Semiparametric Regression Functionals
- 1 March 1995
- journal article
- research article
- Published by JSTOR in Journal of the American Statistical Association
- Vol. 90 (429) , 95
- https://doi.org/10.2307/2291133
Abstract
A regression method is developed for a general class of functionals. A semiparametric linear model is adopted, and the regression parameters are estimated by maximizing a profiled nonparametric or empirical likelihood based on a local estimate of the conditional distribution function. Simulated and real data examples are shown, including an application of quantile regression to censored survival data from a clinical trial for myeloma.Keywords
This publication has 0 references indexed in Scilit: