SEMINARIO/Estatistica/Unicamp

[dias <dias@ime.unicamp.br>]

Prezados,

Nesta sexta, 13 de março as 10hs, sala 221(IMECC) teremos o seminario do 
Prof. Rolando de la Cruz. Contamos com sua presença. Obrigado,

Ronaldo

Title: Bayesian parametric and semiparametric approaches to joint modeling
a primary endpoint and longitudinal measurements

Summary:

In many studies the association of longitudinal measurements
of a continuous response and a primary endpoint are often of interest.
A convenient framework for this type of problems is joint models, which
are formulated to investigate the association between a primary
endpoint and features of longitudinal measurements through a common set
of latent random effects. The joint model, which is the focus of
this talk, is a logistic regression model with covariates defined as the
subject-specific random effects in a non-linear random effects
model for the longitudinal measurements. We discuss parametric
and non-parametric priors on random effects. The proposed
methods are illustrated using a real dataset where
the objective is to study the association between longitudinal hormone
levels and the
pregnancy outcome in a group of young women.


Dr. Rolando De la Cruz
Departamento de Salud Pública
Facultad de Medicina
Pontificia Universidad Católica de Chile
Marcoleta 434, Casilla 114D
Santiago, CHILE

begin:vcard
fn:Ronaldo Dias
n:Dias;Ronaldo
org:University of Campinas;Statistics
adr:;;;Campinas;SP;;Brazil
email;internet:dias@ime.unicamp.br
title:Associate Professor
url:www.ime.unicamp.br/~dias
version:2.1
end:vcard