- Research Grants
graduate at Estatistica from Universidade Federal do Rio Grande do Sul (1984), master's at Probability and Statistics from Universidade de São Paulo (1991) and ph.d. at Probability and Statistics from Universidade de São Paulo (1997). Has experience in Probability and Statistics, focusing on Parametric Inference, acting on the following subjects: skew-normal distribution, calibration, bayesian inference, skew-t distribution and amostrador de gibbs. (Source: Lattes Curriculum)
This project aims to study associations among sets of variables using statistical methodologies based on regression models. In this context, we deal with topics that, in the statistical literature, are known as survival analysis, mixed models, beta regression models, item response theory, etc. In particular, we intend to study different formulations for such models, several estimation m...
(Only some records are available in English at this moment)
We will propor here a new multivariate link function, called skew-probit, to deal with longitudinal binary data. The main goal is to extend some results in the literature gave for multivariate logist and probit link, under Bayesian approach and also to develop efficient MCMC algorithms. Another interest is to work in variable selection under this binary regression model.
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
|Data from Web of Science|
(References retrieved automatically from State of São Paulo Research Institutions)
FARIAS, Rafael Bráz Azevedo. Modelos multivariados binários com funções de ligação assimétricas. Tese (Doutorado) - Instituto de Matemática e Estatística. Universidade de São Paulo (USP). São Paulo. (07/03598-3)