BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Improved conditional approximations of the population Fisher infor
 mation matrix - Nyberg\, J (Uppsala)
DTSTART:20110812T104500Z
DTEND:20110812T113000Z
UID:TALK32334@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:We present an extended approximation of the Fisher Information
  Matrix (FIM) for nonlinear mixed effects models based on a first order co
 nditional (FOCE) approximation of the population likelihood. Unlike previo
 us FOCE based FIM\, we use the empirical Bayes estimates to derive the FIM
 . In several examples\, compared to the old FOCE based FIM\, the improved 
 FIM predicts parameter uncertainty much closer to simulation based empiric
 al parameter uncertainty. Furthermore\, this approach seems more robust ag
 ainst other approximations of the FIM\, i.e. (Full/Reduced FIM). Finally\,
  the new FOCE derived FIM is slightly closer to the simulated empirical pr
 ecision than the FO based FIM.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR