BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Implementing (Multiple) Monte Carlo Tests - Axel Gandy\, Imperial 
 College London
DTSTART:20131018T150000Z
DTEND:20131018T160000Z
UID:TALK47606@talks.cam.ac.uk
CONTACT:20082
DESCRIPTION:Consider Monte Carlo tests\, e.g. bootstrap tests or permutati
 on tests. Naive implementations can lead to decisions that depend mainly o
 n the simulation error and not on the observed data.  This talk will prese
 nt algorithms that solve this problem: for individual Monte Carlo tests as
  well as for multipe Monte Carlo tests with multiplicity correction such a
 s the Benjamini & Hochberg False Discovery Rate (FDR) procedure. The key p
 roperty of the presented algorithms is that\, with arbitrarily high probab
 ility\, the same decisions as the original procedure with the ideal p-valu
 es is reached.
LOCATION:MR12\,  Centre for Mathematical Sciences\, Wilberforce Road\, Cam
 bridge
END:VEVENT
END:VCALENDAR