Advanced search
Start date
Betweenand

Modelling overdispersion for discrete data

Grant number: 12/21389-0
Support Opportunities:Research Grants - Visiting Researcher Grant - International
Start date: January 15, 2013
End date: January 24, 2013
Field of knowledge:Physical Sciences and Mathematics - Probability and Statistics - Applied Probability and Statistics
Principal Investigator:Clarice Garcia Borges Demétrio
Grantee:Clarice Garcia Borges Demétrio
Visiting researcher: Célestin Clotaire Kokonendji
Visiting researcher institution: Université de Franche-Comté (UFC), France
Host Institution: Escola Superior de Agricultura Luiz de Queiroz (ESALQ). Universidade de São Paulo (USP). Piracicaba , SP, Brazil

Abstract

The purpose of the project is to investigate the practical use of regression models based on Poisson-Tweedie mixtures, and investigate the merits of such an approach for modelling over-/under dispersed discrete data. We will first investigate model …fitting by means of quasi-likelihood estimation and Pearson estimating functions, and investigate the practical usefulness of such an approach. We will then investigate the possibility of using maximum likelihood estimation for the Poisson-Tweedie mixtures, including a comparison with quasi-likelihood estimation and an investigation of the efficiency of the latter. The investigation involves simulation of the Poisson-Tweedie mixtures, which is relatively easy because of the availability of good simulation procedures for Tweedie distributions (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

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)
ZOCCHI, SILVIO S.; KOKONENDJI, CELESTIN C.. On General Continuous Triangular and Two-sided Power Distributions. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, v. 44, n. 14, p. 3099-3106, . (12/21389-0)