Tests for Detecting Overdispersion in Poisson Regression Models

Abstract Poisson regression models are widely used in analyzing count data. This article develops tests for detecting extra-Poisson variation in such situations. The tests can be obtained as score tests against arbitrary mixed Poisson alternatives and are generalizations of tests of Fisher (1950) and Collings and Margolin (1985). Accurate approximations for computing significance levels are given, and the power of the tests against negative binomial alternatives is compared with those of the Pearson and deviance statistics. One way to test for extra-Poisson variation is to fit models that parametrically incorporate and then test for the absence of such variation within the models; for example, negative binomial models can be used in this way (Cameron and Trivedi 1986; Lawless 1987a). The tests in this article require only the Poisson model to be fitted. Two test statistics are developed that are motivated partly by a desire to have good distributional approximations for computing significance levels. Simu...

[1]  D. Brillinger,et al.  The natural variability of vital rates and associated statistics. , 1986, Biometrics.

[2]  Edward L. Frome,et al.  Regression Analysis of Poisson-Distributed Data , 1973 .

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

[4]  Peter McCullagh,et al.  The Conditional Distribution of Goodness-of-Fit Statistics for Discrete Data , 1986 .

[5]  P. A. P. Moran,et al.  On asymptotically optimal tests of composite hypotheses , 1970 .

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

[7]  R. W. Farebrother.  A Remark on Algorithms as 106, as 153 and as 155 the Distribution of a Linear Combination of X2 Random Variables , 1984 .

[8]  L. Fahrmeir,et al.  Correction: Consistency and Asymptotic Normality of the Maximum Likelihood Estimator in Generalized Linear Models , 1985 .

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

[10]  J. Lawless.  Regression Methods for Poisson Process Data , 1987 .

[11]  Barry H. Margolin,et al.  Testing Goodness of Fit for the Poisson Assumption When Observations are Not Identically Distributed , 1985 .

[12]  R. L. Plackett,et al.  Inference sensitivity for Poisson mixtures , 1978 .

[13]  E. Frome.  The analysis of rates using Poisson regression models. , 1983, Biometrics.

[14]  M. Woodbury,et al.  A variance components approach to categorical data models with heterogeneous cell populations: analysis of spatial gradients in lung cancer mortality rates in North Carolina counties. , 1981, Biometrics.

[15]  S. Haberman,et al.  The analysis of frequency data , 1974 .

[16]  David R. Cox,et al.  Some remarks on overdispersion , 1983 .

[17]  Lung-fei Lee,et al.  Specification Test for Poisson Regression Models , 1986 .

[18]  A. Cameron,et al.  Econometric models based on count data. Comparisons and applications of some estimators and tests , 1986 .

[19]  Rory A. Fisher,et al.  The significance of deviations from expectation in a Poisson Series. , 1950 .

[20]  J. Lawless.  Negative binomial and mixed Poisson regression , 1987 .

[21]  Andrew Chesher,et al.  Testing for Neglected Heterogeneity , 1984 .