×
Li, Huiqiong; Wu, Liucang; Yi, Jieyi

A skew-normal mixture of joint location, scale and skewness models. (English) Zbl 1374.62081

Appl. Math., Ser. B (Engl. Ed.) 31, No. 3, 283-295 (2016).
Summary: Normal mixture regression model is one of the most important statistical data analysis tools in a heterogeneous population. When the data set under consideration involves asymmetric outcomes, in the last two decades, the skew normal distribution has been shown beneficial in dealing with asymmetric data in various theoretic and applied problems. In this paper, we propose and study a novel class of models: a skew-normal mixture of joint location, scale and skewness models to analyze the heteroscedastic skew-normal data coming from a heterogeneous population. The issues of maximum likelihood estimation are addressed. In particular, an expectation-maximization (EM) algorithm for estimating the model parameters is developed. Properties of the estimators of the regression coeffients are evaluated through Monte Carlo experiments. Results from the analysis of a real data set from the Body Mass Index (BMI) data are presented.

Cited in 6 Documents

MSC:

62J02 General nonlinear regression
62F12 Asymptotic properties of parametric estimators
62H12 Estimation in multivariate analysis

Keywords:

mixture regression models; mixture of joint location; scale and skewness models; EM algorithm; maximum likelihood estimation

Software:

mixsmsn
Cite Review PDF
Full Text: DOI

References:

[1] A Azzalini. A class of distributions which includes the normal ones, Scand J Statist, 1985, 12: 171–178. · Zbl 0581.62014
[2] R Basso, V H Lachos, C R B Cabral. Robust mixture modelling using scale mixtures of skewnormal distributions, Comput Statist Data Anal, 2010, 54: 2926–2941. · Zbl 1284.62193 · doi:10.1016/j.csda.2009.09.031
[3] C R B Cabral, V H Lachos, M O Prates. Multivariate mixture modeling using skew-normal independent distributions, Comput Statist Data Anal, 2012, 56: 126–142. · Zbl 1239.62058 · doi:10.1016/j.csda.2011.06.026
[4] E Cepeda, D Gamerman. Bayesian modeling of variance heterogeneity in normal regression models, Braz J Probab Stat, 2001, 14: 207–221. · Zbl 0983.62013
[5] R D Cook, S Weisberg. An Introduction to Regression Graphics, Wiley, New York, 1994. · Zbl 0925.62287
[6] Y T Du, A Khalili, G N Johanna, J S Russell. Simultaneous fixed and random effects selection in finite mixture of linear mixed-effects models, Canad J Statist, 2013, 41: 596–616. · Zbl 1281.62153 · doi:10.1002/cjs.11192
[7] C S Ferreira, V H Lachos, H Bolfarine. Skew scale mixtures of normal distributions: properties and estimation, Stat Methodol, 2011, 8: 154–171. · Zbl 1213.62023 · doi:10.1016/j.stamet.2010.09.001
[8] S M Goldfeld, R E Quandt. A Markov model for switching regression, J Econometrics, 1973, 1: 3–15. · Zbl 0294.62087 · doi:10.1016/0304-4076(73)90002-X
[9] C Hennig. Identifiability of models for clusterwise linear regression, J Classification, 2000, 17: 273–296. · Zbl 1017.62058 · doi:10.1007/s003570000022
[10] H J Ho, T I Lin. Robust linear mixed models using the skew t distribution with application to schizophrenia data, Biom J, 2010, 52: 449–469. · Zbl 1197.62055 · doi:10.1002/bimj.200900184
[11] H J Ho, S Pyne, T I Lin. Maximum likelihood inference for mixtures of skew Student-t-normal distributions through practical EM-type algorithms, Statist Comput, 2012, 22: 287–299. · Zbl 1322.62087 · doi:10.1007/s11222-010-9225-9
[12] M Huang, R Z Li, S L Wang. Nonparametric mixture of regression models, J Amer Statist Assoc, 2013, 108: 929–941. · Zbl 06224977 · doi:10.1080/01621459.2013.772897
[13] M Huang, W X Yao. Mixture of regression models with varying mixing proportions: a semiparametric approach, J Amer Statist Assoc, 2012, 107: 711–724. · Zbl 1261.62036 · doi:10.1080/01621459.2012.682541
[14] A Khalil, J Chen. Variable selection in finite mixture of regression models, J Amer Statist Assoc, 2007, 102: 1025–1038. · Zbl 1469.62306 · doi:10.1198/016214507000000590
[15] A Khalili, S L Lin. Regularization in finite mixture of regression models with diverging number of parameters, Biometrics, 2011, 69: 436–446. · Zbl 1273.62254 · doi:10.1111/biom.12020
[16] T I Lin. Maximum likelihood estimation for multivariate skew normal mixture models, J Multivariate Anal, 2009, 100: 257–265. · Zbl 1152.62034 · doi:10.1016/j.jmva.2008.04.010
[17] T I Lin. Robust mixture modeling using multivariate skew t distributions, Statist Comput, 2010, 20: 343–356. · doi:10.1007/s11222-009-9128-9
[18] T I Lin, H J Ho, C R Lee. Flexible mixture modelling using the multivariate skew-t-normal distribution, Statist Comput, 2014, 24: 531–546. · Zbl 1325.62113 · doi:10.1007/s11222-013-9386-4
[19] T I Lin, J C Lee, S Y Yen. Finite mixture modelling using the skew normal distribution, Statist Sinica, 2007, 17: 909–927. · Zbl 1133.62012
[20] T I Lin, J C Lee. Robust mixture modeling using the skew t distribution, Statist Comput, 2007, 17: 81–92. · doi:10.1007/s11222-006-9005-8
[21] T I Lin, W L Wang. Bayesian inference in joint modelling of location and scale parameters of the t distribution for longitudinal data, J Statist Plann Inference, 2011, 141: 1543–1553. · Zbl 1204.62040 · doi:10.1016/j.jspi.2010.11.001
[22] T I Lin, Y J Wang. A robust approach to joint modeling of mean and scale covariance for longitudinal data, J Statist Plann Inference, 2009, 139: 3013–3026. · Zbl 1168.62082 · doi:10.1016/j.jspi.2009.02.008
[23] M Liu and T I Lin. A skew-normal mixture regression model, Educ Psychol Meas, 2014, 74: 139–162. · doi:10.1177/0013164413498603
[24] G J McLachlan, K E Basord. Mixture Models: Inference and Application to Clustering, Marcel Dekker, New York, 1988.
[25] G J McLachlan, N Krishnan. The EM Algorithm and Extensions, Wiley, New York, 1997. · Zbl 0882.62012
[26] G J McLachlan, D Peel. Finite Mixture Models, Wiley, New York, 2000. · Zbl 0963.62061
[27] W X Song, W X Yao, Y R Xing. Robust mixture regression models fitting by Laplace distribution, Comput Statist Data Anal, 2014, 71: 128–137. · Zbl 1471.62189 · doi:10.1016/j.csda.2013.06.022
[28] J T Taylor, A P Verbyla. Joint modelling of location and scale parameters of the t distribution, Stat Model, 2004, 4: 91–112. · Zbl 1112.62010 · doi:10.1191/1471082X04st068oa
[29] D M Titterington, A F M Smith, U E Markov. Statistical Analysis of Finite Mixture Distributions, Wiley, New York, 1985. · Zbl 0646.62013
[30] P Wang, M L Puterman, I Cockburn, N Le. Mixed Poisson regression models with covariate dependent rates, Biometrics, 1996, 52: 381–400. · Zbl 0875.62407 · doi:10.2307/2532881
[31] W X Yao, Y Wei, C Yu. Robust mixture regression models using t-distribution, Comput Statist Data Anal, 2014, 71: 116–127. · Zbl 1471.62227 · doi:10.1016/j.csda.2013.07.019
[32] D S Young, D R Hunter. Mixtures of regressions with predictor-dependent mixing proportions, Comput Statist Data Anal, 2010, 54: 2253–2266. · Zbl 1284.62467 · doi:10.1016/j.csda.2010.04.002
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.