BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Bringing Closure to False Discovery Rate Control: A General Princi
 ple for Multiple Testing
DTSTART:20260424T151500
DTEND:20260424T161500
DTSTAMP:20260414T065857Z
UID:b5b51d012b95007f74a90fca4a1db4cd537a51056ee4eb525e0fdea9
CATEGORIES:Conferences - Seminars
DESCRIPTION:Jelle Goeman\, University of Leiden\nWe present a novel necess
 ary and sufficient principle for multiple testing methods controlling an e
 xpected loss. This principle asserts that every such multiple testing meth
 od is a special case of a general closed testing procedure based on e-valu
 es. It generalizes the Closure Principle\, known to underlie all methods c
 ontrolling familywise error and tail probabilities of false discovery prop
 ortions\, to a large class of error rates -- in particular to the false di
 scovery rate (FDR). By writing existing methods as special cases of this p
 rocedure\, we can achieve uniform improvements\, as we demonstrate for the
  e-Benjamini-Hochberg and the Benjamini-Yekutieli procedures\, and the sel
 f-consistent method of Su (2018). We also show that methods derived using 
 our novel e-Closure Principle generally control their error rate not just 
 for one rejected set\, but simultaneously over many\, allowing post hoc fl
 exibility for the researcher.\nMoreover\, we show that because all multipl
 e testing methods for all error metrics are derived from the same procedur
 e\, researchers may even choose the error metric post hoc. Under certain c
 onditions\, this flexibility even extends to post hoc choice of the nomina
 l error rate.\n\n\n 
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR