Confounder adjustment in multiple hypothesis testing

Abstract

Confounding introduces hidden bias to the statistical inference. We show in modern simultaneous testing, it is possible to correct for unmeasured confounders. Previous methods including SVA, LEAPP, RUV are unified in the same framework in this paper. Interestingly, confounder adjustment is as efficient as the oracle linear regression when latent variables are strong.

Publication
Annals of Statistics (2017)
comments powered by Disqus