The purpose of this chapter is to extend the M-estimation results of Chapter 14 to semiparametric M-estimation, where there is both a Euclidean parameter of interest Θ and a nuisance parameter η. Obviously, the semiparametric maximum likelihood estimators we have been discussing in the last several chapters are important examples of semiparametric M-estimators, where the objective function is an empirical likelihood. However, there are numerous other examples of semiparametric M-estimators, including estimators obtained from misspecified semiparametric likelihoods, least-squares, least-absolute deviation, and penalized maximum likelihood (which we discussed some in Sections 4.5 and 15.1 and elsewhere). In this chapter, we will try to provide general results on estimation and inference for semiparametric M-estimators, along with several illustrative examples. The material for this chapter is adapted from Ma and Kosorok (2005b).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
(2008). Semiparametric M-Estimation. In: Introduction to Empirical Processes and Semiparametric Inference. Springer Series in Statistics. Springer, New York, NY. https://doi.org/10.1007/978-0-387-74978-5_21
Download citation
DOI: https://doi.org/10.1007/978-0-387-74978-5_21
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-74977-8
Online ISBN: 978-0-387-74978-5
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)