Year: 2009
Type: report
Abstract: In this paper two kernel-based nonparametric estimators are proposed for estimating the components\nof an additive quantile regression model. The first estimator is a computationally convenient approach\nwhich can be viewed as a viable alternative to the method of De Gooijer and Zerom (2003). With the aim\nto reduce variance of the first estimator, a second estimator is defined via sequential fitting of univariate\nlocal polynomial quantile smoothing for each additive component with the other additive components\nreplaced by the corresponding estimates from the first estimator. The second estimator achieves oracle\nefficiency in the sense that each estimated additive component has the same variance as in the case when\nall other additive components were known. Asymptotic properties are derived for both estimators under\ndependent processes that are strictly stationary and absolutely regular. We also provide a demonstrative\nempirical application of additive quantile models to ambulance travel times.
Authors: Yebin Cheng, Jan De Gooijer, Dawit Zerom
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
Award: G2220785718
OpenAlex ID: W3146510363