BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251122T130029EST-0342OGGEIF@132.216.98.100
DTSTAMP:20251122T180029Z
DESCRIPTION:Copula-Based Logistic Regression Estimation.\n\nIn this talk a 
 new methodology of estimating the predictive probability in a logistic reg
 ression setting is explored. The idea consists in writing this latter in t
 erms of conditional copula and marginal distributions. The approach develo
 ping here constitute\, first\, selecting a parametric family of copula tha
 t describes better the data at hand\, and estimating non parametrically th
 e marginal distributions\, sub- sequently\, we use the plug-in method to b
 uild an estimate of the desired probability either in a binary case or mul
 tinomial one. The availability of a rich family of copula\, a various good
 ness-of-fit test and a nonparametric estimation of the marginal makes the 
 approach more flexible. The asymptotic properties related to these estimat
 ors are provided. Finally\, a simulated study is carried out to evaluate t
 he performance of the newly proposed procedure\, besides the burn injury d
 ata are analyzed to show the flexibility of our method. Joint work with Pr
 ofessors\, Mhamed Mesfioui from UQTR and Taoufik Bouezmarni from Universit
 é de Sherbrooke.\n
DTSTART:20180125T200000Z
DTEND:20180125T210000Z
LOCATION:Room PK-5115 \, CA\, Pavillon President-Kennedy
SUMMARY:Mohamed Belalia\, UQAM
URL:/mathstat/channels/event/mohamed-belalia-uqam-2839
 77
END:VEVENT
END:VCALENDAR