Statistical Inference for Maximin Effects: Identifying Stable Associations across Multiple Studies
Author:
Open Access
- 4 August 2023
- journal article
- research article
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 119 (547) , 1-17
Abstract
Integrative analysis of data from multiple sources is critical to making generalizable discoveries. Associations consistently observed across multiple source populations are more likely to be generalized to target populations with possible distributional shifts. In this paper, we model the heterogeneous multi-source data with multiple high-dimensional regressions and make inferences for the maximin effect (Meinshausen, Bühlmann, AoS, 43(4), 1801-1830). The maximin effect provides a measure of stable associations across multi-source data. A significant maximin effect indicates that a variable has commonly shared effects across multiple source populations, and these shared effects may be generalized to a broader set of target populations. There are challenges associated with inferring maximin effects because its point estimator can have a non-standard limiting distribution. We devise a novel sampling method to construct valid confidence intervals for maximin effects. The proposed confidence interval attains a parametric length. This sampling procedure and the related theoretical analysis are of independent interest for solving other non-standard inference problems. Using genetic data on yeast growth in multiple environments, we demonstrate that the genetic variants with significant maximin effects have generalizable effects under new environments. The proposed method is implemented in the package Maximininfer available from CRAN.
Keywords
All Related Versions
Funding Information
- NSF DMS (1811857, 2015373)
- NIH (R01GM140463, R01LM013614)
This publication has 57 references indexed in Scilit:
- Saccharomyces Genome Database: the genomics resource of budding yeastNucleic Acids Research, 2011
- Replication in Genome-Wide Association StudiesStatistical Science, 2009
- Simultaneous analysis of Lasso and Dantzig selectorThe Annals of Statistics, 2009
- Likelihood ratio tests and singularitiesThe Annals of Statistics, 2009
- Direct Density Ratio Estimation for Large-scale Covariate Shift AdaptationJournal of Information Processing, 2009
- DEG 5.0, a database of essential genes in both prokaryotes and eukaryotesNucleic Acids Research, 2008
- Inconsistency of the Bootstrap when a Parameter is on the Boundary of the Parameter SpaceEconometrica, 2000
- R. A. Fisher and Fiducial ArgumentStatistical Science, 1992
- Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests under Nonstandard ConditionsJournal of the American Statistical Association, 1987
- Bootstrap Methods: Another Look at the JackknifeThe Annals of Statistics, 1979