Bias Correction in Generalized Nonlinear Models with Dispersion Covariates

Abstract

We derive general formulae for the second-order biases of maximum likelihood estimates of the parameters in generalized nonlinear models with dispersion covariates. This result generalizes previous work by Botter and Cordeiro (1998) and Cordeiro and McCullagh (1991). The practical use of such bias corrections is illustrated in a simulation study.

Keywords:

• Bias correction
• Dispersion parameter
• Generalized nonlinear model
• Maximum likelihood
• Precision parameter

Mathematics Subject Classification:

• Primary 62J05
• Secondary 62E20