Regression and time series in modelling incomplete data

• Grant number: 14/13994-7
• Support type: Scholarships abroad - Research Internship - Post-doctor
• Effective date (Start): October 01, 2014
• Effective date (End): December 31, 2014
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics
• Principal Investigator: Víctor Hugo Lachos Dávila
• Grantee: Aldo William Medina Garay
• Supervisor abroad: Jacek Leśkow
• Home Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Local de pesquisa : Cracow University of Technology (CUT), Poland
• Associated to the scholarship: 13/21468-0 - Measurement error-in-variables models for censored data using scale mixtures of skew-normal distributions, BP.PD

Abstract

In recent years, the censored regression models, models with errors in variables, time series data or analysis of heavy tailed data can be signicantly improved and/or validated with thetechniques based on resampling. Thus, in each category of the modeling problems a fundamentalquestion is to be able to better study the nite-sample distributions of the introducedestimators. The emphasis of this research will be based mainly in the study and considerationof three very popular models:(A) The censored linear regression models for irregularly observed longitudinal data.(B) The time series model for nonstationary signals.(C) Inferential models for heavy tailed distributions. (AU)

Scientific publications

(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)

GARAY, ALDO M.; LACHOS, VICTOR H.; BOLFARINE, HELENO. Bayesian estimation and case influence diagnostics for the zero-inflated negative binomial regression model. Journal of Applied Statistics, v. 42, n. 6, p. 1148-1165, JUN 3 2015. Web of Science Citations: 2.