BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Simple Methods to Improve MCMC Efficiency in Random Effect Models 
 - Bill Brown (University of Bristol)
DTSTART:20081205T160000Z
DTEND:20081205T170000Z
UID:TALK14326@talks.cam.ac.uk
CONTACT:8419
DESCRIPTION:MCMC methods have continued to grow in popularity as their fle
 xibility\nin terms of the vast number of models they can fit is realised. 
 The\nfamily of MCMC algorithms is large and many applied researchers expos
 ure\nto MCMC methods is through their use of the default estimation method
 s\nprovided in software packages such as WinBUGS or MLwiN. Although these\
 npackages often try to optimize the steps of the algorithm they use to\nfi
 t particular models they can still produce algorithms that result in\npoor
 ly mixing chains. Many statistical methodologists produce model\nspecific 
 methods to improve mixing and create efficient MCMC algorithms\,\nbut for 
 this methodology to impact on the applied community it needs to\nbe implem
 ented in available software. One particular way to improve the\nefficiency
  of an MCMC algorithm is through model re-parameterisation.\nSome reparame
 terisation methods can be easily implemented by\nmodifications to the mode
 l code input into WinBUGS or via some\nforthcoming developments in MLwiN.\
 nIn this talk we describe briefly three such reparameterisation\ntechnique
 s\, hierarchical centering (Gelfand et al. 1995)\, parameter\nexpansion (L
 iu et al. 1998) and orthogonalisation of the fixed\npredictors (Browne et 
 al. submitted) which can be easily implemented in WinBUGS.  We will show\
 nhow these methods perform on a selection of random effect models applied
  to\nexamples from ecology\, veterinary epidemiology and demography.\n\n
LOCATION:MR12\, CMS\, Wilberforce Road\, Cambridge\, CB3 0WB
END:VEVENT
END:VCALENDAR