Likelihood inferences for the link function without knowing the true underlying distributions

This article is concerned with inference about link function in generalized linear models. A parametric and yet robust likelihood approach is introduced to accomplish the intended goal. More specifically, it is demonstrated that one can convert normal and gamma likelihoods into robust likelihood functions for the link function. The asymptotic validity of the robust likelihood requires only the existence of the second moments of the underlying distributions. The application of this novel robust likelihood method is demonstrated on the Box–Cox transformation. Simulation studies and real data analysis are provided to demonstrate the efficacy of the new parametric robust procedures.