| Full text | |
| Author(s): |
Castro, Luis M.
;
Lachos, Victor H.
;
Ferreira, Guillermo P.
;
Arellano-Valle, Reinaldo B.
;
Stern, JM
;
Lauretto, MD
;
Polpo, A
;
Diniz, MA
Total Authors: 8
|
| Document type: | Journal article |
| Source: | XI BRAZILIAN MEETING ON BAYESIAN STATISTICS (EBEB 2012); v. 1490, p. 12-pg., 2012-01-01. |
| Abstract | |
Regression models where the dependent variable is censored (limited) are usually considered in statistical analysis. Particularly, the case of a truncation to the left of zero and a normality assumption for the error terms is studied in detail by [1] in the well known Tobit model. In the present article, this typical censored regression model is extended by considering a partial linear model with errors belonging to the class of scale mixture of normal distributions. We achieve a fully Bayesian inference by adopting a Metropolis algorithm within a Gibbs sampler. The likelihood function is utilized to compute not only some Bayesian model selection measures but also to develop Bayesian case-deletion influence diagnostics based on the q-divergence measures. We evaluate the performances of the proposed methods with simulated data. In addition, we present an application in order to know what type of variables affect the income of housewives. (AU) | |
| FAPESP's process: | 11/17400-6 - Applications of the scale mixture of Skew-Normal distributions in linear mixed effects models |
| Grantee: | Víctor Hugo Lachos Dávila |
| Support Opportunities: | Regular Research Grants |