics. The presentation is informal and expository. It provides an intuitive understanding of how the bootstrap works. Mathematical details are available in the references that are cited."]]></description>
<dc:subject>to:NB bootstrap statistics economics to_teach:undergrad-ADA horowitz.joel</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5aff30353151/</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:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:horowitz.joel"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.03180">
    <title>[1810.03180] Simple Inference on Functionals of Set-Identified Parameters Defined by Linear Moments</title>
    <dc:date>2019-08-20T14:15:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.03180</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper considers uniformly valid (over a class of data generating processes) inference for linear functionals of partially identified parameters in cases where the identified set is defined by linear (in the parameter) moment inequalities. We propose a bootstrap procedure for constructing uniformly valid confidence sets for a linear functional of a partially identified parameter. The proposed method amounts to bootstrapping the value functions of a linear optimization problem, and subsumes subvector inference as a special case. In other words, this paper shows the conditions under which naively bootstrapping a linear program can be used to construct a confidence set with uniform correct coverage for a partially identified linear functional. Unlike other proposed subvector inference procedures, our procedure does not require the researcher to repeatedly invert a hypothesis test, and is extremely computationally efficient."]]></description>
<dc:subject>to:NB partial_identification confidence_sets linear_programming bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:33650c4ac218/</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:partial_identification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</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/1907.12116">
    <title>[1907.12116] A Higher-Order Swiss Army Infinitesimal Jackknife</title>
    <dc:date>2019-07-30T17:29:21+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.12116</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Cross validation (CV) and the bootstrap are ubiquitous model-agnostic tools for assessing the error or variability of machine learning and statistical estimators. However, these methods require repeatedly re-fitting the model with different weighted versions of the original dataset, which can be prohibitively time-consuming. For sufficiently regular optimization problems the optimum depends smoothly on the data weights, and so the process of repeatedly re-fitting can be approximated with a Taylor series that can be often evaluated relatively quickly. The first-order approximation is known as the "infinitesimal jackknife" in the statistics literature and has been the subject of recent interest in machine learning for approximate CV. In this work, we consider high-order approximations, which we call the "higher-order infinitesimal jackknife" (HOIJ). Under mild regularity conditions, we provide a simple recursive procedure to compute approximations of all orders with finite-sample accuracy bounds. Additionally, we show that the HOIJ can be efficiently computed even in high dimensions using forward-mode automatic differentiation. We show that a linear approximation with bootstrap weights approximation is equivalent to those provided by asymptotic normal approximations. Consequently, the HOIJ opens up the possibility of enjoying higher-order accuracy properties of the bootstrap using local approximations. Consistency of the HOIJ for leave-one-out CV under different asymptotic regimes follows as corollaries from our finite-sample bounds under additional regularity assumptions. The generality of the computation and bounds motivate the name "higher-order Swiss Army infinitesimal jackknife.""]]></description>
<dc:subject>to:NB cross-validation bootstrap jackknife statistics jordan.michael_i.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:173b851e114d/</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:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jackknife"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jordan.michael_i."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.ejs/1561687408">
    <title>Cheng , Chen : Nonparametric inference via bootstrapping the debiased estimator</title>
    <dc:date>2019-07-04T09:44:55+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.ejs/1561687408</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we propose to construct confidence bands by bootstrapping the debiased kernel density estimator (for density estimation) and the debiased local polynomial regression estimator (for regression analysis). The idea of using a debiased estimator was recently employed by Calonico et al. (2018b) to construct a confidence interval of the density function (and regression function) at a given point by explicitly estimating stochastic variations. We extend their ideas of using the debiased estimator and further propose a bootstrap approach for constructing simultaneous confidence bands. This modified method has an advantage that we can easily choose the smoothing bandwidth from conventional bandwidth selectors and the confidence band will be asymptotically valid. We prove the validity of the bootstrap confidence band and generalize it to density level sets and inverse regression problems. Simulation studies confirm the validity of the proposed confidence bands/sets. We apply our approach to an Astronomy dataset to show its applicability."]]></description>
<dc:subject>to:NB to_read statistics bootstrap confidence_sets regression density_estimation re:ADAfaEPoV</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:25365e040388/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:density_estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11222-016-9655-0">
    <title>Multiplier bootstrap methods for conditional distributions | SpringerLink</title>
    <dc:date>2019-05-30T23:58:32+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11222-016-9655-0</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The multiplier bootstrap is a fast and easy-to-implement alternative to the standard bootstrap; it has been used successfully in many statistical contexts. In this paper, resampling methods based on multipliers are proposed in a general framework where one investigates the stochastic behavior of a random vector  𝐘∈ℝ𝑑Y∈Rd conditional on a covariate  𝑋∈ℝX∈R. Specifically, two versions of the multiplier bootstrap adapted to empirical conditional distributions are introduced as alternatives to the conditional bootstrap and their asymptotic validity is formally established. As the method walks hand-in-hand with the functional delta method, theory around the estimation of statistical functionals is developed accordingly; this includes the interval estimation of conditional mean and variance, conditional correlation coefficient, Kendall’s dependence measure and copula. Composite inference about univariate and joint conditional distributions is also considered. The sample behavior of the new bootstrap schemes and related estimation methods are investigated via simulations and an illustration on real data is provided."]]></description>
<dc:subject>to:NB bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:66b063adcabd/</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:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://academic.oup.com/biomet/article-abstract/106/2/385/5431311">
    <title>Bootstrap of residual processes in regression: to smooth or not to smooth? | Biometrika | Oxford Academic</title>
    <dc:date>2019-05-25T02:56:33+00:00</dc:date>
    <link>https://academic.oup.com/biomet/article-abstract/106/2/385/5431311</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper we consider regression models with centred errors, independent of the covariates. Given independent and identically distributed data and given an estimator of the regression function, which can be parametric or nonparametric in nature, we estimate the distribution of the error term by the empirical distribution of estimated residuals. To approximate the distribution of this estimator, Koul & Lahiri (1994) and Neumeyer (2009) proposed bootstrap procedures based on smoothing the residuals before drawing bootstrap samples. So far it has been an open question as to whether a classical nonsmooth residual bootstrap is asymptotically valid in this context. Here we solve this open problem and show that the nonsmooth residual bootstrap is consistent. We illustrate the theoretical result by means of simulations, which demonstrate the accuracy of this bootstrap procedure for various models, testing procedures and sample sizes."]]></description>
<dc:subject>to:NB regression bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9241b1e768e5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1903.05403">
    <title>[1903.05403] Nonparametric estimation and bootstrap inference on trends in atmospheric time series: an application to ethane</title>
    <dc:date>2019-04-11T00:28:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1903.05403</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Understanding the development of trends and identifying trend reversals in decadal time series is becoming more and more important. Many climatological and atmospheric time series are characterized by autocorrelation, heteroskedasticity and seasonal effects. Additionally, missing observations due to instrument failure or unfavorable measurement conditions are common in such series. This is why it is crucial to apply methods which work reliably under these circumstances. The goal of this paper is to provide a toolbox which can be used to determine the presence and form of changes in trend functions using parametric as well as nonparametric techniques. We consider bootstrap inference on broken linear trends and smoothly varying nonlinear trends. In particular, for the broken trend model, we propose a bootstrap method for inference on the break location and the corresponding changes in slope. For the smooth trend model we construct simultaneous confidence bands around the nonparametrically estimated trend. Our autoregressive wild bootstrap approach combined with a seasonal filter, is able to handle all issues mentioned above. We apply our methods to a set of atmospheric ethane series with a focus on the measurements obtained above the Jungfraujoch in the Swiss Alps. Ethane is the most abundant non-methane hydrocarbon in the Earth's atmosphere, an important precursor of tropospheric ozone and a good indicator of oil and gas production as well as transport. Its monitoring is therefore crucial for the characterization of air quality and of the transport of tropospheric pollution."]]></description>
<dc:subject>to:NB time_series climatology bootstrap nonparametrics to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:56c9c3770b8b/</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:climatology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<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/1608.00696">
    <title>[1608.00696] Can we trust the bootstrap in high-dimension?</title>
    <dc:date>2019-02-18T14:59:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.00696</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the performance of the bootstrap in high-dimensions for the setting of linear regression, where p<n but p/n is not close to zero. We consider ordinary least-squares as well as robust regression methods and adopt a minimalist performance requirement: can the bootstrap give us good confidence intervals for a single coordinate of β? (where β is the true regression vector). 
"We show through a mix of numerical and theoretical work that the bootstrap is fraught with problems. Both of the most commonly used methods of bootstrapping for regression -- residual bootstrap and pairs bootstrap -- give very poor inference on β as the ratio p/n grows. We find that the residuals bootstrap tend to give anti-conservative estimates (inflated Type I error), while the pairs bootstrap gives very conservative estimates (severe loss of power) as the ratio p/n grows. We also show that the jackknife resampling technique for estimating the variance of β̂  severely overestimates the variance in high dimensions. 
"We contribute alternative bootstrap procedures based on our theoretical results that mitigate these problems. However, the corrections depend on assumptions regarding the underlying data-generation model, suggesting that in high-dimensions it may be difficult to have universal, robust bootstrapping techniques."]]></description>
<dc:subject>to:NB bootstrap high-dimensional_statistics statistics regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6b6a93c94afb/</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:high-dimensional_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1305292042">
    <title>Kirch , Politis : TFT-bootstrap: Resampling time series in the frequency domain to obtain replicates in the time domain</title>
    <dc:date>2018-09-12T13:37:23+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1305292042</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A new time series bootstrap scheme, the time frequency toggle (TFT)-bootstrap, is proposed. Its basic idea is to bootstrap the Fourier coefficients of the observed time series, and then to back-transform them to obtain a bootstrap sample in the time domain. Related previous proposals, such as the “surrogate data” approach, resampled only the phase of the Fourier coefficients and thus had only limited validity. By contrast, we show that the appropriate resampling of phase and magnitude, in addition to some smoothing of Fourier coefficients, yields a bootstrap scheme that mimics the correct second-order moment structure for a large class of time series processes. As a main result we obtain a functional limit theorem for the TFT-bootstrap under a variety of popular ways of frequency domain bootstrapping. Possible applications of the TFT-bootstrap naturally arise in change-point analysis and unit-root testing where statistics are frequently based on functionals of partial sums. Finally, a small simulation study explores the potential of the TFT-bootstrap for small samples showing that for the discussed tests in change-point analysis as well as unit-root testing, it yields better results than the corresponding asymptotic tests if measured by size and power."]]></description>
<dc:subject>to:NB bootstrap time_series fourier_analysis statistics to_teach:data_over_space_and_time re:stacs</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:72f715bcaea3/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fourier_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:stacs"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11222-016-9717-3">
    <title>Bootstrap bias corrections for ensemble methods | SpringerLink</title>
    <dc:date>2018-05-23T13:24:46+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11222-016-9717-3</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper examines the use of a residual bootstrap for bias correction in machine learning regression methods. Accounting for bias is an important obstacle in recent efforts to develop statistical inference for machine learning. We demonstrate empirically that the proposed bootstrap bias correction can lead to substantial improvements in both bias and predictive accuracy. In the context of ensembles of trees, we show that this correction can be approximated at only double the cost of training the original ensemble. Our method is shown to improve test set accuracy over random forests by up to 70% on example problems from the UCI repository."]]></description>
<dc:subject>ensemble_methods prediction bootstrap hooker.giles statistics to:NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:67009f3757f3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hooker.giles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s11222-016-9712-8?">
    <title>Bootstrap methods for stationary functional time series | SpringerLink</title>
    <dc:date>2018-05-23T13:21:25+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s11222-016-9712-8?</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Bootstrap methods for estimating the long-run covariance of stationary functional time series are considered. We introduce a versatile bootstrap method that relies on functional principal component analysis, where principal component scores can be bootstrapped by maximum entropy. Two other bootstrap methods resample error functions, after the dependence structure being modeled linearly by a sieve method or nonlinearly by a functional kernel regression. Through a series of Monte-Carlo simulation, we evaluate and compare the finite-sample performances of these three bootstrap methods for estimating the long-run covariance in a functional time series. Using the intraday particulate matter (  PM10PM10 ) dataset in Graz, the proposed bootstrap methods provide a way of constructing the distribution of estimated long-run covariance for functional time series."]]></description>
<dc:subject>to:NB bootstrap time_series functional_data_analysis statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c661a9b0febb/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:functional_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nature.com/articles/s41586-018-0043-0">
    <title>Renewing Felsenstein’s phylogenetic bootstrap in the era of big data | Nature</title>
    <dc:date>2018-05-07T17:06:07+00:00</dc:date>
    <link>https://www.nature.com/articles/s41586-018-0043-0</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Felsenstein’s application of the bootstrap method to evolutionary trees is one of the most cited scientific papers of all time. The bootstrap method, which is based on resampling and replications, is used extensively to assess the robustness of phylogenetic inferences. However, increasing numbers of sequences are now available for a wide variety of species, and phylogenies based on hundreds or thousands of taxa are becoming routine. With phylogenies of this size Felsenstein’s bootstrap tends to yield very low supports, especially on deep branches. Here we propose a new version of the phylogenetic bootstrap in which the presence of inferred branches in replications is measured using a gradual ‘transfer’ distance rather than the binary presence or absence index used in Felsenstein’s original version. The resulting supports are higher and do not induce falsely supported branches. The application of our method to large mammal, HIV and simulated datasets reveals their phylogenetic signals, whereas Felsenstein’s bootstrap fails to do so."]]></description>
<dc:subject>to:NB statistics evolutionary_biology phylogenetics bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9d5bc113ba1d/</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:evolutionary_biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:phylogenetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12296">
    <title>Estimating MA Parameters through Factorization of the Autocovariance Matrix and an MA‐Sieve Bootstrap - McMurry - 2018 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2018-05-07T16:53:17+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12296</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A new method to estimate the moving‐average (MA) coefficients of a stationary time series is proposed. The new approach is based on the modified Cholesky factorization of a consistent estimator of the autocovariance matrix. Convergence rates are established, and the new estimates are used to implement an MA‐type sieve bootstrap. Finite‐sample simulations corroborate the good performance of the proposed methodology."]]></description>
<dc:subject>to:NB time_series bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d8140e18e7d3/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.05401">
    <title>[1611.05401] Bootstrapping and Sample Splitting For High-Dimensional, Assumption-Free Inference</title>
    <dc:date>2018-04-05T15:06:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.05401</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Several new methods have been proposed for performing valid inference after model selection. An older method is sampling splitting: use part of the data for model selection and part for inference. In this paper we revisit sample splitting combined with the bootstrap (or the Normal approximation). We show that this leads to a simple, assumption-free approach to inference and we establish results on the accuracy of the method. In fact, we find new bounds on the accuracy of the bootstrap and the Normal approximation for general nonlinear parameters with increasing dimension which we then use to assess the accuracy of regression inference. We show that an alternative, called the image bootstrap, has higher coverage accuracy at the cost of more computation. We define new parameters that measure variable importance and that can be inferred with greater accuracy than the usual regression coefficients. There is a inference-prediction tradeoff: splitting increases the accuracy and robustness of inference but can decrease the accuracy of the predictions."]]></description>
<dc:subject>to:NB heard_the_talk linear_regression model_selection bootstrap kith_and_kin wasserman.larry rinaldo.alessandro g'sell.max lei.jing high-dimensional_statistics statistics to_teach:linear_models post-selection_inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7ccbe54bc5d5/</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:heard_the_talk"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wasserman.larry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:rinaldo.alessandro"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:g'sell.max"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lei.jing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:high-dimensional_statistics"/>
	<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:li rdf:resource="https://pinboard.in/u:cshalizi/t:post-selection_inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12275/abstract">
    <title>Extending the Range of Validity of the Autoregressive (Sieve) Bootstrap - Fragkeskou - 2017 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2018-01-24T23:22:20+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12275/abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Two modifications of the autoregressive-sieve and of the autoregressive bootstrap are proposed. The first modification replaces the classical i.i.d. resampling scheme applied to the residuals of the autoregressive fit by the generation of i.i.d. wild pseudo-innovations that appropriately mimic to the appropriate extent, also the fourth-order moment structure of the true innovations driving the underlying linear process. This modification extends the validity of the autoregressive-sieve bootstrap to classes of statistics for which the classical residual-based autoregressive-sieve bootstrap fails. In the second modification, an autoregressive bootstrap applied to an appropriately transformed time series is proposed, which, together with a dependent wild-type generation of pseudo-innovations, delivers a bootstrap procedure that is valid for large classes of statistics and for stochastic processes satisfying quite general, weak, dependent conditions. A fully data-driven selection of the bootstrap parameters involved in both modifications is proposed, and extensive simulations, including comparisons with alternative bootstrap methods, show a good finite sample performance of the proposed bootstrap procedures."]]></description>
<dc:subject>to:NB bootstrap time_series statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:be68501a0d78/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12270/abstract">
    <title>Oracle Properties, Bias Correction, and Bootstrap Inference for Adaptive Lasso for Time Series M-Estimators - Audrino - 2017 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2017-12-01T15:22:32+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12270/abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We derive new theoretical results on the properties of the adaptive least absolute shrinkage and selection operator (adaptive lasso) for possibly nonlinear time series models. In particular, we investigate the question of how to conduct inference on the parameters given an adaptive lasso model. Central to this study is the test of the hypothesis that a given adaptive lasso parameter equals zero, which therefore tests for a false positive. To this end, we introduce a recentered bootstrap procedure and show, theoretically and empirically through extensive Monte Carlo simulations, that the adaptive lasso can combine efficient parameter estimation, variable selection, and inference in one step. Moreover, we analytically derive a bias correction factor that is able to significantly improve the empirical coverage of the test on the active variables. Finally, we apply the adaptive lasso and the recentered bootstrap procedure to investigate the relation between the short rate dynamics and the economy, thereby providing a statistical foundation (from a model choice perspective) for the classic Taylor rule monetary policy model."

--- The bit about the Taylor rule is just dumb, but let it slide.]]></description>
<dc:subject>to:NB statistics time_series hypothesis_testing bootstrap lasso</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a24d51c8e62f/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lasso"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.02834">
    <title>[1711.02834] Bootstrapping Generalization Error Bounds for Time Series</title>
    <dc:date>2017-11-09T13:18:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.02834</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the problem of finding confidence intervals for the risk of forecasting the future of a stationary, ergodic stochastic process, using a model estimated from the past of the process. We show that a bootstrap procedure provides valid confidence intervals for the risk, when the data source is sufficiently mixing, and the loss function and the estimator are suitably smooth. Autoregressive (AR(d)) models estimated by least squares obey the necessary regularity conditions, even when mis-specified, and simulations show that the finite- sample coverage of our bounds quickly converges to the theoretical, asymptotic level. As an intermediate step, we derive sufficient conditions for asymptotic independence between empirical distribution functions formed by splitting a realization of a stochastic process, of independent interest."]]></description>
<dc:subject>in_NB time_series bootstrap statistics self-promotion to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9fe5b8c32f46/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:self-promotion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.00813">
    <title>[1711.00813] Bootstrapping Exchangeable Random Graphs</title>
    <dc:date>2017-11-06T18:29:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.00813</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce two new bootstraps for exchangeable random graphs. One, the "empirical graphon", is based purely on resampling, while the other, the "histogram stochastic block model", is a model-based "sieve" bootstrap. We show that both of them accurately approximate the sampling distributions of motif densities, i.e., of the normalized counts of the number of times fixed subgraphs appear in the network. These densities characterize the distribution of (infinite) exchangeable networks. Our bootstraps therefore give, for the first time, a valid quantification of uncertainty in inferences about fundamental network statistics, and so of parameters identifiable from them."]]></description>
<dc:subject>in_NB network_data_analysis statistics bootstrap graph_limits nonparametrics self-promotion to:blog re:network_bootstraps</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1f868b9c88d0/</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:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graph_limits"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:self-promotion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_bootstraps"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12256/abstract">
    <title>Block Bootstrap for the Empirical Process of Long-Range Dependent Data - Tewes - 2017 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2017-10-12T23:22:20+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12256/abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the bootstrapped empirical process of long-range dependent data. It is shown that this process converges to a semi-degenerate limit, where the random part of this limit is always Gaussian. Thus the bootstrap might fail when the original empirical process accomplishes a noncentral limit theorem. However, even in this case our results can be used to estimate a nuisance parameter that appears in the limit of many nonparametric tests under long memory. Moreover, we develop a new resampling procedure for goodness-of-fit tests and a test for monotonicity of transformations."]]></description>
<dc:subject>stochastic_processes time_series statistics bootstrap empirical_processes long-range_dependence in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ac0214bb2adb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:long-range_dependence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12221/abstract">
    <title>Oracle M-Estimation for Time Series Models - Giurcanu - 2016 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2017-04-04T13:16:54+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12221/abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a thresholding M-estimator for multivariate time series. Our proposed estimator has the oracle property that its large-sample properties are the same as of the classical M-estimator obtained under the a priori information that the zero parameters were known. We study the consistency of the standard block bootstrap, the centred block bootstrap and the empirical likelihood block bootstrap distributions of the proposed M-estimator. We develop automatic selection procedures for the thresholding parameter and for the block length of the bootstrap methods. We present the results of a simulation study of the proposed methods for a sparse vector autoregressive VAR(2) time series model. The analysis of two real-world data sets illustrate applications of the methods in practice."]]></description>
<dc:subject>bootstrap time_series statistics estimation in_NB sparsity variable_selection high-dimensional_statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7728d02c1d9a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<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:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sparsity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:variable_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:high-dimensional_statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/113/51/14668.abstract">
    <title>Estimating uncertainty in respondent-driven sampling using a tree bootstrap method</title>
    <dc:date>2016-12-28T02:35:06+00:00</dc:date>
    <link>http://www.pnas.org/content/113/51/14668.abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Respondent-driven sampling (RDS) is a network-based form of chain-referral sampling used to estimate attributes of populations that are difficult to access using standard survey tools. Although it has grown quickly in popularity since its introduction, the statistical properties of RDS estimates remain elusive. In particular, the sampling variability of these estimates has been shown to be much higher than previously acknowledged, and even methods designed to account for RDS result in misleadingly narrow confidence intervals. In this paper, we introduce a tree bootstrap method for estimating uncertainty in RDS estimates based on resampling recruitment trees. We use simulations from known social networks to show that the tree bootstrap method not only outperforms existing methods but also captures the high variability of RDS, even in extreme cases with high design effects. We also apply the method to data from injecting drug users in Ukraine. Unlike other methods, the tree bootstrap depends only on the structure of the sampled recruitment trees, not on the attributes being measured on the respondents, so correlations between attributes can be estimated as well as variability. Our results suggest that it is possible to accurately assess the high level of uncertainty inherent in RDS."]]></description>
<dc:subject>to:NB network_data_analysis bootstrap statistics respondent-driven_sampling mccormick.tyler_h. to_read to_teach:baby-nets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e51f59f95394/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:respondent-driven_sampling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mccormick.tyler_h."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:baby-nets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1311.4555">
    <title>[1311.4555] Confidence Intervals for Random Forests: The Jackknife and the Infinitesimal Jackknife</title>
    <dc:date>2016-12-04T21:31:22+00:00</dc:date>
    <link>https://arxiv.org/abs/1311.4555</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the variability of predictions made by bagged learners and random forests, and show how to estimate standard errors for these methods. Our work builds on variance estimates for bagging proposed by Efron (1992, 2012) that are based on the jackknife and the infinitesimal jackknife (IJ). In practice, bagged predictors are computed using a finite number B of bootstrap replicates, and working with a large B can be computationally expensive. Direct applications of jackknife and IJ estimators to bagging require B on the order of n^{1.5} bootstrap replicates to converge, where n is the size of the training set. We propose improved versions that only require B on the order of n replicates. Moreover, we show that the IJ estimator requires 1.7 times less bootstrap replicates than the jackknife to achieve a given accuracy. Finally, we study the sampling distributions of the jackknife and IJ variance estimates themselves. We illustrate our findings with multiple experiments and simulation studies."]]></description>
<dc:subject>to:NB bootstrap confidence_sets ensemble_methods random_forests decision_trees statistics nonparametrics efron.bradley hastie.trevor</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7e987d8e279f/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_forests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:decision_trees"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:efron.bradley"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hastie.trevor"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1311.5828">
    <title>[1311.5828] The Splice Bootstrap</title>
    <dc:date>2016-12-01T20:11:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1311.5828</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper proposes a new bootstrap method to compute predictive intervals for nonlinear autoregressive time series model forecast. This method we call the splice boobstrap as it involves splicing the last p values of a given series to a suitably simulated series. This ensures that each simulated series will have the same set of p time series values in common, a necessary requirement for computing conditional predictive intervals. Using simulation studies we show the methods gives 90% intervals intervals that are similar to those expected from theory for simple linear and SETAR model driven by normal and non-normal noise. Furthermore, we apply the method to some economic data and demonstrate the intervals compare favourably with cross-validation based intervals."]]></description>
<dc:subject>to:NB bootstrap time_series statistics prediction to_teach:undergrad-ADA re:ADAfaEPoV to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dfb04235bd35/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12214/abstract">
    <title>On the Consistency of Bootstrap Testing for a Parameter on the Boundary of the Parameter Space - Cavaliere - 2016 - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2016-11-24T23:59:02+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.1111/jtsa.12214/abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["It is well known that with a parameter on the boundary of the parameter space, such as in the classic cases of testing for a zero location parameter or no autoregressive conditional heteroskedasticity (ARCH) effects, the classic nonparametric bootstrap – based on unrestricted parameter estimates – leads to inconsistent testing. In contrast, we show here that for the two aforementioned cases, a nonparametric bootstrap test based on parameter estimates obtained under the null – referred to as ‘restricted bootstrap’ – is indeed consistent. While the restricted bootstrap is simple to implement in practice, novel theoretical arguments are required in order to establish consistency. In particular, since the bootstrap is analysed both under the null hypothesis and under the alternative, non-standard asymptotic expansions are required to deal with parameters on the boundary. Detailed proofs of the asymptotic validity of the restricted bootstrap are given and, for the leading case of testing for no ARCH, a Monte Carlo study demonstrates that the bootstrap quasi-likelihood ratio statistic performs extremely well in terms of empirical size and power for even remarkably small samples, outperforming the standard and bootstrap Lagrange multiplier tests as well as the asymptotic quasi-likelihood ratio test."]]></description>
<dc:subject>to:NB bootstrap hypothesis_testing statistics time_series</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:99ed3b7734f5/</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:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.mlgworkshop.org/2016/paper/MLG2016_paper_32.pdf">
    <title>Fast Patchwork Bootstrap for Quantifying Estimation Uncertainties in Sparse Random Networks</title>
    <dc:date>2016-07-25T02:30:23+00:00</dc:date>
    <link>http://www.mlgworkshop.org/2016/paper/MLG2016_paper_32.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a new method of nonparametric bootstrap to quantify estimation uncertainties in large and possibly sparse random networks. The method is tailored for inference on functions of network degree distribution, under the assump- tion that both network degree distribution and network or- der are unknown. The key idea is based on adaptation of the “blocking” argument, developed for bootstrapping of time series and re-tiling of spatial data, to random networks. We sample network blocks (patches) and bootstrap the data within these patches. To select an optimal patch size, we de- velop a new computationally efficient and data-driven cross- validation algorithm. The proposed fast patchwork boot- strap (FPB) methodology further extends the ideas devel- oped by [33] for a case of network mean degree, to infer- ence on a degree distribution. In addition, the FPB is sub- stantially less computationally expensive, requires less in- formation on a graph, and is free from nuisance parame- ters. In our simulation study, we show that the new boot- strap method outperforms competing approaches by pro- viding sharper and better calibrated confidence intervals for functions of a network degree distribution than other avail- able approaches. We illustrate the FPB in application to a study of the Erdo ̈s collaboration network."]]></description>
<dc:subject>to:NB to_read bootstrap network_data_analysis re:network_bootstraps</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a41343c28c94/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:network_bootstraps"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://projecteuclid.org/euclid.aos/1176348120">
    <title>Hardle , Marron : Bootstrap Simultaneous Error Bars for Nonparametric Regression</title>
    <dc:date>2016-04-16T13:09:08+00:00</dc:date>
    <link>http://projecteuclid.org/euclid.aos/1176348120</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Simultaneous error bars are constructed for nonparametric kernel estimates of regression functions. The method is based on the bootstrap, where resampling is done from a suitably estimated residual distribution. The error bars are seen to give asymptotically correct coverage probabilities uniformly over any number of gridpoints. Applications to an economic problem are given and comparison to both pointwise and Bonferroni-type bars is presented through a simulation study."]]></description>
<dc:subject>to:NB to_read bootstrap confidence_sets regression nonparametrics statistics to_teach:undergrad-ADA re:ADAfaEPoV</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9e19fec0ab4c/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:ADAfaEPoV"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://link.springer.com/article/10.1007/s11203-015-9120-2?wt_mc=alerts.TOCjournals">
    <title>Blockwise bootstrap of the estimated empirical process based on psi -weakly dependent observations - Springer</title>
    <dc:date>2016-03-14T18:13:05+00:00</dc:date>
    <link>http://link.springer.com/article/10.1007/s11203-015-9120-2?wt_mc=alerts.TOCjournals</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The distributional convergence of the bootstrapped estimated empirical process is shown and bootstrap consistency in the sup-norm for test statistics based on that process. Bootstrapping the estimated empirical process has up to now been considered by assuming independence of the observations, where we give up this assumption now and allow the observations to be ψ-weakly dependent in the sense of Doukhan and Louhichi (Stoch Proc Appl 84:313–342, 1999). Due to the fact that no model assumptions on the original process are made, a nonparametric blockwise bootstrap procedure is used, which has previously been used in empirical process theory based on mixing observations. Here, we succeeded in proving that assuming l=o(n) and l→∞ as only conditions for the blocklength is sufficient to show convergence of the bootstrap process to the same limit as for the original process under H0, which is the weakest condition that has been imposed in that context up to now."]]></description>
<dc:subject>to:NB empirical_processes bootstrap mixing stochastic_processes statistical_inference_for_stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5a3cc34601d4/</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:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1601.00934">
    <title>[1601.00934] Confidence Intervals for Projections of Partially Identified Parameters</title>
    <dc:date>2016-02-09T03:08:03+00:00</dc:date>
    <link>http://arxiv.org/abs/1601.00934</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper proposes a bootstrap-based procedure to build confidence intervals for single components of a partially identified parameter vector, and for smooth functions of such components, in moment (in)equality models. The extreme points of our confidence interval are obtained by maximizing/minimizing the value of the component (or function) of interest subject to the sample analog of the moment (in)equality conditions properly relaxed. The novelty is that the amount of relaxation, or critical level, is computed so that the component of θ, instead of θ itself, is uniformly asymptotically covered with prespecified probability. Calibration of the critical level is based on repeatedly checking feasibility of linear programming problems, rendering it computationally attractive. Computation of the extreme points of the confidence interval is based on a novel application of the response surface method for global optimization, which may prove of independent interest also for applications of other methods of inference in the moment (in)equalities literature. The critical level is by construction smaller (in finite sample) than the one used if projecting confidence regions designed to cover the entire parameter vector θ. Hence, our confidence interval is weakly shorter than the projection of established confidence sets (Andrews and Soares, 2010), if one holds the choice of tuning parameters constant. We provide simple conditions under which the comparison is strict. Our inference method controls asymptotic coverage uniformly over a large class of data generating processes. Our assumptions and those used in the leading alternative approach (a profiling based method) are not nested. We explain why we employ some restrictions that are not required by other methods and provide examples of models for which our method is uniformly valid but profiling based methods are not."]]></description>
<dc:subject>to:NB statistics confidence_sets partial_identification bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b2a50b9ded6f/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:partial_identification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://onlinelibrary.wiley.com/doi/10.3982/ECTA6474/abstract">
    <title>On the Failure of the Bootstrap for Matching Estimators - Abadie - 2008 - Econometrica - Wiley Online Library</title>
    <dc:date>2016-02-08T19:27:27+00:00</dc:date>
    <link>http://onlinelibrary.wiley.com/doi/10.3982/ECTA6474/abstract</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Matching estimators are widely used in empirical economics for the evaluation of programs or treatments. Researchers using matching methods often apply the bootstrap to calculate the standard errors. However, no formal justification has been provided for the use of the bootstrap in this setting. In this article, we show that the standard bootstrap is, in general, not valid for matching estimators, even in the simple case with a single continuous covariate where the estimator is root-N consistent and asymptotically normally distributed with zero asymptotic bias. Valid inferential methods in this setting are the analytic asymptotic variance estimator of Abadie and Imbens (2006a) as well as certain modifications of the standard bootstrap, like the subsampling methods in Politis and Romano (1994)."

--- Need to re-read this carefully, to see exactly what bootstrap they're using and so how generic the result really is.]]></description>
<dc:subject>to:NB bootstrap causal_inference have_read statistics imbens.guido_w.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dc3ae776f202/</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:causal_inference"/>
	<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:imbens.guido_w."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.05034">
    <title>[1507.05034] Bootstrap tuning in ordered model selection</title>
    <dc:date>2015-08-05T22:33:31+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.05034</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In the problem of model selection for a given family of linear estimators, ordered by their variance, we offer a new "smallest accepted" approach motivated by Lepski's method and multiple testing theory. The procedure selects the smallest model which satisfies an acceptance rule based on comparison with all larger models. The method is completely data-driven and does not use any prior information about the variance structure of the noise: its parameters are adjusted to the underlying possibly heterogeneous noise by the so-called "propagation condition" using a wild bootstrap method. The validity of the bootstrap calibration is proved for finite samples with an explicit error bound. We provide a comprehensive theoretical study of the method and describe in detail the set of possible values of the selector \( \hat{m} \). We also establish some precise oracle error bounds for the corresponding estimator \( \hat{\theta} = \tilde{\theta}_{\hat{m}} \) which equally applies to estimation of the whole parameter vectors, some subvector or linear mapping, as well as the estimation of a linear functional."]]></description>
<dc:subject>to:NB model_selection bootstrap statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7f50ca69768a/</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:model_selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jstor.org/stable/1390820">
    <title>Model Search by Bootstrap &quot;Bumping&quot; on JSTOR</title>
    <dc:date>2015-07-14T13:21:34+00:00</dc:date>
    <link>http://www.jstor.org/stable/1390820</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a bootstrap-based method for enhancing a search through a space of models. The technique is well suited to complex, adaptively fitted models--it provides a convenient method for finding better local minima and for resistant fitting. Applications to regression, classification, and density estimation are described. We also provide results on the asymptotic behavior of bumping estimates."]]></description>
<dc:subject>to:NB estimation bootstrap statistics tibshirani.robert</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:df562750f5fd/</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:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tibshirani.robert"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1506.02326">
    <title>[1506.02326] Estimation of the variance of partial sums of dependent processes</title>
    <dc:date>2015-07-14T09:59:54+00:00</dc:date>
    <link>http://arxiv.org/abs/1506.02326</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study subsampling estimators for the limit variance
σ2=Var(X1)+2∑k=2∞Cov(X1,Xk)
of partial sums of a stationary stochastic process (Xk)k≥1. We establish L2-consistency of a non-overlapping block resampling method. Our results apply to processes that can be represented as functionals of strongly mixing processes. Motivated by recent applications to rank tests, we also study estimators for the series Var(F(X1))+2∑∞k=2Cov(F(X1),F(Xk)), where F is the distribution function of X1. Simulations illustrate the usefulness of the proposed estimators and of a mean squared error optimal rule for the choice of the block length."]]></description>
<dc:subject>to:NB statistics time_series variance_estimation bootstrap</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2f6dcb882af5/</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:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:variance_estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1506.05779">
    <title>[1506.05779] Simultaneous likelihood-based bootstrap confidence sets for a large number of models</title>
    <dc:date>2015-07-14T09:52:45+00:00</dc:date>
    <link>http://arxiv.org/abs/1506.05779</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The paper studies a problem of constructing simultaneous likelihood-based confidence sets. We consider a simultaneous multiplier bootstrap procedure for estimating the quantiles of the joint distribution of the likelihood ratio statistics, and for adjusting the confidence level for multiplicity. Theoretical results state the bootstrap validity in the following setting: the sample size \(n\) is fixed, the maximal parameter dimension \(p_{\textrm{max}}\) and the number of considered parametric models \(K\) are s.t. \((\log K)^{12}p_{\max}^{3}/n\) is small. We also consider the situation when the parametric models are misspecified. If the models' misspecification is significant, then the bootstrap critical values exceed the true ones and the simultaneous bootstrap confidence set becomes conservative. Numerical experiments for local constant and local quadratic regressions illustrate the theoretical results."]]></description>
<dc:subject>to:NB bootstrap confidence_sets statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b9f0e67d2d98/</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:confidence_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>