Mixed regression models for bivariate skew continuous and binary data

• Grant number: 15/25867-2
• Support Opportunities: Scholarships in Brazil - Master
• Start date: May 01, 2016
• End date: February 28, 2018
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Caio Lucidius Naberezny Azevedo
• Grantee: Mayara Caroline Maioli
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 12/21788-2 - Regression models and applications, AP.TEM

Abstract

In this project we will develop a clas of mixed regression models for bivariate responses where one variable is continuous and modeled by a skew centered normal distribution, whereas the other is binary (dichotomous). Furthermore, for the binary response, we will use a link function based on the cumulative distribution function of the skew centered normal distribution. To consider the dependence structure between the two response variables, we will use a common structure of random effects which will assumed to follow a multivariate skew centered normal distribution. Also, we will use an augmented data structure for the binary response, as well as suitable stochastic representations for both univariate and multivariate skew normal distributions, for parameter estimation and model fit assessment. Furthermore, the Bayesian paradigm, through MCMC algorithms, it will be considered for parameter estimation as well as for model fit assessment and for comparison of the competing models. All developments will be implemented in the R package. Simulation studies as well as real data analysis will be considered to illustrate the developed methodologies. (AU)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

MAIOLI, Mayara Caroline. Modelos de regressão univariados e bivariados baseados nas distribuições de mistura de escala normal assimétrica sob a parametrização centrada. 2018. Master's Dissertation - Universidade Estadual de Campinas (UNICAMP). Instituto de Matemática, Estatística e Computação Científica Campinas, SP.