BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Lecture on modelling: Mixed effects non-linear and generalized lin
 ear models - Bates\, D (Wisconsin-Madison)
DTSTART:20110809T083000Z
DTEND:20110809T093000Z
UID:TALK32309@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Mixed-effects models are defined by the distributions of two v
 ector-valued random variables\, an n-dimensional response vector\, Y and a
 n unobserved q-dimensional random-effects vector\, B. The mean of the cond
 itional distribution\, Y|B=b\, depends on a linear predictor expression of
  the form X+Zb where  is a p-dimensional fixed-effects parameter vector an
 d the fixed and known model matrices\, X and Z\, are of the appropriate di
 mension. For linear mixed-effects models the conditional mean is the linea
 r predictor\; for generalized linear mixed-effects models the conditional 
 mean is the value of an inverse link function applied to the linear predic
 tor and for a nonlinear mixed-effects model the conditional mean is the re
 sult of applying a nonlinear model function for which the parameter vector
  is derived from the linear predictor.\nWe describe the formulation of the
 se mixed-effects models and provide computationally effective expressions 
 for the profiled deviance function through which the maximum likelihood pa
 rameter estimates can be determined. In the case of the linear mixed-effec
 ts model the profiled deviance expression is exact. For generalized linear
  or nonlinear mixed-effects models the profiled deviance is approximated\,
  either through a Laplace approximation or\, at the expense of somewhat gr
 eater computational effort\, through adaptive Gauss-Hermite quadrature.\n\
 n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR