01 Feb Multiple Testing Procedures-ONLINE
1:00 pm - 2:30 pm
statistics seminar | level: intermediate |
for questions related to this event, contact email@example.com
affiliation: Ghent University
Multiple testing refers to any instance that involves the simultaneous testing of more than one hypothesis. If
decisions about the individual hypotheses are based on the unadjusted marginal p-values, then there is typically a
large probability (typically 5% if all null hypothesis are true) that some of the true null hypotheses will be rejected.
Unfortunately, such a course of action is still common. In this seminar, the problem of multiple testing will be
formally introduced and methods used for their correction will be discussed. More specifically, we introduce
Family wise error rate (FWER) adjustments for medium scale data mining and False discovery rate ( FDR) for megascale
data mining. Multiplicity adjustments for non-parametric tests will also be considered.