BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Signal Identification for Rare and Weak Features:  Higher Criticis
 m or False Discovery Rates - Prof. Korbinian Strimmer\, University of Leip
 zig
DTSTART:20130408T130000Z
DTEND:20130408T140000Z
UID:TALK44184@talks.cam.ac.uk
CONTACT:Dr Jack Bowden
DESCRIPTION:Signal identification in large-dimensional settings is a chall
 enging problem in biostatistics\, even more so if is the signal is very we
 ak.  For this purpose the method of "higher criticism" (HC) has recently b
 een powerfully advocated and shown to be highly effective for determining 
 appropriate decision thresholds.   On the other hand\, many omics studies 
 now routinely employ a variant of the "false discovery rate" (FDR) for scr
 eening for interesting features.\nIn my talk\, I will compare signal ident
 ification using the HC and FDR approaches\, with the aim to provide a bett
 er understanding of HC as well as offering a simple explanation for HC’s
  favorable performance. After a non-technical introduction to both the HC 
 and FDR approaches\, I will derive the ideal thresholds corresponding to t
 he HC and FDR criteria and explore their mutual relationships.  Subsequent
 ly\, it can be established that in a rare-weak setting there is a near ide
 ntity between the HC and a simple FDR threshold.  As a result\, the decisi
 on threshold obtained by the frequentist HC approach is given a natural Ba
 yesian interpretation.  This is joint work with Bernd Klaus\, EMBL Heidelb
 erg.\n
LOCATION:Large  Seminar Room\, 1st Floor\, Institute of Public Health\, Un
 iversity Forvie Site\, Robinson Way\, Cambridge
END:VEVENT
END:VCALENDAR