Augmented Mixed Beta Regression and Modeling of Employed Proportions in Households

Fallah Mohsenkhani, Zohreh; Mohammadzadeh, Mohsen

doi:10.22055/jamm.2017.13102

Augmented Mixed Beta Regression and Modeling of Employed Proportions in Households

Document Type : Original Paper

Authors

Zohreh Fallah Mohsenkhani ¹

Mohsen Mohammadzadeh ²

¹ Department of Statistics, Tarbiat Modares University

² Department of Statistics, Tarbiat Modares University, Tehran, Iran

10.22055/jamm.2017.13102

Abstract

The Beta regression model is usually used for modeling the rates or proportions confined in an open interval (0,1). In some studies, the data may also include zero and one. In this paper, an augmented Beta regression model that is a mixture of Beta distribution with two degenerated distributions at 0 and 1 is presented for rates or proportions confined in [0,1]. For the augmented mixed Beta model with reparametrization of Beta distribution, the mean and precision parameters were modeled including fixed and random effects. This is while taking into account that the random effects make these models applicable to correlated data. Here, the augmented mixed Beta model is presented. Then this model is evaluated in a simulation study. Next, the application of this model is shown for analyzing the proportions of employed persons in every household. Finally, conclusion and results are presented.

Keywords

Augmented Beta Regression

Bayesian Analysis

Labour Force Survey

Beta Distribution

Mixed Model

Subjects

Statistics

[1] Paolino, P. (2001). Maximum Likelihood E stimation of Models with Beta-Distributed Dependent Variables, Political Analysis, 9, 325-346.

[2] Kieschnik, R. and McCullough, B.D. (2003). Regression Analysis of Variates Observed on (0,1): Percentage, Proportions and Fractions. Statistical Modelling, 3,193-213.

[3] Ferrari, S. and Cribari, F. (2004). Beta Regression for ModellingR ates and Proportions, Journal of Applied Statistics, 31, 799-815.

[4] Cepeda, E.D. and Gamerman, D. (2005). Bayesian Methodology for Modeling Parameters in the Two ParameterE xponentialF amily, Revista Estadística, 57, 168-169.

[5] Smithson, M. and Verkuilen, J. (2006). A Better Lemon Squeezer? Maximum-Likelihood Regression with Beta-Distributed Dependent Variables, Psychological Methods, 11, 54-71.

[6] Branscum, A.J., Johnson, W.O. and Thurmond, M. (2007). Baysian Beta Regression Applications to Houshold Expenditure Data and Genetic Distance Between Food and Mouth Dieseas Viruses, Australian & New Zealand Journal of Statistics, 49, 287-301.

[7] Ospina, R. and Ferrari, S. (2010). Inflated Beta Distributions. Statistical Paper, 23, 193-213.

[8] Ospina, R. and Ferrari, S. (2012). A General Class of Zeror-One Inflated Beta Regression Models. Computational Statistics & Data Analysis, 56, 1609-1623.

[9] Galvis, M.D., Dipankar, B. and Victor, H.L. (2014). Augmented Mixed Beta Regression Models for Periodontal Proportion Data, Preprinted, Statistics in Medicine, 33,3759-3771.

[0] Figueroa-Zúñiga, J.I., Arellano-Valle, R.B. and Ferrari, S.L. (2013). Mixed Beta Regression: A Bayesian Perspective, Computational Statistics & Data Analysis, 61, 137– 147.

[11] Sturtz, S., Ligges, U. and Gelman, A. (2005). R2winbugs: A Package for Running Winbugs from R, Journal of Statistical Software, 12, 1–16.

[12] نتایج آمارگیری نیروی کار (1392)، مرکز آمار ایران، تهران.

[13] Gelman, A. and Rubin, D.B. (1992). Inference from Iterative Simulation Using Multiple Sequences, Statistical Science 7, 457–511.

[14] Heidelberger, P. and Welch, P.D. (1981). A Spectral Method for Confidence Interval Generation and Run Length Contral in Simulations, Communications of the ACM, 24, 233-245.

[15] Brooks, S.P. and Gelman, A., (1998). General Methods for Monitoring Convergence of Iterative Simulations. Journal of Computational and Graphical Statistics 7, 434–455.

[16] Plummer, M., Best, N., Cowles, K. and Vines, K., (2006). The coda Package. R Project. http://cran.r-project.org/doc/packages/coda.pdf.