A flexible approach for multivariate mixed-effects models with non-ignorable missing values

被引:1
作者
Liu, Juxin [1 ]
Liu, Wei [2 ]
Wu, Lang [3 ]
Yan, Guohua [4 ]
机构
[1] Univ Saskatchewan, Dept Math & Stat, Saskatoon, SK S7N 5E6, Canada
[2] York Univ, Dept Math & Stat, Toronto, ON M3J 1P3, Canada
[3] Univ British Columbia, Dept Stat, Vancouver, BC V6T 1Z4, Canada
[4] Univ New Brunswick, Dept Math & Stat, Fredericton, NB E3B 5A3, Canada
关键词
Dirichlet process; Dirichlet process mixture models; random effects; non-ignorable missing values; Bayesian MCMC; DIRICHLET PROCESS PRIOR; NONPARAMETRIC PROBLEMS; APPROXIMATE DIRICHLET; INFERENCE; MIXTURES; DISTRIBUTIONS; BAYES;
D O I
10.1080/00949655.2015.1005014
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
We propose a flexible model approach for the distribution of random effects when both response variables and covariates have non-ignorable missing values in a longitudinal study. A Bayesian approach is developed with a choice of nonparametric prior for the distribution of random effects. We apply the proposed method to a real data example from a national long-term survey by Statistics Canada. We also design simulation studies to further check the performance of the proposed approach. The result of simulation studies indicates that the proposed approach outperforms the conventional approach with normality assumption when the heterogeneity in random effects distribution is salient.
引用
收藏
页码:3727 / 3743
页数:17
相关论文
共 25 条
[1]   Examples in which misspecification of a random effects distribution reduces efficiency, and possible remedies [J].
Agresti, A ;
Caffo, B ;
Ohman-Strickland, P .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2004, 47 (03) :639-653
[2]   MIXTURES OF DIRICHLET PROCESSES WITH APPLICATIONS TO BAYESIAN NONPARAMETRIC PROBLEMS [J].
ANTONIAK, CE .
ANNALS OF STATISTICS, 1974, 2 (06) :1152-1174
[3]   Variational Inference for Dirichlet Process Mixtures [J].
Blei, David M. ;
Jordan, Michael I. .
BAYESIAN ANALYSIS, 2006, 1 (01) :121-143
[4]   ESTIMATING NORMAL MEANS WITH A DIRICHLET PROCESS PRIOR [J].
ESCOBAR, MD .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1994, 89 (425) :268-277
[5]   BAYESIAN ANALYSIS OF SOME NONPARAMETRIC PROBLEMS [J].
FERGUSON, TS .
ANNALS OF STATISTICS, 1973, 1 (02) :209-230
[6]   A SEMIPARAMETRIC BAYESIAN APPROACH TO NETWORK MODELLING USING DIRICHLET PROCESS PRIOR DISTRIBUTIONS [J].
Ghosh, Pulak ;
Gill, Paramjit ;
Muthukumarana, Saman ;
Swartz, Tim .
AUSTRALIAN & NEW ZEALAND JOURNAL OF STATISTICS, 2010, 52 (03) :289-302
[7]   Misspecified maximum likelihood estimates and generalised linear mixed models [J].
Heagerty, PJ ;
Kurland, BF .
BIOMETRIKA, 2001, 88 (04) :973-985
[8]   Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models [J].
Ishwaran, H ;
Zarepour, M .
BIOMETRIKA, 2000, 87 (02) :371-390
[9]   Approximate Dirichlet process computing in finite normal mixtures: Smoothing and prior information [J].
Ishwaran, H ;
James, LF .
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2002, 11 (03) :508-532
[10]  
Jara A, 2011, J STAT SOFTW, V40, P1