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

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.

[1]  Suresh H. Moolgavkar,et al.  A Geometric Approach to Nonlinear Regression Diagnostics with Applications to matched Case-Control Studies , 1984 .

[2]  M. Kupperman.  Linear Statistical Inference and Its Applications 2nd Edition (C. Radhakrishna Rao) , 1975 .

[3]  D. McFadden.  Conditional logit analysis of qualitative choice behavior , 1972 .

[4]  Luigi Pace,et al.  Principles of statistical inference : from a neo-Fisherian perspective , 1997 .

[5]  Adrian Bowman,et al.  Generalized additive models for location, scale and shape - Discussion , 2005 .

[6]  David R. Cox.  The analysis of binary data , 1970 .

[7]  B. McCullough,et al.  Regression analysis of variates observed on (0, 1): percentages, proportions and fractions , 2003 .

[8]  Bo-Cheng Wei,et al.  Exponential Family Nonlinear Models , 1998 .

[9]  J. H. Schuenemeyer,et al.  Generalized Linear Models (2nd ed.) , 1992 .

[10]  S. Weisberg,et al.  Residuals and Influence in Regression , 1982 .

[11]  Wagner Barreto-Souza,et al.  Improved estimators for a general class of beta regression models , 2008, Comput. Stat. Data Anal..

[12]  Brian D. Ripley,et al.  Modern applied statistics with S, 4th Edition , 2002, Statistics and computing.

[13]  H. Akaike.  A new look at the statistical model identification , 1974 .

[14]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[15]  R. Rigby,et al.  Generalized additive models for location, scale and shape , 2005 .

[16]  Michael Smithson,et al.  A better lemon squeezer? Maximum-likelihood regression with beta-distributed dependent variables. , 2006, Psychological methods.

[17]  P. McCullagh,et al.  Generalized Linear Models, 2nd Edn. , 1990 .

[18]  Calyampudi Radhakrishna Rao,et al.  Linear Statistical Inference and its Applications , 1967 .

[19]  Ayoe Hoff,et al.  Second stage DEA: Comparison of approaches for modelling the DEA score , 2007, Eur. J. Oper. Res..

[20]  Bruce D. McCullough,et al.  Regression analysis of proportions in finance with self selection , 2008 .

[21]  R. Rigby,et al.  Generalized Additive Models for Location Scale and Shape (GAMLSS) in R , 2007 .

[22]  Miina Rautiainen,et al.  Local Models for Forest Canopy Cover with Beta Regression , 2007 .

[23]  S. Ferrari,et al.  On beta regression residuals , 2008 .

[24]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[25]  Raydonal Ospina,et al.  Inflated beta distributions , 2007, 0705.0700.

[26]  Francisco Cribari-Neto,et al.  Influence diagnostics in beta regression , 2008, Comput. Stat. Data Anal..

[27]  D. Cox,et al.  Parameter Orthogonality and Approximate Conditional Inference , 1987 .

[28]  Seung-Hoon Yoo.  A Note on an Approximation of the Mobile Communications Expenditures Distribution Function Using a Mixture Model , 2004 .

[29]  Ross Ihaka,et al.  Gentleman R: R: A language for data analysis and graphics , 1996 .

[30]  M. Kendall.  Theoretical Statistics , 1956, Nature.

[31]  J. B. Ramsey,et al.  Tests for Specification Errors in Classical Linear Least‐Squares Regression Analysis , 1969 .

[32]  D. Cox,et al.  A General Definition of Residuals , 1968 .

[33]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[34]  José M. R. Murteira,et al.  Alternative Estimating and Testing Empirical Strategies for Fractional Regression Models , 2011 .

[35]  P. Zarembka.  Frontiers in econometrics , 1973 .

[36]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[37]  W. Press,et al.  Numerical Recipes in C++: The Art of Scientific Computing (2nd edn)1 Numerical Recipes Example Book (C++) (2nd edn)2 Numerical Recipes Multi-Language Code CD ROM with LINUX or UNIX Single-Screen License Revised Version3 , 2003 .

[38]  Michael Smithson,et al.  Beta Regression Finite Mixture Models of Polarization and Priming , 2011 .

[39]  N. L. Johnson,et al.  Continuous Univariate Distributions. , 1995 .

[40]  S. Ferrari,et al.  Improved likelihood inference in beta regression , 2011 .

[41]  Peter K. Dunn,et al.  Randomized Quantile Residuals , 1996 .

[42]  T. L. Pereira,et al.  A TEST FOR CORRECT MODEL SPECIFICATION IN INFLATED BETA REGRESSIONS , 2010 .

[43]  L. Fahrmeir,et al.  Correction: Consistency and Asymptotic Normality of the Maximum Likelihood Estimator in Generalized Linear Models , 1985 .

[44]  Anthony C. Atkinson,et al.  Plots, transformations, and regression : an introduction to graphical methods of diagnostic regression analysis , 1987 .

[45]  Philip Paolino,et al.  Maximum Likelihood Estimation of Models with Beta-Distributed Dependent Variables , 2001, Political Analysis.

[46]  S. Ferrari,et al.  Beta Regression for Modelling Rates and Proportions , 2004 .

[47]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[48]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[49]  Chris A. Glasbey,et al.  A simulation-based method for model evaluation , 2003 .

[50]  Calyampudi R. Rao,et al.  Linear Statistical Inference and Its Applications. , 1975 .