BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260123T204253EST-66830FgVAX@132.216.98.100
DTSTAMP:20260124T014253Z
DESCRIPTION:Order Selection in Multidimensional Finite Mixture Models\n\nAb
 stract: Finite mixture models provide a natural framework for analyzing da
 ta from heterogeneous populations. In practice\, however\, the number of h
 idden subpopulations in the data may be unknown. The problem of estimating
  the order of a mixture model\, namely the number of subpopulations\, is t
 hus crucial for many applications. In this talk\, we present a new penaliz
 ed likelihood solution to this problem\, which is applicable to models wit
 h a multidimensional parameter space. The order of the model is estimated 
 by starting with a large number of mixture components\, which are clustere
 d and then merged via two penalty functions. Doing so estimates the unknow
 n parameters of the mixture\, at the same time as the order. We will prese
 nt extensive simulation studies\, showing our approach outperforms many of
  the most common methods for this problem\, such as the Bayesian Informati
 on Criterion. Real data examples involving normal and multinomial mixtures
  further illustrate its performance.\n\n \n\n \n
DTSTART:20170120T203000Z
DTEND:20170120T213000Z
LOCATION:room 1205\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Tudor Manole (Â鶹´«Ã½ÍøÕ¾)
URL:/mathstat/channels/event/tudor-manole-mcgill-unive
 rsity-265186
END:VEVENT
END:VCALENDAR