Research Seminars

Integrative High Dimensional Inference with Heterogeneity under Data Sharing Constraints

Speaker:Prof. Yin XIA,Fudan University

Time:Nov 26, 2020, 16:00-17:00

Location:Tencent Meeting ID: 919 850 940

报告简介  Abstract

Evidence based decision making often relies on meta-analyzing multiple studies, which enables more precise estimation and investigation of generalizability. Integrative analysis of multiple heterogeneous studies is, however, highly challenging in the high dimensional setting. The challenge is even more pronounced when the individual level data cannot be shared across studies due to privacy concerns. Under ultra high dimensional sparse regression models and the constraint of not sharing individual data across studies, we propose in this talk a novel integrative estimation procedure by Aggregating and Debiasing Local Estimators (ADeLE). The ADeLE procedure protects individual data through summary-statistics-based integrating procedure, accommodates between study heterogeneity in both the covariate distribution and model parameters, and attains consistent variable selection. Furthermore, the prediction and estimation errors incurred by aggregating derived data is negligible compared to the statistical minimax rate. In addition, the ADeLE estimator is shown to be asymptotically equivalent in prediction and estimation to the ideal estimator obtained by sharing all data. Furthermore, we propose a novel data shielding integrative large-scale testing approach to signal detection by allowing between study heterogeneity and not requiring sharing of individual level data. Assuming the underlying high dimensional regression models of the data differ across studies yet share  similar support, the proposed method incorporates proper integrative estimation and debiasing procedures to construct test statistics for the overall effects of specific covariates. We also develop a multiple testing procedure to identify significant effects while controlling the false discovery rate and false discovery proportion. The new method is applied to a real example on detecting interaction effect of the genetic variants for statins and obesity on the risk for type II diabetes.


嘉宾简介  About the Speaker

夏寅,复旦大学管理学院教授,博导,2013年博士毕业于宾夕法尼亚大学,2013-2016年在美国北卡大学教堂山分校任tenure track Assistant Prof。2016年入选中组部千人计划青年项目;2020年获得国家自科基金优秀青年基金资助。研究方向包括高维统计推断、大范围检验及应用等。在JASA, AOS, JRSSB, Biometrika等期刊上发表多篇论文。


讲座海报 Poster

1. 统计数科学术讲座-夏寅教授.jpg