|
Activity Number:
|
30
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #303276 |
|
Title:
|
Spline-Backfitted Kernal Smoothing of Partially Linear Additive Model
|
|
Author(s):
|
Shujie Ma*+ and Lijian Yang
|
|
Companies:
|
Michigan State University and Michigan State University
|
|
Address:
|
Department of Statistics and Probability, East Lansing, MI, 48824,
|
|
Keywords:
|
Bandwidths ; B spline ; knots ; local linear estimator ; mixing ; Nadaraya-Watson estimator
|
|
Abstract:
|
A spline-backfitted kernel smoothing method is proposed for partially linear additive model. Under mild assumptions such as geometric mixing and stationarity of the data, the proposed function and parameter estimators are oracally efficient and fast to compute, and especially appealing when the data dimension is high. Such superior properties are achieved by applying spline smoothing to the data in step one and kernel smoothing to a pseudo data in step two. Simulation experiments with both moderate and large number of variables confirm the asymptotic results.
|
