Adaptive Bandwidth Choice for Kernel Regression

Abstract

A data-based procedure is introduced for local bandwidth selection for kernel estimation of a regression function at a point. The estimated bandwidth is shown to be consistent and asymptotically normal as an estimator of the (asymptotic) optimal value for minimum mean square estimation. The rate of convergence is identical to that of plug-in bandwidth estimators. The proposed method has the practical advantage that it reduces the need for a priori values and does not require pilot estimates of the regression function, optimization of estimated objective functions or resampling. A small Monte Carlo study is used to examine the behavior of the new bandwidth estimator in a variety of situations. The resulting finite-sample mean square errors of the corresponding curve estimates are generally found to be less than or equal to those of an idealized plug-in estimator. (kr)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 19, 1990
Accession Number
ADA228437

Entities

People

  • R. L. Eubank
  • W. R. Schucany

Organizations

  • Southern Methodist University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Asymptotic Normality
  • Bandwidth
  • Convergence
  • Data Science
  • Estimators
  • Information Science
  • Normality
  • Optimization
  • Probability
  • Random Variables
  • Regression Analysis
  • Standards
  • Statistical Algorithms
  • Statistics
  • Surveys
  • Validation

Fields of Study

  • Mathematics

Readers

  • Statistical inference.