BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A novel emulation-based algorithm for likelihood-free model calibr
 ation - Helen Johnson\, LSHTM
DTSTART:20130429T103000Z
DTEND:20130429T113000Z
UID:TALK41118@talks.cam.ac.uk
CONTACT:Prof. Julia Gog
DESCRIPTION:Models are applied widely in the biological sciences and elsew
 here but their usefulness depends on the quality of calibration to observe
 d data. Stochastic individual-based models are becoming more popular but t
 heir calibration is beset by two particular difficulties: likelihood intra
 ctability and high computational expense. To overcome both these limitatio
 ns\, we develop a novel adaptive emulation-based calibration algorithm. We
  apply the algorithm to a deterministic HPV-16 model and compare the resul
 ts with full MCMC before extending its application to a stochastic individ
 ual-based model of HPV-16. It works well in both cases\, fitting the model
  to the observed data and inferring similar parameter values as the full M
 CMC analysis (but with lower variance). It also provides similar estimates
  of the mean and variance values of inferred parameters for both the deter
 ministic and stochastic models. 
LOCATION:DD47\, Cripps Court\, Queens' College
END:VEVENT
END:VCALENDAR