The Annals of Statistics

Profile Likelihood and Conditionally Parametric Models

Thomas A. Severini and Wing Hung Wong

Full-text: Open access

Abstract

In this paper, we outline a general approach to estimating the parametric component of a semiparametric model. For the case of a scalar parametric component, the method is based on the idea of first estimating a one-dimensional subproblem of the original problem that is least favorable in the sense of Stein. The likelihood function for the scalar parameter along this estimated subproblem may be viewed as a generalization of the profile likelihood for the problem. The scalar parameter is then estimated by maximizing this "generalized profile likelihood." This method of estimation is applied to a particular class of semiparametric models, where it is shown that the resulting estimator is asymptotically efficient.

Article information

Source
Ann. Statist., Volume 20, Number 4 (1992), 1768-1802.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176348889

Digital Object Identifier
doi:10.1214/aos/1176348889

Mathematical Reviews number (MathSciNet)
MR1193312

Zentralblatt MATH identifier
0768.62015

JSTOR
links.jstor.org

Subjects
Primary: 62F35: Robustness and adaptive procedures
Secondary: 62G07: Density estimation 62F10: Point estimation

Keywords
Efficiency estimation nonparametric semiparametric

Citation

Severini, Thomas A.; Wong, Wing Hung. Profile Likelihood and Conditionally Parametric Models. Ann. Statist. 20 (1992), no. 4, 1768--1802. doi:10.1214/aos/1176348889. https://projecteuclid.org/euclid.aos/1176348889


Export citation