[ABE-L] Seminário"Modelos de Regressão e Aplicações" - Celso Cabral, sexta, 11h, IME-USP

[Silvia Ferrari]

*Seminário - Projeto Temático: Modelos de Regressão e Aplicações*



*Título: *Multivariate Measurement Error Models Based on Student-t
Distribution Under Censored Responses



*Palestrante: *Celso R. B. Cabral, Depto. de Estatística, Universidade
Federal do Amazonas



*Quando: *21 de agosto, sexta-feira, às 11h.



*Onde: *Auditório Jacy Monteiro, Bloco B, piso térreo - IME-USP



*Resumo*. Measurement error models constitute a wide class of models, that
include linear and nonlinear regression models, very useful to model many
real life phenomena, in particular in the medical and biological areas. The
great advantage of this type of models is that, in some sense, they can be
represented as mixed effects models, allowing to us the implementation of
well-known techniques, as the EM-algorithm for the parameter estimation. In
this work, we consider the study of a class of multivariate measurement
error models where the observed response and/or the covariate is not fully
observed, or in other words, the observations are subjected to certain
threshold values below or above which the measurements are not
quantifiable. Consequently, these observations are considered as censored.
We assume a Student-t distribution as the distribution of the unobserved
true value of the covariate and the error term of the model, providing a
robust alternative to parameter estimation. Our approach relies on a
likelihood-based inference using the EM-algorithm. The proposed method is
illustrated through a simulation study and a real data set.



Joint work with Larissa A. Matos (UNICAMP), Luis M. Castro (Universidad de
Concepción) and Víctor H. Lachos (UNICAMP)
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <https://lists.ime.usp.br/archives/abe/attachments/20150817/42737df2/attachment.html>