BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semi Markov models under panel observation  - Andrew Titman\, Univ
 ersity of Lancaster
DTSTART:20130514T133000Z
DTEND:20130514T143000Z
UID:TALK44517@talks.cam.ac.uk
CONTACT:Dr Jack Bowden
DESCRIPTION:Multi-state models are widely used in event history analysis. 
 Often the state of the process is only known at a set of discrete\, potent
 ially unequally spaced and subject specific\, examination times leading to
  panel data. Most analyses for panel data assume a Markov model\, but we m
 ay instead wish to allow the transition intensities to depend on the time 
 spent in the current state leading to a semi-Markov model. The likelihood 
 for general semi-Markov models is somewhat intractable. This talk focuses 
 on semi-Markov models with phase-type sojourn distributions which allow an
  aggregated (or hidden) Markov representation making computation simpler. 
 Two main approaches can be considered. Firstly\, the states in the model c
 an be assumed to have phase-type distributions directly [1]. Alternatively
 \, phase-type distributions approximations to parametric distributions can
  be used to build an approximate likelihood for Weibull or Gamma semi-Mark
 ov models [2]. In either case\, the addition of misclassification of the d
 isease states can be incorporated relatively easily. The methods are illus
 trated on chronic disease data from post-lung-transplantation patients.\n\
 n[1] Titman A.C.\, Sharples L.D. Semi-Markov models with phase-type sojour
 n distributions. Biometrics. 2010. 66 (3): 742-752.\n[2] Titman A.C.  Esti
 mating parametric semi-Markov models from panel data using phase-type appr
 oximations. Statistics and Computing. 2012. Online First.\n\n\n
LOCATION:Large  Seminar Room\, 1st Floor\, Institute of Public Health\, Un
 iversity Forvie Site\, Robinson Way\, Cambridge
END:VEVENT
END:VCALENDAR