Parameter estimation of Poisson generalized linear mixed models based on three different statistical principles: a simulation study

Generalized linear mixed models are flexible tools for modeling non-normal data and are usefulfor accommodating overdispersion in Poisson regression models with random effects. Theirmain difficulty resides in the parameter estimation because there is no analytic solution for themaximization of the marginal likelihood. Many methods have been proposed for this purpose andmany of them are implemented in software packages. The purpose of this study is to comparethe performance of three different statistical principles –marginal likelihood, extended likelihood,Bayesian analysis – via simulation studies. Real data on contact wrestling are used for illustration.

[1]  Mollie E. Brooks,et al.  Generalized linear mixed models: a practical guide for ecology and evolution. , 2009, Trends in ecology & evolution.

[2]  M. Girabent-Farrés,et al.  Methodological Quality and Reporting of Generalized Linear Mixed Models in Clinical Medicine (2000–2012): A Systematic Review , 2014, PloS one.

[3]  Philippe Hellard,et al.  Modeling the training-performance relationship using a mixed model in elite swimmers. , 2003, Medicine and science in sports and exercise.

[4]  M. Wand,et al.  Gaussian Variational Approximate Inference for Generalized Linear Mixed Models , 2012 .

[5]  Robert A. Muenchen,et al.  The Popularity of Data Analysis Software , 2013 .

[6]  D. Bates,et al.  Linear Mixed-Effects Models using 'Eigen' and S4 , 2015 .

[7]  Murray Aitkin,et al.  A general maximum likelihood analysis of overdispersion in generalized linear models , 1996, Stat. Comput..

[8]  Jarrod Had.  MCMC Methods for Multi-Response Generalized Linear Mixed Models: The MCMCglmm R Package , 2010 .

[9]  Martí Casals,et al.  Modelling player performance in basketball through mixed models , 2013 .

[10]  Emmanuel Lesaffre,et al.  On the effect of the number of quadrature points in a logistic random effects model: an example , 2001 .

[11]  J. Wakefield,et al.  Bayesian inference for generalized linear mixed models. , 2010, Biostatistics.

[12]  Kirk Goldsberry,et al.  A Multiresolution Stochastic Process Model for Predicting Basketball Possession Outcomes , 2014, 1408.0777.

[13]  A. Zuur,et al.  Mixed Effects Models and Extensions in Ecology with R , 2009 .

[14]  J. Nelder,et al.  Hierarchical Generalized Linear Models , 1996 .

[15]  Finn Lindgren,et al.  Bayesian Spatial Modelling with R-INLA , 2015 .

[16]  Emmanuel Lesaffre,et al.  Hierarchical Generalized Linear Models: The R Package HGLMMM , 2011 .

[17]  Ewout W Steyerberg,et al.  Logistic random effects regression models: a comparison of statistical packages for binary and ordinal outcomes , 2011, BMC medical research methodology.

[18]  Jianxin Pan,et al.  Quasi-Monte Carlo estimation in generalized linear mixed models , 2007, Comput. Stat. Data Anal..

[19]  W. Hopkins,et al.  Methods for tracking athletes' competitive performance in skeleton , 2009, Journal of sports sciences.

[20]  D. A. Williams,et al.  Extra‐Binomial Variation in Logistic Linear Models , 1982 .

[21]  R. Allan Reese,et al.  Linear Mixed Models: a Practical Guide using Statistical Software , 2008 .

[22]  J. Nelder,et al.  Hierarchical generalised linear models: A synthesis of generalised linear models, random-effect models and structured dispersions , 2001 .

[23]  Jiri Dvorak,et al.  Sports Injuries During the Summer Olympic Games 2008 , 2009, The American journal of sports medicine.

[24]  Emmanuel Lesaffre,et al.  Generalized linear mixed model with a penalized Gaussian mixture as a random effects distribution , 2008, Comput. Stat. Data Anal..

[25]  C B Dean,et al.  Generalized linear mixed models: a review and some extensions , 2007, Lifetime data analysis.

[26]  N. Breslow.  Extra‐Poisson Variation in Log‐Linear Models , 1984 .

[27]  Y. Pawitan.  In all likelihood : statistical modelling and inference using likelihood , 2002 .

[28]  S. Frühwirth-Schnatter,et al.  Stochastic model specification search for Gaussian and partial non-Gaussian state space models , 2010 .

[29]  J. F. Bjørnstad.  ----On the Generalization of the Likelihood Function and the Likelihood Principle , 2008 .

[30]  Jaime Sampaio,et al.  Effects of season period, team quality, and playing time on basketball players' game-related statistics , 2010 .

[31]  Woojoo Lee,et al.  Modifications of REML algorithm for HGLMs , 2012, Stat. Comput..

[32]  Geoffrey Gregory,et al.  Foundations of Statistical Inference , 1973 .

[33]  H. Rue,et al.  Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations , 2009 .

[34]  J. Hardin,et al.  Generalized Linear Models and Extensions , 2001 .

[35]  C. Czado,et al.  Zero-inflated generalized Poisson models with regression effects on the mean, dispersion and zero-inflation level applied to patent outsourcing rates , 2007 .

[36]  Rafael E. Diaz.  Comparison of PQL and Laplace 6 estimates of hierarchical linear models when comparing groups of small incident rates in cluster randomised trials , 2007, Comput. Stat. Data Anal..

[37]  M. J. Bayarri,et al.  Bayesian Variable Selection for Random Intercept Modeling of Gaussian and non-Gaussian Data , 2010 .

[38]  R Bahr,et al.  Methods for epidemiological study of injuries to professional football players: developing the UEFA model , 2005, British Journal of Sports Medicine.

[39]  Liang Zhu,et al.  On fitting generalized linear mixed‐effects models for binary responses using different statistical packages , 2011, Statistics in medicine.

[40]  Andreas Wienke,et al.  Software for semiparametric shared gamma and log-normal frailty models: An overview , 2012, Comput. Methods Programs Biomed..

[41]  Boris Worm,et al.  Applying Bayesian spatiotemporal models to fisheries bycatch in the Canadian Arctic , 2015 .

[42]  Herwig Friedl,et al.  Negative binomial loglinear mixed models , 2003 .

[43]  Patrick Brown,et al.  MCMC for Generalized Linear Mixed Models with glmmBUGS , 2010, R J..

[44]  Moudud Alam,et al.  hglm: A Package for Fitting Hierarchical Generalized Linear Models , 2010, R J..

[45]  S. R. Searle,et al.  Generalized, Linear, and Mixed Models , 2005 .

[46]  N. Breslow,et al.  Approximate inference in generalized linear mixed models , 1993 .

[47]  D. Collins.  The performance of estimation methods for generalized linear mixed models , 2008 .

[48]  J. Nelder,et al.  Generalized Linear Models with Random Effects: Unified Analysis via H-likelihood , 2006 .

[49]  Thiago G. Martins,et al.  Penalising Model Component Complexity: A Principled, Practical Approach to Constructing Priors , 2014, 1403.4630.

[50]  C Arrowsmith,et al.  Analysis of aggregation, a worked example: numbers of ticks on red grouse chicks , 2001, Parasitology.

[51]  L. Grilli,et al.  Bayesian estimation with integrated nested Laplace approximation for binary logit mixed models , 2015 .

[52]  Yoonsang Kim,et al.  Logistic Regression With Multiple Random Effects: A Simulation Study of Estimation Methods and Statistical Packages , 2013, The American statistician.

[53]  Ignoring overdispersion in hierarchical loglinear models: Possible problems and solutions , 2012, Statistics in medicine.

[54]  T. Hewett,et al.  Wrestling injuries. , 2005, Medicine and sport science.

[55]  Peter C Austin,et al.  Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures , 2010, The international journal of biostatistics.

[56]  Håvard Rue,et al.  A Bayesian Approach to estimate the biomass of anchovies in the coast of Perú , 2014 .

[57]  Moudud Alam,et al.  Fitting Conditional and Simultaneous Autoregressive Spatial Models in hglm , 2015, R J..

[58]  Geert Molenberghs,et al.  A hierarchical Bayesian approach for the analysis of longitudinal count data with overdispersion: A simulation study , 2013, Comput. Stat. Data Anal..

[59]  M. Hägglund,et al.  The importance of epidemiological research in sports medicine , 2010 .

[60]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[61]  Brady T. West,et al.  Linear Mixed Models: A Practical Guide Using Statistical Software , 2006 .

[62]  Maengseok Noh,et al.  REML estimation for binary data in GLMMs , 2007 .

[63]  A. Gelman.  Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper) , 2004 .