PC Adjusted Testing for Low Dimensional Parameters

Authors Sohom Bhattacharya, Rounak Dey, Rajarshi Mukherjee

Publication date 22 September 2022

Minimax procedures in statistical decision theory (62C20) Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20)

Abstract: In this paper we consider the effect of high dimensional Principal Component (PC) adjustments while inferring the effects of variables on outcomes. This problem is particularly motivated by applications in genetic association studies where one performs PC adjustment to account for population stratification. We consider simple statistical models to obtain asymptotically precise understanding of when such PC adjustments are supposed to work in terms of providing valid tests with controlled Type I errors. We also verify these results through a class of numerical experiments.

This page was built for publication: PC Adjusted Testing for Low Dimensional Parameters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6411542)