Variable bandwidth selection in varying-coefficient models

Zhang, W.Y. and Lee, S.Y. (2000) Variable bandwidth selection in varying-coefficient models. Journal of Multivariate Analysis, 74 (1). pp. 116-134. ISSN 0047-259X. (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1006/jmva.1999.1883

Abstract

The varying-coefficient model is an attractive alternative to the additive and other models. One important method in estimating the coefficient functions in this model is the local polynomial fitting approach. In this approach, the choice of bandwidth is crucial. If the unknown curve is spatial homogeneous, a constant bandwidth is sufficient. However, for estimating curves with a more complicated structure, a variable bandwidth is needed. The present article focuses on a variable bandwidth selection procedure, and provides the conditional bias and the conditional variance of the estimator, the convergence rate of the bandwidth, and the asymptotic distribution of its error relative to the theoretical optimal variable bandwidth.

Item Type: Article
Uncontrolled keywords: varying-coefficient models; local polynomial fitting; data-driven bandwidth selection; relative error; asymptotic normality; assessment of conditional bias and variance
Subjects: Q Science > QA Mathematics (inc Computing science) > QA273 Probabilities
H Social Sciences > HA Statistics
Divisions: Faculties > Science Technology and Medical Studies > School of Mathematics Statistics and Actuarial Science
Depositing User: A. Xie
Date Deposited: 13 Mar 2009 16:19
Last Modified: 13 Mar 2009 16:21
Resource URI: http://kar.kent.ac.uk/id/eprint/16764 (The current URI for this page, for reference purposes)
  • Depositors only (login required):