József Bukszár 

Title: Estimate of the individual effect sizes in
multiple-hypothesis testing problem and its applications

Abstract: We present a method that estimates the individual effect sizes (IES) in
multiple-hypothesis testing problem, where the effect size can be
interpreted as the unknown parameter of the test statistic distribution
of the alternative hypothesis. The IES estimates enable us to estimate the
posterior probability that a hypothesis is true null, i.e. the local
FDR, accurately. Techniques based on local FDR rather than on the less
informative false discovery rate (FDR) can be used now in some
applications, where inaccuracy of local FDR estimate has prevented these techniques
from being applied. This will be demonstrated on analysis of genome-wide
association data.

Joint work with Edwin J. C. G. van den Oord