BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Model criticism in complex Bayesian evidence synthesis for infecti
 ous disease models - Anne Presanis\, MRC Biostatistics Unit
DTSTART:20110302T163000Z
DTEND:20110302T173000Z
UID:TALK29533@talks.cam.ac.uk
CONTACT:Richard Samworth
DESCRIPTION:Complex evidence synthesis (e.g. Ades & Sutton 2006) is increa
 singly being\nemployed in epidemiology to combine diverse data sources\, w
 ith the aim of\nestimating key characteristics of infectious diseases\, su
 ch as prevalence\nand incidence. Often this is carried out in a Bayesian f
 ramework\, to ease\nformulation of complex models and incorporate prior kn
 owledge. Model\ncriticism in complex evidence synthesis is a challenging a
 nd expanding area\nof research. I will give a broad introductory (but by n
 o means exhaustive)\noverview of the literature in this area\, discussing 
 inconsistency and\nconflict in evidence\, modelling bias\, identifiability
 \, model comparison and\nsensitivity analysis. I will illustrate some of t
 he ideas with examples from\nmy own work on HIV and pandemic influenza.\n\
 nA.E. Ades\, A.J. Sutton\nMultiparameter evidence synthesis in epidemiolog
 y and medical\ndecision-making:current approaches.\nJRSS (A)\, 169\, 5--35
 \, 2006.\n
LOCATION:MR5\, CMS
END:VEVENT
END:VCALENDAR