研究园简易版 · 经典书籍 · 期刊文章 · 有原文 · 完整版(可多选筛选、搜索) · 首页
2022 年的期刊文章 · 第 2 页
共 1481 篇,按发表时间排,新的在前,每页 40 篇。这一页是 2022-12-12 到 2022-11-30。
按期刊、按主题看 →
JASA Causal Inference · 发表于 2022-12-12
Xiao Wu, Fabrizia Mealli, Marianthi-Anna Kioumourtzoglou, Francesca Dominici, Danielle Braun
摘要
In the context of a binary treatment, matching is a well-established approach in causal inference. However, in the context of a continuous treatment or exposure, matching is still underdeveloped. We propose an innovative matching approach to estimate an average causal exposure-response function under the setting of continuous exposures that relies on the generalized propensity score (GPS). Our approach maintains the following attractive features of matching: a) clear separation between the design and the analysis; b) robustness to model misspecification or to the presence of extreme values of the estimated GPS; c) straightforward assessments of covariate balance. We first introduce an assumption of identifiability, called local weak unconfoundedness. Under this assumption and mild smoothness conditions, we provide theoretical guarantees that our proposed matching estimator attains point-wise consistency and asymptotic normality. In simulations, our proposed matching approach outperforms existing methods under settings with model misspecification or in the presence of extreme values of the estimated GPS. We apply our proposed method to estimate the average causal exposure-response function between long-term PM2.5 exposure and all-cause mortality among 68.5 million Medicare enrollees, 2000-2016. We found strong evidence of a harmful effect of long-term PM2.5 exposure on mortality. Code for the proposed matching approach is provided in the CausalGPS R package, which is available on CRAN and provides a computationally efficient implementation. *(abstract via PubMed)*
JASA Meta-Analysis & Data Integration Networks & Graphs High-Dimensional · 发表于 2022-12-12
Xin Zhang, Jia Liu, Zhengyuan Zhu
摘要
Identifying the latent cluster structure based on model heterogeneity is a fundamental but challenging task arises in many machine learning applications. In this article, we study the clustered coefficient regression problem in the distributed network systems, where the data are locally collected and held by nodes. Our work aims to improve the regression estimation efficiency by aggregating the neighbors’ information while also identifying the cluster membership for nodes. To achieve efficient estimation and clustering, we develop a distributed spanning-tree-based fused-lasso regression (DTFLR) approach. In particular, we propose an adaptive spanning-tree-based fusion penalty for the low-complexity clustered coefficient regression. We show that our proposed estimator satisfies statistical oracle properties. Additionally, to solve the problem parallelly, we design a distributed generalized alternating direction method of multiplier algorithm, which has a simple node-based implementation scheme and enjoys a linear convergence rate. Collectively, our results in this article contribute to the theories of low-complexity clustered coefficient regression and distributed optimization over networks. Thorough numerical experiments and real-world data analysis are conducted to verify our theoretical results, which show that our approach outperforms existing works in terms of estimation accuracy, computation speed, and communication costs. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA Causal Inference Networks & Graphs Nonparametric & Semiparametric · 发表于 2022-12-12
Elizabeth L. Ogburn, Oleg Sofrygin, Iván Díaz, Mark J. van der Laan
摘要
We describe semiparametric estimation and inference for causal effects using observational data from a single social network. Our asymptotic results are the first to allow for dependence of each observation on a growing number of other units as sample size increases. In addition, while previous methods have implicitly permitted only one of two possible sources of dependence among social network observations, we allow for both dependence due to transmission of information across network ties and for dependence due to latent similarities among nodes sharing ties. We propose new causal effects that are specifically of interest in social network settings, such as interventions on network ties and network structure. We use our methods to reanalyze an influential and controversial study that estimated causal peer effects of obesity using social network data from the Framingham Heart Study; after accounting for network structure we find no evidence for causal peer effects. *(abstract via PubMed)*
SiM Causal Inference · 发表于 2022-12-11
Deshanee Senevirathne Wickramarachchi, Laura Huey Mien Lim, Baoluo Sun
摘要
It is often of interest in the health and social sciences to investigate the joint mediation effects of multiple post‐exposure mediating variables. Identification of such joint mediation effects generally require no unmeasured confounding of the outcome with respect to the whole set of mediators. As the number of mediators under consideration grows, this key assumption is likely to be violated as it is often infeasible to intervene on any of the mediators. In this article, we develop a simple two‐step method of moments estimation procedure to assess mediation with multiple mediators simultaneously in the presence of potential unmeasured mediator‐outcome confounding. Our identification result leverages heterogeneity of the population exposure effect on the mediators, which is plausible under a variety of empirical settings. The proposed estimators are illustrated through both simulations and an application to evaluate the mediating effects of post‐traumatic stress disorder symptoms in the association between self‐efficacy and fatigue among health care workers during the COVID‐19 outbreak.
Biometrics Nonparametric & Semiparametric · 发表于 2022-12-09
Bo Wei, Limin Peng, Ying Guo, Amita Manatunga, Jennifer Stevens
摘要
Collecting neuroimaging data in the form of tensors (i.e. multidimensional arrays) has become more common in mental health studies, driven by an increasing interest in studying the associations between neuroimaging phenotypes and clinical disease manifestation. Motivated by a neuroimaging study of post-traumatic stress disorder (PTSD) from the Grady Trauma Project, we study a tensor response quantile regression framework, which enables novel analyses that confer a detailed view of the potentially heterogeneous association between a neuroimaging phenotype and relevant clinical predictors. We adopt a sensible low-rank structure to represent the association of interest, and propose a simple two-step estimation procedure which is easy to implement with existing software. We provide rigorous theoretical justifications for the intuitive two-step procedure. Simulation studies demonstrate good performance of the proposed method with realistic sample sizes in neuroimaging studies. We conduct the proposed tensor response quantile regression analysis of the motivating PTSD study to investigate the association between fMRI resting-state functional connectivity and PTSD symptom severity. Our results uncover non-homogeneous effects of PTSD symptoms on brain functional connectivity, which cannot be captured by existing tensor response methods.
Biometrics Other · 发表于 2022-12-09
Lina M. Montoya, Michael R. Kosorok, Elvin H. Geng, Joshua Schwab, Thomas A. Odeny, Maya L. Petersen
摘要
Personalized intervention strategies, in particular those that modify treatment based on a participant's own response, are a core component of precision medicine approaches. Sequential multiple assignment randomized trials (SMARTs) are growing in popularity and are specifically designed to facilitate the evaluation of sequential adaptive strategies, in particular those embedded within the SMART. Advances in efficient estimation approaches that are able to incorporate machine learning while retaining valid inference can allow for more precise estimates of the effectiveness of these embedded regimes. However, to the best of our knowledge, such approaches have not yet been applied as the primary analysis in SMART trials. In this paper, we present a robust and efficient approach using targeted maximum likelihood estimation (TMLE) for estimating and contrasting expected outcomes under the dynamic regimes embedded in a SMART, together with generating simultaneous confidence intervals for the resulting estimates. We contrast this method with two alternatives (G-computation and inverse probability weighting estimators). The precision gains and robust inference achievable through the use of TMLE to evaluate the effects of embedded regimes are illustrated using both outcome-blind simulations and a real-data analysis from the Adaptive Strategies for Preventing and Treating Lapses of Retention in Human Immunodeficiency Virus (HIV) Care (ADAPT-R) trial (NCT02338739), a SMART with a primary aim of identifying strategies to improve retention in HIV care among people living with HIV in sub-Saharan Africa.
Biometrics Spatial & Time Series · 发表于 2022-12-09
Oliver Stoner, Alba Halliday, Theo Economou
摘要
The COVID-19 pandemic has highlighted delayed reporting as a significant impediment to effective disease surveillance and decision-making. In the absence of timely data, statistical models which account for delays can be adopted to nowcast and forecast cases or deaths. We discuss the four key sources of systematic and random variability in available data for COVID-19 and other diseases, and critically evaluate current state-of-the-art methods with respect to appropriately separating and capturing this variability. We propose a general hierarchical approach to correcting delayed reporting of COVID-19 and apply this to daily English hospital deaths, resulting in a flexible prediction tool which could be used to better inform pandemic decision-making. We compare this approach to competing models with respect to theoretical flexibility and quantitative metrics from a 15-month rolling prediction experiment imitating a realistic operational scenario. Based on consistent leads in predictive accuracy, bias, and precision, we argue that this approach is an attractive option for correcting delayed reporting of COVID-19 and future epidemics.
JASA High-Dimensional · 发表于 2022-12-08
Bingyuan Liu, Qi Zhang, Lingzhou Xue, Peter X.-K. Song, Jian Kang
摘要
It is important to develop statistical techniques to analyze high-dimensional data in the presence of both complex dependence and possible heavy tails and outliers in real-world applications such as imaging data analyses. We propose a new robust high-dimensional regression with coefficient thresholding, in which an efficient nonconvex estimation procedure is proposed through a thresholding function and the robust Huber loss. The proposed regularization method accounts for complex dependence structures in predictors and is robust against heavy tails and outliers in outcomes. Theoretically, we rigorously analyze the landscape of the population and empirical risk functions for the proposed method. The fine landscape enables us to establish both statistical consistency and computational convergence under the high-dimensional setting. We also present an extension to incorporate spatial information into the proposed method. Finite-sample properties of the proposed methods are examined by extensive simulation studies. An application concerns a scalar-on-image regression analysis for an association of psychiatric disorder measured by the general factor of psychopathology with features extracted from the task functional MRI data in the Adolescent Brain Cognitive Development (ABCD) study. *(abstract via PubMed)*
SMMR Causal Inference Testing & Uncertainty · 发表于 2022-12-07
Roland A Matsouaka, Yi Liu, Yunji Zhou
摘要
Common causal estimands include the average treatment effect, the average treatment effect of the treated, and the average treatment effect on the controls. Using augmented inverse probability weighting methods, parametric models are judiciously leveraged to yield doubly robust estimators, that is, estimators that are consistent when at least one the parametric models is correctly specified. Three sources of uncertainty are associated when we evaluate these estimators and their variances, that is, when we estimate the treatment and outcome regression models as well as the desired treatment effect. In this article, we propose methods to calculate the variance of the normalized, doubly robust average treatment effect of the treated and average treatment effect on the controls estimators and investigate their finite sample properties. We consider both the asymptotic sandwich variance estimation, the standard bootstrap as well as two wild bootstrap methods. For the asymptotic approximations, we incorporate the aforementioned uncertainties via estimating equations. Moreover, unlike the standard bootstrap procedures, the proposed wild bootstrap methods use perturbations of the influence functions of the estimators through independently distributed random variables. We conduct an extensive simulation study where we vary the heterogeneity of the treatment effect as well as the proportion of participants assigned to the active treatment group. We illustrate the methods using an observational study of critical ill patients on the use of right heart catherization.
SiM Survival Analysis Testing & Uncertainty · 发表于 2022-12-07
Ziqi Geng, Jialiang Li, Yi Niu, Xiaoguang Wang
摘要
Partly interval‐censored event time data arise naturally in medical, biological, sociological and demographic studies. In practice, some patients may be immune from the event of interest, invoking a cure model for survival analysis. Choosing an appropriate parametric distribution for the failure time of susceptible patients is an important step to fully structure the mixture cure model. In the literature, goodness‐of‐fit tests for survival models are usually restricted to uncensored or right‐censored data. We fill in this gap by proposing a new goodness‐of‐fit test dealing with partly interval‐censored data under mixture cure models. Specifically, we investigate whether a parametric distribution can fit the susceptible part by using a Cramér‐von Mises type of test, and establish the asymptotic distribution of the test . Empirically, the critical value is determined from the bootstrap resamples. The proposed test, compared to the traditional leveraged bootstrap approach, yields superior practical results under various settings in extensive simulation studies. Two clinical data sets are analyzed to illustrate our method.
SiM Testing & Uncertainty · 发表于 2022-12-05
Weizhen Wang, Shuiyun Lu, Tianfa Xie
摘要
The relative risk and odds ratio are widely used in many fields, including biomedical research, to compare two treatments. Extensive research has been done to infer the two parameters through approximate or exact confidence intervals. However, these intervals may be liberal or conservative. A natural question is whether the intervals can be further improved in maintaining the correct confidence coefficient of an approximate interval or shortening an exact but conservative interval. In this article, when two independent binomials are observed we offer an effort to improve any of the existing intervals by applying the ‐function method. In particular, if the given interval is approximate, then the improved interval is exact; if the given interval is exact, then the improved interval is a subset of the given interval. This method is also applied multiple times to the improved intervals until the final resultant interval cannot be shortened any further. To demonstrate the effectiveness of the method, we use three real datasets to illustrate in detail how several good intervals in practice are improved. Two exact intervals are then recommended for estimating each of the two parameters in different scenarios.
Biometrics Survival Analysis · 发表于 2022-12-05
S. Mandal, J. Qin, R.M. Pfeiffer
摘要
We propose and study a simple and innovative non-parametric approach to estimate the age-of-onset distribution for a disease from a cross-sectional sample of the population that includes individuals with prevalent disease. First, we estimate the joint distribution of two event times, the age of disease onset and the survival time after disease onset. We accommodate that individuals had to be alive at the time of the study by conditioning on their survival until the age at sampling. We propose a computationally efficient expectation–maximization (EM) algorithm and derive the asymptotic properties of the resulting estimates. From these joint probabilities we then obtain non-parametric estimates of the age-at-onset distribution by marginalizing over the survival time after disease onset to death. The method accommodates categorical covariates and can be used to obtain unbiased estimates of the covariate distribution in the source population. We show in simulations that our method performs well in finite samples even under large amounts of truncation for prevalent cases. We apply the proposed method to data from female participants in the Washington Ashkenazi Study to estimate the age-at-onset distribution of breast cancer associated with carrying BRCA1 or BRCA2 mutations.
Biometrics Causal Inference · 发表于 2022-12-05
An‐Shun Tai, Sheng‐Hsuan Lin
摘要
Inferring causality is a key task in data science. Recent advances in causal inference methodology have provided a framework for identifying causal effects from observational data. Of the models for causal analysis, the counterfactual model is advantageous in enabling mathematically precise distinctions between causal inference and associational modeling, which are often confused in data science. The model achieves this advantage by adopting counterfactual values, instead of observations, of the variables of interest under hypothetical interventions to determine causal effects. However, understanding counterfactuals and causality is often challenging for data science novices. The book Fundamentals of Causal Inference with R by Babette A. Brumback not only details the fundamentals of causal inference and the mathematical theory of causation but also uses toy examples and analyses of simulated data with R software to illustrate the concepts of counterfactual models and causal mechanisms. The book also demonstrates the implementation of causal methods in R. This book is recommended for beginners, especially those with a basic knowledge of statistics and the R language, and for those who want to perform causal analysis in clinical and biomedical studies. The book is organized into 13 chapters. Herein, we categorize these chapters into four groups. The first group comprises Chapters 1 and 2, in which the author introduces a brief but clear history of causal inference and reviews the primary statistical techniques for causal analysis, including conditional probability and expected values, methods of estimating equations, and bootstrapping. Chapter 1.2 further presents five data-based examples that are used as the motivation for and to illustrate the concepts in the following chapters. The second group comprises Chapters 3 and 5, which present formal definitions of causal problems and the required causal assumptions in terms of mathematical logic. In Chapter 3, readers learn the concepts of potential outcomes (also known as counterfactual outcomes) and understand the fundamental problems of causal inference. In Chapter 3, potential outcomes are also used to mathematically define the causal effects of interest and the causal assumptions required for identifying these effects. Chapter 5 introduces a directed acyclic graph (DAG), which is a common technique of intuitively representing the causal dependencies among variables and of conceptualizing the causal assumptions made in a study. Additionally, the author describes how to generate simulated data in the R language in accordance with a DAG to clarify the meaning of the causal relations and enhance the reader's understanding of a causal DAG. The third group comprises Chapters 6 through 10 and demonstrates implementations of causal analysis and the corresponding statistical approaches. The elimination of confounding is key for successful causal inference in observational data. Five methods commonly used for causal inference—back-door criterion, difference-in-differences estimators, front-door criterion, instrumental variables, and propensity score methods—are introduced in Chapters 6–10. Chapter 6 presents the back-door criterion and describes the use of three standardization methods (standardization via outcome modeling, standardization via exposure modeling, and doubly robust standardization) to satisfy this criterion. The second and third standardizations are essentially the well-known inverse-probability-weighting estimation and doubly robust estimation. The difference-in-differences estimators presented in Chapter 7 rely on an additive equi-confounding assumption that is mainly used in cases in which common confounders of the outcomes of multiple groups are unobserved. The chapter also introduces negative outcome controls (typically pretreatment outcomes) in the causal analysis to remove potential confounding effects. Chapters 8 and 9 also address the problem of unmeasured common causes by borrowing information from another variable. In Chapter 8, a perfect mediating variable that satisfies the front-door criterion is assumed to exist, and the corresponding formulas of causal effects are derived. In Chapter 9, the method of instrumental variables is reviewed, and procedures for estimating the complier average causal effect and those for estimating the average treatment effect on the treated through the use of instrumental variables are provided. Chapter 10 presents propensity score methods. The back-door criterion states that the effect of a treatment on outcomes can be causally interpreted if all of the confounding variables are collected and included in the analysis. However, statistical problems, such as model misspecification, may occur in models constructed with complex confounders. Propensity score methods remedy this problem by using only the propensity score—a univariate variable. Chapter 10 presents three propensity score methods. The final group comprises Chapter 4 and Chapters 11–13. In this group, extended causal inference concepts are described, including effect modification, causal interaction, precision variables, mediation, and time-varying confounders. The task of causal inference is to assess the effect of a causal factor on an outcome of interest. In some cases, researchers must clarify the role of a third variable, which could be an effect modifier or a second cause of the outcome, in this causal mechanism. Chapter 4 is useful for those interested in effect modification and causal interaction. Chapter 11 introduces the concept of a precision variable, which is used to reduce the sampling variability of causal estimators. Incorporating a precision variable in causal inference enables reducing the standard error of the estimated causal effects. Chapters 12 and 13 introduce two notable extensions of causal inference: causal mediation analysis and time-varying causal inference. Causal mediation analysis enables assessing how the effects of treatment on an outcome are mediated by a third variable (called a mediator) and enables exploring the causal mechanism. Chapter 12 presents the theory of causal mediation analysis, defines the effects of mediation, and demonstrates a traditional parametric method for estimation. Chapter 13 focuses on longitudinal studies, in which time-varying treatments and time-varying confounders are commonly observed. For these studies, treatment–confounder feedback may exist, and the use of the conventional confounder adjustment methods presented in Chapters 6–10 could result in a biased estimation of causal effects. Therefore, Chapter 13 introduces three different methods—marginal structural models, structural nested mean models, and optimal dynamic treatment regimes—for adjusting time-varying confounding. Overall, this textbook is a perfect guide for interested researchers and students who wish to understand the rationale and methods of causal inference. Each chapter provides an R implementation of the introduced causal concepts and models and concludes with appropriate exercises. We believe that this book can evoke reader interest in causal thinking and reduce the difficulty of learning about causal inference. We thus enthusiastically recommend this book to statisticians in all fields. This study was supported by a grant from the Ministry of Science and Technology, Taiwan (No. MOST 111-2628-B-A49-007). *(abstract via OpenAlex)*
SMMR Survival Analysis Causal Inference Clinical Trials · 发表于 2022-12-04
Alexandra Erdmann, Anja Loos, Jan Beyersmann
摘要
Recently, treatment interruptions such as a clinical hold in randomized clinical trials have been investigated by using a multistate model approach. The phase III clinical trial START (Stimulating Targeted Antigenic Response To non-small-cell cancer) with primary endpoint overall survival was temporarily placed on hold for enrollment and treatment by the US Food and Drug Administration (FDA). Multistate models provide a flexible framework to account for treatment interruptions induced by a time-dependent external covariate. Extending previous work, we propose a censoring and a filtering approach both aimed at estimating the initial treatment effect on overall survival in the hypothetical situation of no clinical hold. A special focus is on creating a link to causal inference. We show that calculating the matrix of transition probabilities in the multistate model after application of censoring (or filtering) yields the desired causal interpretation. Assumptions in support of the identification of a causal effect by censoring (or filtering) are discussed. Thus, we provide the basis to apply causal censoring (or filtering) in more general settings such as the COVID-19 pandemic. A simulation study demonstrates that both causal censoring and filtering perform favorably compared to a naïve method ignoring the external impact.
AoS Optimization & Learning Theory · 发表于 2022-12-01
Wenhao Yang, Liangyu Zhang, Zhihua Zhang
摘要
In this paper, we study the nonasymptotic and asymptotic performances of the optimal robust policy and value function of robust Markov Decision Processes (MDPs), where the optimal robust policy and value function are estimated from a generative model. While prior work focusing on nonasymptotic performances of robust MDPs is restricted in the setting of the KL uncertainty set and (s,a)-rectangular assumption, we improve their results and also consider other uncertainty sets, including the L1 and χ2 balls. Our results show that when we assume (s,a)-rectangular on uncertainty sets, the sample complexity is about O˜(|S|2|A| ε2ρ2(1−γ)4). In addition, we extend our results from the (s,a)-rectangular assumption to the s-rectangular assumption. In this scenario, the sample complexity varies with the choice of uncertainty sets and is generally larger than the case under the (s,a)-rectangular assumption. Moreover, we also show that the optimal robust value function is asymptotically normal with a typical rate n under the (s,a) and s-rectangular assumptions from both theoretical and empirical perspectives.
SMMR Clinical Trials Testing & Uncertainty · 发表于 2022-12-01
Werner Brannath, Charlie Hillner, Kornelius Rohmeyer
摘要
We introduce a new multiple type I error criterion for clinical trials with multiple, overlapping populations. Such trials are of interest in precision medicine where the goal is to develop treatments that are targeted to specific sub-populations defined by genetic and/or clinical biomarkers. The new criterion is based on the observation that not all type I errors are relevant to all patients in the overall population. If disjoint sub-populations are considered, no multiplicity adjustment appears necessary, since a claim in one sub-population does not affect patients in the other ones. For intersecting sub-populations we suggest to control the average multiple type I error rate, i.e. the probability that a randomly selected patient will be exposed to an inefficient treatment. We call this the population-wise error rate, exemplify it by a number of examples and illustrate how to control it with an adjustment of critical boundaries or adjusted [Formula: see text]-values. We furthermore define corresponding simultaneous confidence intervals. We finally illustrate the power gain achieved by passing from family-wise to population-wise error rate control with two simple examples and a recently suggested multiple-testing approach for umbrella trials.
AoS Nonparametric & Semiparametric · 发表于 2022-12-01
Yuichi Goto, Tobias Kley, Ria Van Hecke, Stanislav Volgushev, Holger Dette, Marc Hallin
摘要
Frequency domain methods form a ubiquitous part of the statistical toolbox for time-series analysis. In recent years, considerable interest has been given to the development of new spectral methodology and tools capturing dynamics in the entire joint distributions, and thus avoiding the limitations of classical, L2-based spectral methods. Most of the spectral concepts proposed in that literature suffer from one major drawback, though: their estimation requires the choice of a smoothing parameter, which has a considerable impact on estimation quality and poses challenges for statistical inference. In this paper, associated with the concept of a copula-based spectrum, we introduce the notion of a copula spectral distribution function or integrated copula spectrum. This integrated copula spectrum retains the advantages of copula-based spectra but can be estimated without the need for smoothing parameters. We provide such estimators, along with a thorough theoretical analysis, based on a functional central limit theorem, of their asymptotic properties. We leverage these results to test various hypotheses that cannot be addressed by classical spectral methods, such as the lack of time reversibility or asymmetry in tail dynamics.
AoS Nonparametric & Semiparametric · 发表于 2022-12-01
Kartik G. Waghmare, Victor M. Panaretos
摘要
We consider the problem of positive-semidefinite continuation: extending a partially specified covariance kernel from a subdomain Ω of a rectangular domain I×I to a covariance kernel on the entire domain I×I. For a broad class of domains Ω called serrated domains, we are able to present a complete theory. Namely, we demonstrate that a canonical completion always exists and can be explicitly constructed. We characterise all possible completions as suitable perturbations of the canonical completion, and determine necessary and sufficient conditions for a unique completion to exist. We interpret the canonical completion via the graphical model structure it induces on the associated Gaussian process. Furthermore, we show how the estimation of the canonical completion reduces to the solution of a system of linear statistical inverse problems in the space of Hilbert–Schmidt operators, and derive rates of convergence. We conclude by providing extensions of our theory to more general forms of domains, and by demonstrating how our results can be used to construct covariance estimators from sample path fragments of the associated stochastic process. Our results are illustrated numerically by way of a simulation study and a real example.
AoS Other · 发表于 2022-12-01
Andrew McCormack, Peter Hoff
摘要
The Fréchet mean is a useful description of location for a probability distribution on a metric space that is not necessarily a vector space. This article considers simultaneous estimation of multiple Fréchet means from a decision-theoretic perspective, and in particular, the extent to which the unbiased estimator of a Fréchet mean can be dominated by a generalization of the James–Stein shrinkage estimator. It is shown that if the metric space satisfies a nonpositive curvature condition, then this generalized James–Stein estimator asymptotically dominates the unbiased estimator as the dimension of the space grows. These results hold for a large class of distributions on a variety of spaces, including Hilbert spaces and, therefore, partially extend known results on the applicability of the James–Stein estimator to nonnormal distributions on Euclidean spaces. Simulation studies on phylogenetic trees and symmetric positive definite matrices are presented, numerically demonstrating the efficacy of this generalized James–Stein estimator.
AoS Testing & Uncertainty Missing Data & Measurement Error · 发表于 2022-12-01
Anirvan Charkaborty, Victor M. Panaretos
摘要
How can we discern whether the covariance operator of a stochastic process is of reduced rank, and if so, what its precise rank is? And how can we do so at a given level of confidence? This question is central to a great deal of methods for functional data, which require low-dimensional representations whether by functional PCA or other methods. The difficulty is that the determination is to be made on the basis of i.i.d. replications of the process observed discretely and with measurement error contamination. This adds a ridge to the empirical covariance, obfuscating the underlying dimension. We build a matrix-completion inspired test statistic that circumvents this issue by measuring the best possible least square fit of the empirical covariance’s off-diagonal elements, optimised over covariances of given finite rank. For a fixed grid of sufficiently large size, we determine the statistic’s asymptotic null distribution as the number of replications grows. We then use it to construct a bootstrap implementation of a stepwise testing procedure controlling the familywise error rate corresponding to the collection of hypotheses formalising the question at hand. Under minimal regularity assumptions, we prove that the procedure is consistent and that its bootstrap implementation is valid. The procedure circumvents smoothing and associated smoothing parameters, is indifferent to measurement error heteroskedasticity, and does not assume a low-noise regime. An extensive simulation study reveals an excellent practical performance, stably across a wide range of settings and the procedure is further illustrated by means of two data analyses.
AoS Nonparametric & Semiparametric · 发表于 2022-12-01
Cathrine Aeckerle-Willems, Claudia Strauch
摘要
We consider the question of estimating the drift for a large class of ergodic multivariate and possibly nonreversible diffusion processes, based on continuous observations, in sup-norm loss. Nonparametric classes of smooth functions of unknown order are considered, and we suggest an adaptive approach which allows to construct drift estimators attaining optimal sup-norm rates of convergence. Reversibility structures and related functional inequalities are known to be key tools for these estimation problems. We can discard such restrictions by making use of mixing properties which are satisfied for the very general class of processes under consideration. Analysing diffusions, the scalar case is very distinct from the general multivariate setting. Therefore, we treat scalar and multivariate processes separately which leads to in several aspects improved univariate results. While we consider drift estimation on bounded domains for exponentially β-mixing multivariate processes, for scalar diffusion processes we work under minimal assumptions that allow estimation of unbounded drift terms over the entire real line, and we provide classical minimax results (including lower bounds) which cannot be obtained under state-of-the-art conditions in the multivariate case. In addition, we prove a Donsker theorem for the classical kernel estimator of the invariant density in the scalar setting and establish its semiparametric efficiency.
AoS Causal Inference · 发表于 2022-12-01
Yuhao Wang, Xinran Li
摘要
Completely randomized experiments have been the gold standard for drawing causal inference because they can balance all potential confounding on average. However, they may suffer from unbalanced covariates for realized treatment assignments. Rerandomization, a design that rerandomizes the treatment assignment until a prespecified covariate balance criterion is met, has recently got attention due to its easy implementation, improved covariate balance and more efficient inference. Researchers have then suggested to use the treatment assignments that minimize the covariate imbalance, namely the optimally balanced design. This has caused again the long-time controversy between two philosophies for designing experiments: randomization versus optimal, and thus almost deterministic designs. Existing literature argued that rerandomization with overly balanced observed covariates can lead to highly imbalanced unobserved covariates, making it vulnerable to model misspecification. On the contrary, rerandomization with properly balanced covariates can provide robust inference for treatment effects while sacrificing some efficiency compared to the ideally optimal design. In this paper, we show it is possible that, by making the covariate imbalance diminishing at a proper rate as the sample size increases, rerandomization can achieve its ideally optimal precision that one can expect with perfectly balanced covariates, while still maintaining its robustness. We further investigate conditions on the number of covariates for achieving the desired optimality. Our results rely on a more delicate asymptotic analysis for rerandomization, allowing both diminishing covariate imbalance threshold (or equivalently the acceptance probability) and diverging number of covariates. The derived theory for rerandomization provides a deeper understanding of its large-sample property and can better guide its practical implementation. Furthermore, it also helps reconcile the controversy between randomized and optimal designs in an asymptotic sense.
AoS Optimization & Learning Theory · 发表于 2022-12-01
Anil Aswani, Matt Olfat
摘要
Data-driven decision making has drawn scrutiny from policy makers due to fears of potential discrimination, and a growing literature has begun to develop fair statistical techniques. However, these techniques are often specialized to one model context and based on ad hoc arguments, which makes it difficult to perform theoretical analysis. This paper develops an optimization hierarchy, which is a sequence of optimization problems with an increasing number of constraints, for fair statistical decision problems. Because our hierarchy is based on the framework of statistical decision problems, this means it provides a systematic approach for developing and studying fair versions of hypothesis testing, decision making, estimation, regression, and classification. We use the insight that qualitative definitions of fairness are equivalent to statistical independence between the output of a statistical technique and a random variable that measures attributes for which fairness is desired. We use this insight to construct an optimization hierarchy that lends itself to numerical computation, and we use tools from variational analysis and random set theory to prove that higher levels of this hierarchy lead to consistency in the sense that it asymptotically imposes this independence as a constraint in corresponding statistical decision problems. We demonstrate numerical effectiveness of our hierarchy using several data sets, and we use our hierarchy to fairly perform automated dosing of morphine.
AoS Other · 发表于 2022-12-01
Nicolas Chopin, Sumeetpal S. Singh, Tomás Soto, Matti Vihola
摘要
We consider particle filters with weakly informative observations (or ‘potentials’) relative to the latent state dynamics. The particular focus of this work is on particle filters to approximate time-discretisations of continuous-time Feynman–Kac path integral models—a scenario that naturally arises when addressing filtering and smoothing problems in continuous time—but our findings are indicative about weakly informative settings beyond this context too. We study the performance of different resampling schemes, such as systematic resampling, SSP (Srinivasan sampling process) and stratified resampling, as the time-discretisation becomes finer and also identify their continuous-time limit, which is expressed as a suitably defined ‘infinitesimal generator.’ By contrasting these generators, we find that (certain modifications of) systematic and SSP resampling ‘dominate’ stratified and independent ‘killing’ resampling in terms of their limiting overall resampling rate. The reduced intensity of resampling manifests itself in lower variance in our numerical experiment. This efficiency result, through an ordering of the resampling rate, is new to the literature. The second major contribution of this work concerns the analysis of the limiting behaviour of the entire population of particles of the particle filter as the time discretisation becomes finer. We provide the first proof, under general conditions, that the particle approximation of the discretised continuous-time Feynman–Kac path integral models converges to a (uniformly weighted) continuous-time particle system.
AoS Spatial & Time Series · 发表于 2022-12-01
Qihao Zhang, Soumendra N. Lahiri, Daniel J. Nordman
摘要
Block-based resampling estimators have been intensively investigated for weakly dependent time processes, which has helped to inform implementation (e.g., best block sizes). However, little is known about resampling performance and block sizes under strong or long-range dependence. To establish guideposts in block selection, we consider a broad class of strongly dependent time processes, formed by a transformation of a stationary long-memory Gaussian series, and examine block-based resampling estimators for the variance of the prototypical sample mean; extensions to general statistical functionals are also considered. Unlike weak dependence, the properties of resampling estimators under strong dependence are shown to depend intricately on the nature of nonlinearity in the time series (beyond Hermite ranks) in addition to the long-memory coefficient and block size. Additionally, the intuition has often been that optimal block sizes should be larger under strong dependence (say O(n1/2) for a sample size n) than the optimal order O(n1/3) known under weak dependence. This intuition turns out to be largely incorrect, though a block order O(n1/2) may be reasonable (and even optimal) in many cases, owing to nonlinearity in a long-memory time series. While optimal block sizes are more complex under long-range dependence compared to short-range, we provide a consistent data-driven rule for block selection. Numerical studies illustrate that the guides for block selection perform well in other block-based problems with long-memory time series, such as distribution estimation and strategies for testing Hermite rank.
Biometrics Nonparametric & Semiparametric · 发表于 2022-12-01
David Todem, Wei-Wen Hsu, KyungMann Kim
摘要
In many applications of hierarchical models, there is often interest in evaluating the inherent heterogeneity in view of observed data. When the underlying hypothesis involves parameters resting on the boundary of their support space such as variances and mixture proportions, it is a usual practice to entertain testing procedures that rely on common heterogeneity assumptions. Such procedures, albeit omnibus for general alternatives, may entail a substantial loss of power for specific alternatives such as heterogeneity varying with covariates. We introduce a novel and flexible approach that uses covariate information to improve the power to detect heterogeneity, without imposing unnecessary restrictions. With continuous covariates, the approach does not impose a regression model relating heterogeneity parameters to covariates or rely on arbitrary discretizations. Instead, a scanning approach requiring continuous dichotomizations of the covariates is proposed. Empirical processes resulting from these dichotomizations are then used to construct the test statistics, with limiting null distributions shown to be functionals of tight random processes. We illustrate our proposals and results on a popular class of two-component mixture models, followed by simulation studies and applications to two real datasets in cancer and caries research.
AoS Testing & Uncertainty · 发表于 2022-12-01
Ilmun Kim, Matey Neykov, Sivaraman Balakrishnan, Larry Wasserman
摘要
In this paper, we investigate local permutation tests for testing conditional independence between two random vectors X and Y given Z. The local permutation test determines the significance of a test statistic by locally shuffling samples, which share similar values of the conditioning variables Z, and it forms a natural extension of the usual permutation approach for unconditional independence testing. Despite its simplicity and empirical support, the theoretical underpinnings of the local permutation test remain unclear. Motivated by this gap, this paper aims to establish theoretical foundations of local permutation tests with a particular focus on binning-based statistics. We start by revisiting the hardness of conditional independence testing and provide an upper bound for the power of any valid conditional independence test, which holds when the probability of observing “collisions” in Z is small. This negative result naturally motivates us to impose additional restrictions on the possible distributions under the null and alternate. To this end, we focus our attention on certain classes of smooth distributions and identify provably tight conditions under which the local permutation method is universally valid, that is, it is valid when applied to any (binning-based) test statistic. To complement this result on type I error control, we also show that in some cases, a binning-based statistic calibrated via the local permutation method can achieve minimax optimal power. We also introduce a double-binning permutation strategy, which yields a valid test over less smooth null distributions than the typical single-binning method without compromising much power. Finally, we present simulation results to support our theoretical findings.
AoS Other · 发表于 2022-12-01
Johannes Heiny, Jianfeng Yao
摘要
Consider a p-dimensional population x∈Rp with i.i.d. coordinates that are regularly varying with index α∈(0,2). Since the variance of x is infinite, the diagonal elements of the sample covariance matrix Sn=n−1 ∑ i=1nxixi′ based on a sample x1,…,xn from the population tend to infinity as n increases and it is of interest to use instead the sample correlation matrix Rn={diag(Sn)}−1/2Sn{diag(Sn)}−1/2. This paper finds the limiting distributions of the eigenvalues of Rn when both the dimension p and the sample size n grow to infinity such that p/n→γ∈(0,∞). The family of limiting distributions {Hα,γ} is new and depends on the two parameters α and γ. The moments of Hα,γ are fully identified as sum of two contributions: the first from the classical Marčenko–Pastur law and a second due to heavy tails. Moreover, the family {Hα,γ} has continuous extensions at the boundaries α=2 and α=0 leading to the Marčenko–Pastur law and a modified Poisson distribution, respectively. Our proofs use the method of moments, the path-shortening algorithm developed in [18] (Stochastic Process. Appl. 128 (2018) 2779–2815) and some novel graph counting combinatorics. As a consequence, the moments of Hα,γ are expressed in terms of combinatorial objects such as Stirling numbers of the second kind. A simulation study on these limiting distributions Hα,γ is also provided for comparison with the Marčenko–Pastur law.
AoS Optimization & Learning Theory High-Dimensional · 发表于 2022-12-01
Xin Bing, Florentina Bunea, Seth Strimas-Mackey, Marten Wegkamp
摘要
This paper studies the estimation of high-dimensional, discrete, possibly sparse, mixture models in the context of topic models. The data consists of observed multinomial counts of p words across n independent documents. In topic models, the p×n expected word frequency matrix is assumed to be factorized as a p×K word-topic matrix A and a K×n topic-document matrix T. Since columns of both matrices represent conditional probabilities belonging to probability simplices, columns of A are viewed as p-dimensional mixture components that are common to all documents while columns of T are viewed as the K-dimensional mixture weights that are document specific and are allowed to be sparse. The main interest is to provide sharp, finite sample, ℓ1-norm convergence rates for estimators of the mixture weights T when A is either known or unknown. For known A, we suggest MLE estimation of T. Our nonstandard analysis of the MLE not only establishes its ℓ1 convergence rate, but also reveals a remarkable property: the MLE, with no extra regularization, can be exactly sparse and contain the true zero pattern of T. We further show that the MLE is both minimax optimal and adaptive to the unknown sparsity in a large class of sparse topic distributions. When A is unknown, we estimate T by optimizing the likelihood function corresponding to a plug in, generic, estimator Aˆ of A. For any estimator Aˆ that satisfies carefully detailed conditions for proximity to A, we show that the resulting estimator of T retains the properties established for the MLE. Our theoretical results allow the ambient dimensions K and p to grow with the sample sizes. Our main application is to the estimation of 1-Wasserstein distances between document generating distributions. We propose, estimate and analyze new 1-Wasserstein distances between alternative probabilistic document representations, at the word and topic level, respectively. We derive finite sample bounds on the estimated proposed 1-Wasserstein distances. For word level document-distances, we provide contrast with existing rates on the 1-Wasserstein distance between standard empirical frequency estimates. The effectiveness of the proposed 1-Wasserstein distances is illustrated by an analysis of an IMDB movie reviews data set. Finally, our theoretical results are supported by extensive simulation studies.
AoS Latent Variables & Mixtures Causal Inference · 发表于 2022-12-01
Rina Foygel Barber, Mathias Drton, Nils Sturma, Luca Weihs
摘要
We consider linear structural equation models with latent variables and develop a criterion to certify whether the direct causal effects between the observable variables are identifiable based on the observed covariance matrix. Linear structural equation models assume that both observed and latent variables solve a linear equation system featuring stochastic noise terms. Each model corresponds to a directed graph whose edges represent the direct effects that appear as coefficients in the equation system. Prior research has developed a variety of methods to decide identifiability of direct effects in a latent projection framework, in which the confounding effects of the latent variables are represented by correlation among noise terms. This approach is effective when the confounding is sparse and effects only small subsets of the observed variables. In contrast, the new latent-factor half-trek criterion (LF-HTC) we develop in this paper operates on the original unprojected latent variable model and is able to certify identifiability in settings, where some latent variables may also have dense effects on many or even all of the observables. Our LF-HTC is an effective sufficient criterion for rational identifiability, under which the direct effects can be uniquely recovered as rational functions of the joint covariance matrix of the observed random variables. When restricting the search steps in LF-HTC to consider subsets of latent variables of bounded size, the criterion can be verified in time that is polynomial in the size of the graph.
AoS Other · 发表于 2022-12-01
Sjoerd Dirksen, Johannes Maly, Holger Rauhut
摘要
We consider the classical problem of estimating the covariance matrix of a sub-Gaussian distribution from i.i.d. samples in the novel context of coarse quantization, that is, instead of having full knowledge of the samples, they are quantized to one or two bits per entry. This problem occurs naturally in signal processing applications. We introduce new estimators in two different quantization scenarios and derive nonasymptotic estimation error bounds in terms of the operator norm. In the first scenario, we consider a simple, scale-invariant one-bit quantizer and derive an estimation result for the correlation matrix of a centered Gaussian distribution. In the second scenario, we add random dithering to the quantizer. In this case, we can accurately estimate the full covariance matrix of a general sub-Gaussian distribution by collecting two bits per entry of each sample. In both scenarios, our bounds apply to masked covariance estimation. We demonstrate the near optimality of our error bounds by deriving corresponding (minimax) lower bounds and using numerical simulations.
AoS Testing & Uncertainty Diagnostics & Prediction · 发表于 2022-12-01
William Fithian, Lihua Lei
摘要
We introduce a new class of methods for finite-sample false discovery rate (FDR) control in multiple testing problems with dependent test statistics where the dependence is known. Our approach separately calibrates a data-dependent p-value rejection threshold for each hypothesis, relaxing or tightening the threshold as appropriate to target exact FDR control. In addition to our general framework, we propose a concrete algorithm, the dependence-adjusted Benjamini–Hochberg (dBH) procedure, which thresholds the BH-adjusted p-value for each hypothesis. Under positive regression dependence, the dBH procedure uniformly dominates the standard BH procedure, and in general it uniformly dominates the Benjamini–Yekutieli (BY) procedure (also known as BH with log correction), which makes a conservative adjustment for worst-case dependence. Simulations and real data examples show substantial power gains over the BY procedure, and competitive performance with knockoffs in settings where both methods are applicable. When the BH procedure empirically controls FDR (as it typically does in practice), the dBH procedure performs comparably.
AoS Bayesian Methods · 发表于 2022-12-01
Christophe Andrieu, Anthony Lee, Sam Power, Andi Q. Wang
摘要
We investigate the use of a certain class of functional inequalities known as weak Poincaré inequalities to bound convergence of Markov chains to equilibrium. We show that this enables the straightforward and transparent derivation of subgeometric convergence bounds for methods such as the Independent Metropolis–Hastings sampler and pseudo-marginal methods for intractable likelihoods, the latter being subgeometric in many practical settings. These results rely on novel quantitative comparison theorems between Markov chains. Associated proofs are simpler than those relying on drift/minorisation conditions and the tools developed allow us to recover and further extend known results as particular cases. We are then able to provide new insights into the practical use of pseudo-marginal algorithms, analyse the effect of averaging in Approximate Bayesian Computation (ABC) and the use of products of independent averages and also to study the case of log-normal weights relevant to particle marginal Metropolis–Hastings (PMMH).
AoS Spatial & Time Series · 发表于 2022-12-01
Ilias Chronopoulos, Liudas Giraitis, George Kapetanios
摘要
This paper suggests a multiplicative volatility model where volatility is decomposed into a stationary and a nonstationary persistent part. We provide a testing procedure to determine which type of volatility is prevalent in the data. The persistent part of volatility is associated with a nonstationary persistent process satisfying some smoothness and moment conditions. The stationary part is related to stationary conditional heteroskedasticity. We outline theory and conditions that allow the extraction of the persistent part from the data and enable standard conditional heteroskedasticity tests to detect stationary volatility after persistent volatility is taken into account. Monte Carlo results support the testing strategy in small samples. The empirical application of the theory supports the persistent volatility paradigm, suggesting that stationary conditional heteroskedasticity is considerably less pronounced than previously thought.
AoS Bayesian Methods · 发表于 2022-12-01
Cheng Li
摘要
Gaussian process models typically contain finite-dimensional parameters in the covariance function that need to be estimated from the data. We study the Bayesian fixed-domain asymptotics for the covariance parameters in a universal kriging model with an isotropic Matérn covariance function, which has many applications in spatial statistics. We show that when the dimension of domain is less than or equal to three, the joint posterior distribution of the microergodic parameter and the range parameter can be factored independently into the product of their marginal posteriors under fixed-domain asymptotics. The posterior of the microergodic parameter is asymptotically close in total variation distance to a normal distribution with shrinking variance, while the posterior distribution of the range parameter does not converge to any point mass distribution in general. Our theory allows an unbounded prior support for the range parameter and flexible designs of sampling points. We further study the asymptotic efficiency and convergence rates in posterior prediction for the Bayesian kriging predictor with covariance parameters randomly drawn from their posterior distribution. In the special case of one-dimensional Ornstein–Uhlenbeck process, we derive explicitly the limiting posterior of the range parameter and the posterior convergence rate for asymptotic efficiency in posterior prediction. We verify these asymptotic results in numerical experiments.
AoS Optimization & Learning Theory Causal Inference · 发表于 2022-12-01
Peng Liao, Zhengling Qi, Runzhe Wan, Predrag Klasnja, Susan A. Murphy
摘要
We consider the batch (off-line) policy learning problem in the infinite horizon Markov decision process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward. We propose a doubly robust estimator for the average reward and show that it achieves semiparametric efficiency. Further, we develop an optimization algorithm to compute the optimal policy in a parameterized stochastic policy class. The performance of the estimated policy is measured by the difference between the optimal average reward in the policy class and the average reward of the estimated policy and we establish a finite-sample regret guarantee. The performance of the method is illustrated by simulation studies and an analysis of a mobile health study promoting physical activity.
AoS High-Dimensional Machine Learning · 发表于 2022-12-01
Chien-Ming Chi, Patrick Vossler, Yingying Fan, Jinchi Lv
摘要
As a flexible nonparametric learning tool, the random forests algorithm has been widely applied to various real applications with appealing empirical performance, even in the presence of high-dimensional feature space. Unveiling the underlying mechanisms has led to some important recent theoretical results on the consistency of the random forests algorithm and its variants. However, to our knowledge, almost all existing works concerning random forests consistency in a high-dimensional setting were established for various modified random forests models where the splitting rules are independent of the response; a few exceptions assume simple data generating models with binary features. In light of this, in this paper we derive the consistency rates for the random forests algorithm associated with the sample CART splitting criterion, which is the one used in the original version of the algorithm (Mach. Learn. 45 (2001) 5–32), in a general high-dimensional nonparametric regression setting through a bias-variance decomposition analysis. Our new theoretical results show that random forests can indeed adapt to high dimensionality and allow for discontinuous regression function. Our bias analysis characterizes explicitly how the random forests bias depends on the sample size, tree height and column subsampling parameter. Some limitations on our current results are also discussed.
AoS Other · 发表于 2022-12-01
Steve Hanneke, Samory Kpotufe
摘要
Multitask learning and related areas such as multisource domain adaptation address modern settings where data sets from N related distributions {Pt} are to be combined toward improving performance on any single such distribution D. A perplexing fact remains in the evolving theory on the subject: while we would hope for performance bounds that account for the contribution from multiple tasks, the vast majority of analyses result in bounds that improve at best in the number n of samples per task, but most often do not improve in N. As such, it might seem at first that the distributional settings or aggregation procedures considered in such analyses might be somehow unfavorable; however, as we show, the picture happens to be more nuanced, with interestingly hard regimes that might appear otherwise favorable. In particular, we consider a seemingly favorable classification scenario where all tasks Pt share a common optimal classifier h∗, and which can be shown to admit a broad range of regimes with improved oracle rates in terms of N and n. Some of our main results are: ∙ We show that, even though such regimes admit minimax rates accounting for both n and N, no adaptive algorithm exists, that is, without access to distributional information, no algorithm can guarantee rates that improve with large N for n fixed. ∙ With a bit of additional information, namely, a ranking of tasks {Pt} according to their distance to a target D, a simple rank-based procedure can achieve near optimal aggregations of tasks’ data sets, despite a search space exponential in N. Interestingly, the optimal aggregation might exclude certain tasks, even though they all share the same h∗.
SiM Clinical Trials Causal Inference · 发表于 2022-11-30
David S. Robertson, Babak Choodari‐Oskooei, Munya Dimairo, Laura Flight, Philip Pallmann, Thomas Jaki
摘要
Recent FDA guidance on adaptive clinical trial designs defines bias as “a systematic tendency for the estimate of treatment effect to deviate from its true value,” and states that it is desirable to obtain and report estimates of treatment effects that reduce or remove this bias. The conventional end‐of‐trial point estimates of the treatment effects are prone to bias in many adaptive designs, because they do not take into account the potential and realized trial adaptations. While much of the methodological developments on adaptive designs have tended to focus on control of type I error rates and power considerations, in contrast the question of biased estimation has received relatively less attention. This article is the first in a two‐part series that studies the issue of potential bias in point estimation for adaptive trials. Part I provides a comprehensive review of the methods to remove or reduce the potential bias in point estimation of treatment effects for adaptive designs, while part II illustrates how to implement these in practice and proposes a set of guidelines for trial statisticians. The methods reviewed in this article can be broadly classified into unbiased and bias‐reduced estimation, and we also provide a classification of estimators by the type of adaptive design. We compare the proposed methods, highlight available software and code, and discuss potential methodological gaps in the literature.
Biometrika Causal Inference Testing & Uncertainty · 发表于 2022-11-30
Kevin Guo, Dominik Rothenhäusler
摘要
Summary: In observational causal inference, exact covariate matching plays two statistical roles: (i) it effectively controls for bias due to measured confounding; (ii) it justifies assumption-free inference based on randomization tests. In this paper we show that inexact covariate matching does not always play these same roles. We find that inexact matching often leaves behind statistically meaningful bias, and that this bias renders standard randomization tests asymptotically invalid. We therefore recommend additional model-based covariate adjustment after inexact matching. In the framework of local misspecification, we prove that matching makes subsequent parametric analyses less sensitive to model selection or misspecification. We argue that gaining such robustness is the primary statistical role of inexact matching.