BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:1717@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20170424T153000
DTEND;TZID=Europe/Paris:20170424T163000
DTSTAMP:20170409T133000Z
URL:https://www.i2m.univ-amu.fr/evenements/variable-selection-for-mixed-da
 ta-clustering-a-model-based-approach/
SUMMARY: (...): Variable selection for mixed data clustering: a model-based
  approach
DESCRIPTION:: In this talk\, we consider two approaches for selecting varia
 bles in latent class analysis. The first approach consists in optimizing t
 he BIC with a modified version of the EM algorithm. This approach simultan
 eously performs both model selection and parameter inference.The second ap
 proach consists in maximizing the MICL\, which considers the clustering ta
 sk\, with an algorithm of alternate optimization. This approach performs m
 odel selection without requiring the maximum likelihood estimates for mode
 l comparison\, then parameter inference is done for the unique selected mo
 del. Thus\, both approaches avoid the computation of the maximum likelihoo
 d estimates for each model comparison. Moreover\, they also avoid the use 
 of the standard algorithms for variable selection which are often suboptim
 al (e.g. stepwise method) and computationally expensive. The case of data 
 with missing values is also discussed. The interest of both proposed crite
 ria is shown on a medical data sets describing 1300patients by 160000 vari
 ables.http://ms.mcmaster.ca/~marbacm/
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20170326T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR