© 2001 by Biometrika Trust
Hierarchical generalised linear models: A synthesis of generalised linear models, random-effect models and structured dispersions
1 Department of Statistics, Seoul National University, Seoul, Koreayoungjo{at}plaza.snu.ac.kr 2 Department of Mathematics, Imperial College, London SW7 2BZ, U.K.j.nelder{at}ic.ac.uk
Hierarchical generalised linear models are developed as a synthesis of generalised linear models, mixed linear models and structured dispersions.We generalise the restricted maximum likelihood method for the estimation of dispersion to the wider class and show how the joint fitting of models for mean and dispersion can be expressed by two interconnected generalised linear models. The method allows models with (i) any combination of a generalised linear model distribution for the response with any conjugate distribution for the random effects, (ii) structured dispersion components, (iii) different link and variance functions for the fixed and random effects, and (iv) the use of quasilikelihoods in place of likelihoods for either or both of the mean and dispersion models. Inferences can be made by applying standard procedures, in particular those for model checking, to components of either generalised linear model. We also show by numerical studies that the new method gives an efficient estimation procedure for substantial class of models of practical importance. Likelihood-type inference is extended to this wide class of models in a unified way.
Key Words: Double extended quasilikelihood; Extended quasilikelihood; Generalised linear mixed model; Generalised linear model; Hierarchical generalised linear model; Quasilikelihood; Restricted maximum likelihood
Received July 2000. Revised January 2001
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  J. d. Castillo and Y. Lee GLM-methods for volatility models Statistical Modeling, September 1, 2008; 8(3): 263 - 283. [Abstract] [PDF]
|
|
|
|
 |
|
 M. Erlinghagen Self-Perceived Job Insecurity and Social Context: A Multi-Level Analysis of 17 European Countries Eur. Sociol. Rev., April 1, 2008; 24(2): 183 - 197. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 S.-C. Yun, Y. Lee, and M. G. Kenward Using Hierarchical Likelihood for Missing Data Problems Biometrika, December 1, 2007; 94(4): 905 - 919. [Abstract] [PDF]
|
|
|
|
 |
|
 S. A. Harrow, V. Ravindran, R. C. Butler, J. W. Marshall, and G. W. Tannock Real-Time Quantitative PCR Measurement of Ileal Lactobacillus salivarius Populations from Broiler Chickens To Determine the Influence of Farming Practices Appl. Envir. Microbiol., November 15, 2007; 73(22): 7123 - 7127. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
R. Bellio and C. Varin A pairwise likelihood approach to generalized linear models with crossed random effects Statistical Modeling, October 1, 2005; 5(3): 217 - 227. [Abstract] [PDF]
|
|
|
|
|
|
F. Vaida and X.-L. Meng Two slice-EM algorithms for fitting generalized linear mixed models with binary response Statistical Modeling, October 1, 2005; 5(3): 229 - 242. [Abstract] [PDF]
|
|
|
|
|
|
Y. Lee Estimating intraclass correlation for binary data using extended quasi-likelihood Statistical Modeling, July 1, 2004; 4(2): 113 - 126. [Abstract] [PDF]
|
|