论文检索

多维聚类稳健的双重／去偏机器学习AI 解读

This article investigates double/debiased machine learning (DML) under multiway clustered sampling environments. We propose a novel multiway cross-fitting algorithm and a multiway DML estimator based on this algorithm. We also develop a multiway cluster robust standard error formula. Simulations indicate that the proposed procedure has favorable finite sample performance. Applying the proposed method to market share data for demand analysis, we obtain larger two-way cluster…

不同样本选择校正方法的准实验评估AI 解读

Researchers routinely use datasets where outcomes of interest are unobserved for some cases, potentially creating a sample selection problem. Statisticians and econometricians have proposed many selection correction methods to address this challenge. We use a natural experiment to evaluate different sample selection correction methods’ performance. From 2007, the state of Michigan required that all students take a college entrance exam, increasing the exam-taking rate from…

周倪文与郭旭对《广义线性模型参数的少假设推断》的讨论AI 解读

We thank Professors Vansteelandt and Dukes for their innovative and stimulating paper. They introduce a new estimand which reduces to the exposure effect parameter when the (semi)parametric model holds, is generic for continuous or discrete exposure, and still captures conditional association when model assumption fails. We make some additional understanding of the new estimand and introduce a related new estimand. Here we consider the expectation of the ratio. Here β· and…

Ilya Shpitser 对《广义线性模型参数的少假设推断》的讨论AI 解读

A hallmark of principled causal inference is being careful and explicit about assumptions underlying data analysis. In their timely paper, the authors, Professor Stijn Vansteelandt and Oliver Dukes, adopt this view to provide a general roadmap for cautious statistical inference about target parameters. The authors distinguish between assumptions made for substantive reasons and those made for convenience. An important feature of their approach is that an estimand with…

Phillips 与 van der Laan 对《广义线性模型参数的弱假设推断》的讨论AI 解读

We commend the authors on this novel non-parametric extension of main and interaction coefficients in a generalised linear model (GLM), such as E(Y|A,L)=βA+g(L)⁠, and their efficient estimation. There is a wealth of non-parametric extensions one could pursue, including weighted squared error projections of a conditional treatment effect E(Y|A=a,L)-E(Y|A=0,L) and conditional interaction effect E(Y|A=(a1+1,a2+1),L)-E(Y|A=(a1,a2+1),L)-E(Y|A=(a1+1,a2),L)+E(Y|A=(a1,a2),L) onto a…

Ogburn 等对《广义线性模型参数的弱假设推断》的讨论AI 解读

Not all conditional associations between outcomes and exposures are of interest. Those that are tend to be directional: up or down. The simplest way to assess directionality is to fit a confounder- adjusted linear exposure term, as the authors propose. We agree with this approach as some of us have argued that linear slopes are meaningful and interpretable even if the directional association is not linear (Buja et al., 2019, section 10). The authors, and Whitney et al.…

Ian Hunt 对《广义线性模型参数的少假设推断》的讨论AI 解读

This paper offers a generic and principled addition to conventional statistical modelling. It is a real advance in applicable methodology. But there is no need in the paper for the following claims: that statisticians routinely use ‘dishonest’ modelling assumptions, that statisticians should aim for ‘purely evidence-based’ inferences and that modelling assumptions are ‘almost always a pure mathematical convenience’. These sorts of claims are redundant or misleading for three…

Choi 与 Wong 对《广义线性模型参数的弱假设推断》的讨论AI 解读

We congratulate the authors for major advances in the methodology of estimands, in particular assumption-lean reference for the estimands in possibly misspecified generalised linear models. Whereas the simulation studies in Section 6 indeed support the ‘assumption-lean’ claim and the authors’ software in Practice of Epidemiology187 (pp. 1079–1084, 2018) facilitates such inference, the empirical example in Section 7 seems problematic to illustrate applications of the…

Buja 等对“广义线性模型参数的弱假设推断”的讨论AI 解读

We thank the authors for their stimulating article. At the highest level, it agrees with our thinking as expressed in the second of two articles in Statistical Science (Buja et al., 2019). The guiding principle is to focus on quantities of interest that are meaningful statistical functionals, beyond the statistical models that motivate them, even when those models are fully misspecified. In some form, this focus has existed for decades in the semi-parametric literature. We…

Pallavi Basu 对《广义线性模型参数的弱假设推断》的讨论AI 解读

The authors propose an ingenious way to improve on providing inference for the main and interaction effects for generalised linear model parameters. With the use of the efficient influence function, they can extend the allowable bias introduced by machine learning estimators up to op(n −1/4). Noting that cross-fitting has been suggested to counter the Donsker condition, it may be a useful alternative to contrast with machine learning estimates, averages over sample splits or…

Stensrud 与 Sarvet 对《广义线性模型参数的弱假设推断》的讨论AI 解读

We congratulate Vansteelandt and Dukes (V & D) with their innovative and interesting article. Here we further explore the interpretation of V & D’s main effects estimand. An algorithm for causal inference. There has been tremendous progress in causal inference by approaching causal queries in the following way (Hernan & Robins, 2020; Richardson & Robins, 2013; Robins, 1986): Choose a causal target: an estimand that corresponds to a scientific question of interest (usually a…

彭鼎对《广义线性模型参数的弱假设推断》的讨论AI 解读

I want to congratulate the authors on a thought-provoking paper on statistical inference with misspecified models. It deepens our understanding of the role of models in causal inference. I offer two comments. Comparison of the conditional and marginal estimands based on 105 Monte Carlo samples. The parameters of the distributions of L and Y are all drawn independently from Uniform(0, 1) The authors provide inspiring derivations of the novel average effect and interaction…

《广义线性模型参数的弱假设推断》讨论与致谢附议AI 解读

In my view, one of the most important contributions of the field of causal inference has been to place the target of inference, the desired estimand, at the centre of the analysis. The estimand is chosen in view of the research question, and typically reflects what decision problem we need to solve or what our ideal (target) trial would be. Crucially, the (causal) estimand is not automatically a parameter that happens to parametrise a chosen model. The role of models is…

多个因果有序中介变量下的因果中介分析半参数估计AI 解读

Abstract Causal mediation analysis concerns the pathways through which a treatment affects an outcome. While most of the mediation literature focuses on settings with a single mediator, a flourishing line of research has examined settings involving multiple mediators, under which path-specific effects (PSEs) are often of interest. We consider estimation of PSEs when the treatment effect operates through K(≥ 1) causally ordered, possibly multivariate mediators. In this…

条件矩模型的贝叶斯估计与比较AI 解读

Abstract We consider the Bayesian analysis of models in which the unknown distribution of the outcomes is specified up to a set of conditional moment restrictions. The non-parametric exponentially tilted empirical likelihood function is constructed to satisfy a sequence of unconditional moments based on an increasing (in sample size) vector of approximating functions (such as tensor splines based on the splines of each conditioning variable). For any given sample size,…

货币政策沟通及其对家庭通胀预期的影响AI 解读

We study how different forms of communication influence inflation expectations in a randomized controlled trial using nearly 20,000 US individuals. We elicit individuals’ inflation expectations and then provide eight different forms of information regarding inflation. Reading the actual Federal Open Market Committee (FOMC) statement has about the same average effect on expectations as simply being told about the Federal Reserve’s inflation target. Reading news articles about…

利用多个可能无效的工具变量构造证据因子AI 解读

Valid instrumental variables enable treatment effect inference even when selection into treatment is biased by unobserved confounders. When multiple candidate instruments are available, but some of them are possibly invalid, the previously proposed reinforced design enables one or more nearly independent valid analyses that depend on very different assumptions. That is, we can perform evidence factor analysis. However, the validity of the reinforced design depends crucially…

双重去偏 lasso：隐藏混杂下的高维推断AI 解读

Inferring causal relationships or related associations from observational data can be invalidated by the existence of hidden confounding. We focus on a high-dimensional linear regression setting, where the measured covariates are affected by hidden confounding and propose the doubly debiased lasso estimator for individual components of the regression coefficient vector. Our advocated method simultaneously corrects both the bias due to estimation of high-dimensional…

信号、工具变量与首席财务官决策AI 解读

Building parable economies embedding econometricians, we view alternative estimators (Instrumental variables, fuzzy regression discontinuity, natural experiments, OLS, event studies) from the perspective of privately informed decision-makers, e.g., CFOs. Instrumental variable estimates can be misleading since randomization through observable instruments eliminates signal content arising from discretion. If the goal is informing discretionary decisions, rather than predicting…

早年饥荒暴露、饥饿回忆与晚年健康AI 解读

Abstract We use newly collected individual‐level hunger recall information from the China Family Panel Survey to estimate the causal effect of undernourishment on later‐life health. We develop a two‐sample instrumental variable (TSIV) estimator that can deal with heterogeneous samples. We find a nonlinear relationship between mortality rates, a commonly used famine indicator, and the individual hunger experience. The nonlinearity in famine exposure may explain the variation…

重新评估瑞典综合学校改革：教育与收入效应AI 解读

Summary We revisit a Swedish comprehensive school reform first evaluated by Meghir and Palme (2005). This reform increased years of schooling and abolished tracking. We extend the original analysis to the full population and introduce an improved education measure. Our results confirm the original overall finding of small average earnings effects. However, we find considerably larger increases in educational attainment and no evidence of decreased labor earnings for students…

高维半监督学习：寻求均值的最优推断AI 解读

Summary A fundamental challenge in semi-supervised learning lies in the observed data’s disproportional size when compared with the size of the data collected with missing outcomes. An implicit understanding is that the dataset with missing outcomes, being significantly larger, ought to improve estimation and inference. However, it is unclear to what extent this is correct. We illustrate one clear benefit: root-$n$ inference of the outcome’s mean is possible while only…

利用汇总关联统计量估计遗传相关性AI 解读

Summary Genome-wide association studies have identified thousands of genetic variants that are associated with complex traits. Many complex traits are shown to share genetic etiology. Although various genetic correlation measures and their estimators have been developed, rigorous statistical analysis of their properties, including their robustness to model assumptions, is still lacking. We develop a method of moments estimator of genetic correlation between two traits in the…

双重机器学习下的因果中介分析AI 解读

Summary This paper combines causal mediation analysis with double machine learning for a data-driven control of observed confounders in a high-dimensional setting. The average indirect effect of a binary treatment and the unmediated direct effect are estimated based on efficient score functions, which are robust with respect to misspecifications of the outcome, mediator, and treatment models. This property is key for selecting these models by double machine learning, which…