The Finite Mixture Model: some theory and applications
Hemant Ishwaran
Biostatistics, Cleveland Clinic Foundation
Refreshments: 3:30 - 4:00 p.m. Friday,
December 3, at 327 Yost Talk: 4:00 - 5:00 p.m. Friday, December 3, at 327 Yost.
The finite mixture model has been the subject of much interest in
statistics, with research on the topic going as far back as Robbins
(1950) and Kiefer and Wolfowitz (1956). I will present a general
overview on this topic focusing on the topics of: (i) identification,
(ii) the nonparametric MLE, (iii) classical methods of computation
such as the EM algorithm (and if time permits gradient based
algorithms), and (iv) Bayesian nonparametric computation with
examples. Part (iv) will reflect some of my recent research, although
I plan to only discuss general details and will focus on the use of
some interesting examples to illustrate these methods.
Questions? Nidhan Choudhuri