Towards Efficient Bias Correction in Data Snooping

实现数据窥探中的有效偏差校正

• 批准号: 1914496
• 负责人: Xuming He
• 金额: $ 25万
• 依托单位: Regents of the University of Michigan - Ann Arbor
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1914496&HistoricalAwards=false
• 关键词: Towards; Efficient; Bias; Correction; Data

The choice of a statistical model is often a critical part of data analysis because a useful model helps researchers extract relevant information from noisy data to reach interpretable findings. While scientific or economic theories do help formulate models in some applications, most data analysts have to rely on empirical models. Using the same data to select a model and then to perform model-based statistical inference is commonly known as data snooping. Unfortunately, data snooping is intrinsically risky without a careful analysis of the potential bias resulting from such practices. The primary goal of this project is to study how to understand and correct bias from data snooping and develop sound statistical inference methods. The research will provide valuable tools for scientists, researchers, and policy makers who rely on data-driven models for uncertainty assessment and confirmatory data analysis.This project focuses on regression-adjusted inference on treatment effects and inference on the best selected subgroup. The proposed work is motivated by the pressing need for more fundamental research related to the handling of "post-selection bias" in statistical analysis. The repeated data-splitting method for de-biased inference on a structural parameter (for example, the average treatment effect) enables efficient bias removal in addressing an intrinsic scientific question. The proposed inference on the best selected subgroup provides a bias-correction to a natural estimate of the subgroup effect size, and therefore reduces the risk of data-snooping and false discoveries in subgroup analysis. In the big data era, data-driven models and subgroup analyses are often used to take advantage of anticipated sparsity in the data structure or to explore data heterogeneity. The proposed research aims to provide insights, theory, and tools for more informed decision making in such endeavors. The project will involve collaborations with researchers investigating the risk of concussion as well as scientists in the biotechnology industry who routinely rely on subgroup analysis. Graduate and undergraduate students will be engaged in the proposed research.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

统计模型的选择通常是数据分析的关键部分，因为一个有用的模型可以帮助研究人员从嘈杂的数据中提取相关信息，以获得可解释的发现。虽然科学或经济理论确实有助于在某些应用中制定模型，但大多数数据分析师必须依赖经验模型。使用相同的数据来选择模型，然后执行基于模型的统计推断，这通常被称为数据窥探。不幸的是，如果不仔细分析这种做法造成的潜在偏见，数据窥探本质上是有风险的。本项目的主要目标是研究如何从数据窥探中理解和纠正偏见，并开发合理的统计推断方法。该研究将为依赖数据驱动模型进行不确定性评估和验证性数据分析的科学家、研究人员和政策制定者提供有价值的工具。本项目侧重于对治疗效果的回归校正推断和对最佳选择亚组的推断。提出这项工作的动机是迫切需要更多与处理统计分析中的“后选择偏差”相关的基础研究。对结构参数（例如，平均处理效果）进行去偏推理的重复数据分割方法可以在解决内在科学问题时有效地去除偏倚。所提出的关于最佳选择子组的推断为子组效应大小的自然估计提供了偏差校正，因此降低了子组分析中数据窥探和错误发现的风险。在大数据时代，数据驱动模型和子组分析通常用于利用数据结构中预期的稀疏性或探索数据异质性。提出的研究旨在为这些努力中更明智的决策提供见解，理论和工具。该项目将包括与调查脑震荡风险的研究人员以及生物技术行业的科学家合作，他们通常依赖于亚组分析。研究生和本科生将参与拟议的研究。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Hypothesis Testing for Block-structured Correlation for High Dimensional Variables

• DOI: 10.5705/ss.202019.0319
• 发表时间: 2022
• 期刊: Statistica Sinica
• 影响因子: 1.4
• 作者: Shurong Zheng;Xuming He;Jianhua Guo

From regression rank scores to robust inference for censored quantile regression

• DOI: 10.1002/cjs.11740
• 发表时间: 2022-11
• 期刊: Canadian Journal of Statistics
• 作者: Yuan Sun;Xuming He

Inference on Selected Subgroups in Clinical Trials

• DOI: 10.1080/01621459.2020.1740096
• 发表时间: 2020-04-17
• 期刊: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• 影响因子: 3.7
• 作者: Guo, Xinzhou;He, Xuming
• 通讯作者: He, Xuming

Model-based bootstrap for detection of regional quantile treatment effects

基于模型的引导程序用于检测区域分位数治疗效果

• DOI: 10.1080/10485252.2021.1934465
• 发表时间: 2021
• 期刊: Journal of Nonparametric Statistics
• 影响因子: 1.2
• 作者: Sun, Yuan;He, Xuming
• 通讯作者: He, Xuming

Comments on "Two Cultures": What have changed over 20 years?

评《两种文化》：20年来发生了什么变化？

• DOI: 10.1353/obs.2021.0026
• 发表时间: 2021
• 期刊: Observational Studies
• 作者: He, Xuming;Wang, Jingshen
• 通讯作者: Wang, Jingshen