FDR control for multiple hypothesis testing on composite nulls
From MaRDI portal
Abstract: Multiple hypothesis testing often involves composite nulls, i.e., nulls that are associated with two or more distributions. In many cases, it is reasonable to assume that there is a prior distribution on the distributions despite it is unknown. When the number of distributions under true nulls is finite, we show that under the above assumption, the false discover rate (FDR) can be controlled using -values computed under constraints imposed by the empirical distribution of the observations. Comparing to FDR control using -values defined as maximum significance level over all null distributions, the proposed FDR control can have substantially more power.
This page was built for publication: FDR control for multiple hypothesis testing on composite nulls
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6210433)
