Quasi-Likelihood Estimation in the Presence of a Nuisance Parameter

Abstract

In this paper, we propose an asymptotically efficient method for quasi-likelihood estimation for the parameter of interest. To estimate the parameter of interest, we propose an unbiased estimating function for both the parameter of interest and the nuisance parameter. the resulting estimator for the parameter of interest is asymptotically equivalent to its quasi-score estimator given the nuisance parameter. Finally, we compare the small sample performance of resulting estimator with that of the quasi-score estimator given the nuisance parameter.

In this paper, we propose an asymptotically efficient method for quasi-likelihood estimation for the parameter of interest. To estimate the parameter of interest, we propose an unbiased estimating function for both the parameter of interest and the nuisance parameter. the resulting estimator for the parameter of interest is asymptotically equivalent to its quasi-score estimator given the nuisance parameter. Finally, we compare the small sample performance of resulting estimator with that of the quasi-score estimator given the nuisance parameter.