A general class of zero-or-one inflated beta regression models

被引:354
作者
Ospina, Raydonal [2 ]
Ferrari, Silvia L. P. [1 ]
机构
[1] Univ Sao Paulo, Dept Estat IME, BR-05508090 Sao Paulo, Brazil
[2] Univ Fed Pernambuco, Dept Estat CCEN, BR-50740540 Recife, PE, Brazil
基金
巴西圣保罗研究基金会;
关键词
Continuous proportions; Zero-or-one inflated beta distribution; Fractional data; Maximum likelihood estimation; Diagnostics; Residuals; DIAGNOSTICS;
D O I
10.1016/j.csda.2011.10.005
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
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. (C) 2011 Elsevier B.V. All rights reserved.
引用
收藏
页码:1609 / 1623
页数:15
相关论文
共 41 条
  • [1] NEW LOOK AT STATISTICAL-MODEL IDENTIFICATION
    AKAIKE, H
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1974, AC19 (06) : 716 - 723
  • [2] [Anonymous], TEST CORRECT MODEL S
  • [3] [Anonymous], STAT MODELLING
  • [4] [Anonymous], 1997, ADV SERIES STAT SCI
  • [5] [Anonymous], 1998, Exponential family nonlinear models
  • [6] [Anonymous], 1996, J COMPUT GRAPH STAT
  • [7] [Anonymous], 1995, CONTINUOUS UNIVARIAT
  • [8] [Anonymous], 2006, ZERO INFLATED BETA D
  • [9] Atkinson Anthony Curtes, 1985, Plots, transformations and regression
  • [10] an introduction to graphical methods of diagnostic regression analysis