Abstract
False Discovery Rate, Bayes and Multiple Comparisons
Jonathan Taylor
Stanford University
In this talk, we present an expository overview of a relatively new approach to the multiple comparisons problem in brain imaging: the False Discovery Rate (FDR). The FDR is particularly well suited to exploratory data analysis, as it allows for some Type I errors by focusing on the proportion of false positives among the total number of discoveries.
We also describe a Bayesian interpretation of the FDR, which implies that estimating the FDR is equivalent to estimating a posterior probability. This Bayesian perspective suggests new inferential procedures and highlights connections with existing approaches to the multiple comparisons problem in the literature.
We also describe a Bayesian interpretation of the FDR, which implies that estimating the FDR is equivalent to estimating a posterior probability. This Bayesian perspective suggests new inferential procedures and highlights connections with existing approaches to the multiple comparisons problem in the literature.
No video available