BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Lectures & Presentations
DESCRIPTION:Presenter: Jonathan R. Bradley\, Associate Professor in the Dep
artment of Statistics at Florida State University\n\nMarkov chain Monte Car
lo (MCMC) has become a standard in Bayesian statistics that allows one to g
enerate dependent replicates from a posterior distribution for general Baye
sian hierarchical models. However\, convergence issues\, tuning\, and the e
ffective sample size of the MCMC are nontrivial considerations that are oft
en overlooked or can be difficult to assess. This motivates us to consider
finding expressions of the posterior distribution that are computationally
straightforward to sample from directly (i.e.\, independently) without MCMC
. We focus on a broad class of Bayesian generalized linear mixed-effects mo
dels (GLMM) that allows one to jointly model data without the use of MCMC.
We derive a class of conjugate distributions that allows one to specify the
prior on fixed and random effects to be any conjugate multivariate distrib
ution. The expression of the posterior distribution is given\, and direct s
imulations have an efficient projection form. Several examples are presennt
ed in the context of spatial GLMMs including spatial basis function expansi
ons\, weakly stationary spatial process models\, and conditional autoregres
sive models.\n\nAbout the speaker: Jonathan R. Bradley received his Ph.D. f
rom The Ohio State University in 2013. He is now an Associate professor at
Florida State University's Department of Statistics. His primary interests
include Bayesian analysis and spatio-temporal statistics with applications
to environmental processes and to official statistics.
DTEND:20230207T010500Z
DTSTAMP:20240915T061929Z
DTSTART:20230207T000000Z
LOCATION:
SEQUENCE:0
SUMMARY: Exact MCMC-free Bayesian Inference for a Class of Generalized Line
ar Mixed Effects Models with Application to Spatial Data
UID:tag:localist.com\,2008:EventInstance_42210615256428
URL:https://calendar.ucsc.edu/event/exact_mcmc-free_bayesian_inference_for_
a_class_of_generalized_linear_mixed_effects_models_with_application_to_spat
ial_data
END:VEVENT
END:VCALENDAR