Premium
Nonlinear regression models for correlated count data
Author(s) -
Burnett R. T.,
Shedden J.,
Krewski D.
Publication year - 1992
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.3170030206
Subject(s) - statistics , multivariate statistics , count data , bayesian multivariate linear regression , mathematics , covariance , regression analysis , regression , nonlinear regression , mixing (physics) , variance (accounting) , correlation , linear regression , econometrics , physics , accounting , quantum mechanics , business , poisson distribution , geometry
In this article, nonlinear regression models for correlated count data are examined. Correlation within clusters is modelled by a multivariate Gaussian mixing process on the log‐expectation scale. The regression parameters and the variance‐covariance parameters of the mixing process are estimated using quasi‐likelihood methods. An example involving temporal trends in hospital admissions for respiratory disease is used to illustrate the methods proposed.