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:4968@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20231120T140000
DTEND;TZID=Europe/Paris:20231120T150000
DTSTAMP:20240524T072506Z
URL:https://www.i2m.univ-amu.fr/evenements/a-monte-carlo-em-for-the-poisso
 n-log-normal-model/
SUMMARY: (...): A Monte Carlo EM for the Poisson Log-Normal Model
DESCRIPTION:: The Poisson log-normal (PLN) model is a generic model for the
  joint distribution of count data\, accounting for covariates. It is also 
 an incomplete data model. A classical way to achieve maximum likelihood in
 ference for model parameters 𝜃 is to resort to the EM algorithm\, which
  aims at maximising\, with respect to 𝜃\, the conditional expectation\,
  given the observed data 𝑌\, of the so-called complete log-likelihood. 
 Unfortunately\, the evaluation of the latter is intractable in the case of
  the PLN model because the conditional distribution of the latent vector c
 onditionally on the corresponding observed count vector has no closed form
  and none of its moments can be evaluated in an efficient manner. Variatio
 nal approaches have been studied to tackle this problem but lack from stat
 istical guarantees. Indeed the resulting estimate does not enjoy the gener
 al properties of MLEs. In particular\, its (asymptotic) variance is unknow
 n\, so no test nor confidence interval can be derived easily from the vari
 ational inference. Starting from already available variational approximati
 ons\, we define a first Monte Carlo EM algorithm to obtain maximum likelih
 ood estimators of this model. We then extend this first algorithm to the c
 ase of a composite likelihood in order to be able to handle higher dimensi
 onal count data. Both methods are statically grounded and provide confiden
 ce region for model parameters.
CATEGORIES:Séminaire,Statistique
LOCATION:Saint-Charles - FRUMAM  (2ème étage)\, 3 Place Victor Hugo\, Mar
 seille\, 13003\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=3 Place Victor Hugo\, Marse
 ille\, 13003\, France;X-APPLE-RADIUS=100;X-TITLE=Saint-Charles - FRUMAM  (
 2ème étage):geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR