Hierarchical Generalized Linear Models

We consider hierarchical generalized linear models which allow extra error components in the linear predictors of generalized linear models. The distribution of these components is not restricted to be normal; this allows a broader class of models, which includes generalized linear mixed models. We use a generalization of Henderson's joint likelihood, called a hierarchical or h-likelihood, for inferences from hierarchical generalized linear models. This avoids the integration that is necessary when marginal likelihood is used. Under appropriate conditions maximizing the h-likelihood gives fixed effect estimators that are asymptotically equivalent to those obtained from the use of marginal likelihood; at the same time we obtain the random effect estimates that are asymptotically best unbiased predictors. An adjusted profile h-likelihood is shown to give the required generalization of restricted maximum likelihood for the estimation of dispersion components. A scaled deviance test for the goodness of fit, a model selection criterion for choosing between various dispersion models and a graphical method for checking the distributional assumption of random effects are proposed. The ideas of quasi-likelihood and extended quasi-likelihood are generalized to the new class. We give examples of the Poisson-gamma, binomial-beta and gamma-inverse gamma hierarchical generalized linear models. A resolution is proposed for the apparent difference between population-averaged and subject-specific models. A unified framework is provided for viewing and extending many existing methods.

[1]  William G. Cochran,et al.  Experimental designs, 2nd ed. , 1957 .

[2]  S. R. Searle,et al.  The estimation of environmental and genetic trends from records subject to culling. , 1959 .

[3]  C. R. Rao,et al.  Linear Statistical Inference and its Applications , 1968 .

[4]  David R. Cox.  The analysis of binary data , 1970 .

[5]  H. D. Patterson,et al.  Recovery of inter-block information when block sizes are unequal , 1971 .

[6]  P. McCullagh,et al.  Generalized Linear Models , 1972, Predictive Analytics.

[7]  R. W. Wedderburn.  Quasi-likelihood functions, generalized linear models, and the Gauss-Newton method , 1974 .

[8]  C. R. Henderson,et al.  Best linear unbiased estimation and prediction under a selection model. , 1975, Biometrics.

[9]  David A. Harville,et al.  Extension of the Gauss-Markov Theorem to Include the Estimation of Random Effects , 1976 .

[10]  D. Harville.  Maximum Likelihood Approaches to Variance Component Estimation and to Related Problems , 1977 .

[11]  Martin Crowder,et al.  Beta-binomial Anova for Proportions , 1978 .

[12]  A. C. Atkinson,et al.  Two graphical displays for outlying and influential observations in regression , 1981 .

[13]  D. Rubin.  Estimation in Parallel Randomized Experiments , 1981 .

[14]  T. Louis.  Finding the Observed Information Matrix When Using the EM Algorithm , 1982 .

[15]  P. W. Lane,et al.  Analysis of covariance and standardization as instances of prediction. , 1982, Biometrics.

[16]  J. Ware,et al.  Random-effects models for serial observations with binary response. , 1984, Biometrics.

[17]  Ross L. Prentice,et al.  Likelihood inference in a correlated probit regression model , 1984 .

[18]  A. L. Rae,et al.  The analysis of binomial data by a generalized linear mixed model , 1985 .

[19]  S. Weisberg.  Plots, transformations, and regression , 1985 .

[20]  C. Weinberg,et al.  The beta-geometric distribution applied to comparative fecundability studies. , 1986, Biometrics.

[21]  D. Pierce,et al.  Residuals in Generalized Linear Models , 1986 .

[22]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[23]  L. Tierney,et al.  Accurate Approximations for Posterior Moments and Marginal Densities , 1986 .

[24]  D. Clayton,et al.  Empirical Bayes estimates of age-standardized relative risks for use in disease mapping. , 1987, Biometrics.

[25]  Richard Morton,et al.  A generalized linear model with nested strata of extra-Poisson variation , 1987 .

[26]  D. A. Williams,et al.  Generalized Linear Model Diagnostics Using the Deviance and Single Case Deletions , 1987 .

[27]  D. Cox,et al.  Parameter Orthogonality and Approximate Conditional Inference , 1987 .

[28]  Christopher J. Nachtsheim,et al.  Diagnostics for mixed-model analysis of variance , 1987 .

[29]  P. Green.  Penalized Likelihood for General Semi-Parametric Regression Models. , 1987 .

[30]  J. Nelder,et al.  An extended quasi-likelihood function , 1987 .

[31]  H. Goldstein.  Multilevel Statistical Models , 2006 .

[32]  D. Gaver,et al.  Robust empirical bayes analyses of event rates , 1987 .

[33]  R. Tsutakawa.  Mixed model for analyzing geographic variability in mortality rates. , 1988, Journal of the American Statistical Association.

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

[35]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[36]  P. Thall,et al.  Some covariance models for longitudinal count data with overdispersion. , 1990, Biometrics.

[37]  Robin Thompson,et al.  Generalized Linear Models and Applications to Animal Breeding , 1990 .

[38]  Nearly Parallel Lines in Residual Plots , 1990 .

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

[40]  Scott L. Zeger,et al.  Generalized linear models with random e ects: a Gibbs sampling approach , 1991 .

[41]  McGilchrist Ca,et al.  Regression with frailty in survival analysis. , 1991 .

[42]  R. Schall.  Estimation in generalized linear models with random effects , 1991 .

[43]  David Firth,et al.  Quasi-likelihood for multiplicative random effects , 1991 .

[44]  M. West,et al.  Dynamic linear model diagnostics , 1991 .

[45]  H. Goldstein.  Nonlinear multilevel models, with an application to discrete response data , 1991 .

[46]  Terry Speed,et al.  [That BLUP is a Good Thing: The Estimation of Random Effects]: Comment , 1991 .

[47]  L. Fahrmeir.  Posterior Mode Estimation by Extended Kalman Filtering for Multivariate Dynamic Generalized Linear Models , 1992 .

[48]  Anthony C. Davison,et al.  Regression model diagnostics , 1992 .

[49]  W. Gilks,et al.  Adaptive Rejection Sampling for Gibbs Sampling , 1992 .

[50]  S L Zeger,et al.  Generalized linear models with random effects; salamander mating revisited. , 1992, Biometrics.

[51]  Guido Consonni,et al.  Conjugate Priors for Exponential Families Having Quadratic Variance Functions , 1992 .

[52]  John A. Nelder,et al.  Likelihood, Quasi-likelihood and Pseudolikelihood: Some Comparisons , 1992 .

[53]  A. F. Desmond,et al.  Modelling Task Completion Data with Inverse Gaussian Mixtures , 1993 .

[54]  Russell D. Wolfinger,et al.  Laplace's approximation for nonlinear mixed models. , 1993 .

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

[56]  Pranab Kumar Sen,et al.  Large Sample Methods in Statistics: An Introduction with Applications , 1993 .

[57]  A. F. Smith,et al.  Conjugate likelihood distributions , 1993 .

[58]  Donald A. Pierce,et al.  Heterogeneity in Mantel-Haenszel-type models , 1993 .

[59]  C. Mcgilchrist.  Estimation in Generalized Mixed Models , 1994 .

[60]  H Goldstein,et al.  Multilevel time series models with applications to repeated measures data. , 1994, Statistics in medicine.

[61]  A. Keen,et al.  A simple approach for the analysis of generalizea linear mixed models , 1994 .

[62]  Walter R. Gilks,et al.  A Language and Program for Complex Bayesian Modelling , 1994 .

[63]  B. Silverman,et al.  Nonparametric Regression and Generalized Linear Models: A roughness penalty approach , 1993 .

[64]  M. Lavine.  More Aspects of Polya Tree Distributions for Statistical Modelling , 1992 .

[65]  Adrian F. M. Smith,et al.  Bayesian Analysis of Linear and Non‐Linear Population Models by Using the Gibbs Sampler , 1994 .

[66]  Robin Thompson,et al.  Comparisons of some GLMM estimators for a simple binomial model , 1994 .

[67]  N. Shephard,et al.  The simulation smoother for time series models , 1995 .

[68]  John W. McDonald,et al.  Marginal regression analysis of a multivariate binary response , 1995 .

[69]  Noreen Goldman,et al.  An assessment of estimation procedures for multilevel models with binary responses , 1995 .

[70]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[71]  Peter McCullagh,et al.  Laplace Approximation of High Dimensional Integrals , 1995 .

[72]  W. Buist,et al.  Inference for threshold models with variance components from the generalized linear mixed model perspective , 1995, Genetics Selection Evolution.

[73]  L. Bernardinelli,et al.  Bayesian methods for mapping disease risk , 1996 .

[74]  N. Breslow,et al.  Bias Correction in Generalized Linear Mixed Models with Multiple Components of Dispersion , 1996 .

[75]  C. Morris,et al.  Hierarchical Poisson Regression Modeling , 1997 .

[76]  Bani K. Mallick,et al.  Hierarchical Generalized Linear Models and Frailty Models with Bayesian Nonparametric Mixing , 1997 .