Influence analysis for the generalized Waring regression model

Luisa Rivas; Manuel Galea

doi:10.1080/02664763.2019.1670148

Influence analysis for the generalized Waring regression model

J Appl Stat. 2019 Sep 26;47(1):1-27. doi: 10.1080/02664763.2019.1670148. eCollection 2020.

Authors

Luisa Rivas¹, Manuel Galea²

Affiliations

¹ Departamento de Estadística, Universidad de Concepción, Concepción, Chile.
² Departamento de Estadística, Pontificia Universidad Católica de Chile, Santiago, Chile.

Abstract

In this paper, we consider a regression model under the generalized Waring distribution for modeling count data. We develop and implement local influence diagnostic techniques based on likelihood displacement. Also we develop case-deletion methods. The generalized Waring regression model is presented as a mixture of the Negative Binomial and the Beta II distributions, and it is compared to the Negative Binomial and Waring regression models. Estimation is performed by maximum likelihood function. The influence measures developed in this paper are applied to a Spanish football league data set. Empirical results show that the generalized Waring regression model performs better when compared to the Negative Binomial and Waring regression models. Technical details are presented in the Appendix.

Keywords: Local influence diagnostic; appropriate perturbation; beta-negative binomial mixture; case-deletion methods.

Grants and funding

The authors acknowledge the partial financial support from Project VRID 215.014.025-1IN, Universidad de Concepción and Project FONDECYT- Fondo Nacional de Desarrollo Científico y Tecnológico 1150325, Chile.