BAYESIAN HIERARCHICAL MODELS FOR MULTI-LEVEL REPEATED ORDINAL DATA USING WinBUGS

Multi-level repeated ordinal data arise if ordinal outcomes are measured repeatedly in subclusters of a cluster or on subunits of an experimental unit. If both the regression coefficients and the correlation parameters are of interest, the Bayesian hierarchical models have proved to be a powerful tool for analysis with computation being performed by Markov Chain Monte Carlo (MCMC) methods. The hierarchical models extend the random effects models by including a (usually flat) prior on the regression coefficients and parameters in the distribution of the random effects. Because the MCMC can be implemented by the widely available BUGS or WinBUGS software packages, the computation burden of MCMC has been alleviated. However, thoughtfulness is essential in order to use this software effectively to analyze such data with complex structures. For example, we may have to reparameterize the model and standardize the covariates to accelerate the convergence of the MCMC, and then carefully monitor the convergence of the Markov chain. This article aims at resolving these issues in the application of the WinBUGS through the analysis of a real multi-level ordinal data. In addition, we extend the hierarchical model to include a wider class of distributions for the random effects. We propose to use the deviance information criterion (DIC) for model selection. We show that the WinBUGS software can readily implement such extensions and the DIC criterion.

[1]  A. Agresti.  Modelling ordered categorical data: recent advances and future challenges. , 1999, Statistics in medicine.

[2]  D. Hedeker,et al.  Random effects probit and logistic regression models for three-level data. , 1997, Biometrics.

[3]  Adrian E. Raftery,et al.  Bayes factors and model uncertainty , 1995 .

[4]  J. R. Landis,et al.  The analysis of longitudinal polytomous data: generalized estimating equations and connections with weighted least squares. , 1993, Biometrics.

[5]  M Tan,et al.  A Bayesian hierarchical model for multi-level repeated ordinal data: analysis of oral practice examinations in a large anaesthesiology training programme. , 1999, Statistics in medicine.

[6]  A. Gelfand,et al.  Efficient parametrizations for generalized linear mixed models, (with discussion). , 1996 .

[7]  Robert Crouchley,et al.  A Random-Effects Model for Ordered Categorical Data , 1995 .

[8]  Farid Kianifard,et al.  Models for Repeated Measurements , 2001, Technometrics.

[9]  Mark R. Conaway,et al.  A random effects model for binary data , 1990 .

[10]  Jiming Jiang.  Consistent Estimators in Generalized Linear Mixed Models , 1998 .

[11]  G. W. Snedecor.  Statistical Methods , 1964 .

[12]  Radford M. Neal,et al.  Suppressing Random Walks in Markov Chain Monte Carlo Using Ordered Overrelaxation , 1995, Learning in Graphical Models.

[13]  P. Albert,et al.  Models for longitudinal data: a generalized estimating equation approach. , 1988, Biometrics.

[14]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[15]  Hoon Kim,et al.  Monte Carlo Statistical Methods , 2000, Technometrics.

[16]  D. Hedeker,et al.  A random-effects ordinal regression model for multilevel analysis. , 1994, Biometrics.

[17]  J E Tetzlaff,et al.  Consistency, inter-rater reliability, and validity of 441 consecutive mock oral examinations in anesthesiology: implications for use as a tool for assessment of residents. , 1999, Anesthesiology.

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

[19]  Andrew L. Rukhin,et al.  Tools for statistical inference , 1991 .

[20]  Yinsheng Qu,et al.  Analysis of clustered ordinal data with subclusters via a Bayesian hierarchical model , 1998 .

[21]  G. Molenberghs,et al.  Marginal Modeling of Correlated Ordinal Data Using a Multivariate Plackett Distribution , 1994 .

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

[23]  Sylvia Richardson,et al.  Markov Chain Monte Carlo in Practice , 1997 .

[24]  G. Tutz,et al.  Random effects in ordinal regression models , 1996 .

[25]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.

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

[27]  A. Gelfand,et al.  Efficient parametrisations for normal linear mixed models , 1995 .

[28]  Robert W. Mee,et al.  A mixed-model procedure for analyzing ordered categorical data , 1984 .

[29]  S. Zeger,et al.  Marginal Regression Models for Clustered Ordinal Measurements , 1996 .