TY - JOUR

T1 - Integrated likelihood inference in semiparametric regression models

AU - He, H.

AU - Severini, T. A.

N1 - Funding Information:
Acknowledgments This work was presented at the conference “Recent advances in statistical inference: theory and case studies” held in Padova in March, 2013. We would like to thank the discussants at the conference, B. Liseo and N. Sartori, as well as a referee, for a number of useful comments. The work of TS was supported by the U.S. National Science Foundation.

PY - 2014/8

Y1 - 2014/8

N2 - Consider a linear semiparametric regression model with normal errors in which the mean function depends on two parameters, a p-dimensional regression parameter, which is the parameter of interest, and an unknown function, which is a nuisance parameter. We consider estimation of the parameter of interest using an integrated likelihood function, in which the nuisance parameter is eliminated from the likelihood function by averaging with respect to some distribution. Here we take this distribution to be a Gaussian process with a given covariance function, whichmay depend on additional parameters. Likelihood inference based on the resulting integrated likelihood is considered and the properties of the score statistic based on the integrated likelihood, the maximum integrated likelihood estimator, and the integrated likelihood ratio statistic are presented. The methodology is illustrated on two examples.

AB - Consider a linear semiparametric regression model with normal errors in which the mean function depends on two parameters, a p-dimensional regression parameter, which is the parameter of interest, and an unknown function, which is a nuisance parameter. We consider estimation of the parameter of interest using an integrated likelihood function, in which the nuisance parameter is eliminated from the likelihood function by averaging with respect to some distribution. Here we take this distribution to be a Gaussian process with a given covariance function, whichmay depend on additional parameters. Likelihood inference based on the resulting integrated likelihood is considered and the properties of the score statistic based on the integrated likelihood, the maximum integrated likelihood estimator, and the integrated likelihood ratio statistic are presented. The methodology is illustrated on two examples.

KW - Gaussian process

KW - Likelihood inference

KW - Likelihood ratio test

KW - Semiparametric Estimation

UR - http://www.scopus.com/inward/record.url?scp=84905234995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905234995&partnerID=8YFLogxK

U2 - 10.1007/s40300-014-0042-3

DO - 10.1007/s40300-014-0042-3

M3 - Article

AN - SCOPUS:84905234995

SN - 0026-1424

VL - 72

SP - 185

EP - 199

JO - Metron

JF - Metron

IS - 2

ER -