A general class of zero-or-one inflated beta regression models
Abstract
This paper proposes a general class of regression models for continuous proportions when the data contain zeros or ones. The proposed class of models assumes that the response variable has a mixed continuous-discrete distribution with probability mass at zero or one. The beta distribution is used to describe the continuous component of the model, since its density has a wide range of different shapes depending on the values of the two parameters that index the distribution. We use a suitable parameterization of the beta law in terms of its mean and a precision parameter. The parameters of the mixture distribution are modeled as functions of regression parameters. We provide inference, diagnostic, and model selection tools for this class of models. A practical application that employs real data is presented.
Cite
@article{arxiv.1103.2372,
title = {A general class of zero-or-one inflated beta regression models},
author = {Raydonal Ospina and Silvia L. P. Ferrari},
journal= {arXiv preprint arXiv:1103.2372},
year = {2011}
}
Comments
21 pages, 3 figures, 5 tables. Computational Statistics and Data Analysis, 17 October 2011, ISSN 0167-9473 (http://www.sciencedirect.com/science/article/pii/S0167947311003628)