Overview of Semiparametric Inference
This chapter presents an overview of the main ideas and techniques of semiparametric inference, with particular emphasis on semiparametric efficiency. The major distinction between this kind of efficiency and the standard notion of efficiency for parametric maximum likelihood estimators—as expressed in the Cramér-Rao lower bound—is the presence of an infinite-dimensional nuisance parameter in semiparametric models. Proofs and other technical details will generally be postponed until Part III.
KeywordsScore Function Maximum Likelihood Estimator Nuisance Parameter Empirical Likelihood Partial Likelihood
Unable to display preview. Download preview PDF.