BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Dynamic predicting by landmarking as an alternative for multi-stat
 e modeling: an application to acute lymphoid leukemia data - Hans van Houw
 elingen\, Leiden University Medical Center\, Netherlands
DTSTART:20080506T133000Z
DTEND:20080506T143000Z
UID:TALK8547@talks.cam.ac.uk
CONTACT:Nikolaos Demiris
DESCRIPTION:We consider the problem of obtaining a dynamic prediction for 
 5 year failure free survival after bone marrow transplantation in ALL pati
 ents using data from the EBMT\, the  European Group for Blood and Marrow T
 ransplantation . We will compare our recently developed landmark methodolo
 gy [1] and the established multi-state modeling as described in a recent T
 utorial in Biostatistics in Statistics in Medicine by Putter et al. [2].  
 As expected the two approaches give similar results. The landmark methodol
 ogy does not need complex modeling and leads to easy prediction rules. On 
 the other hand\, it does not give the insight in the biological processes 
 as obtained for the multi-state model.\n\nReferences\n\nVan Houwelingen HC
  (2007). Dynamic prediction by landmarking in event history analysis. Scan
 d J Statist 34:70–85.\n\nPutter H\, Fiocco M\, Geskus RB (2007) Tutorial
  in biostatistics: competing risks and multi-state models. Stat Med 26:238
 9–2430.
LOCATION:Large Seminar Room\, 1st Floor\, Institute of Public Health\, Uni
 versity Forvie Site\, Robinson Way\, Cambridge
END:VEVENT
END:VCALENDAR