Bandwidth Selection in Local Polynomial Regression Using Eigenvalues
Authors:
- 21 December 2005
- journal article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 68 (1) , 135-154
Abstract
Summary: Local polynomial regression is commonly used for estimating regression functions. In practice, however, with rough functions or sparse data, a poor choice of bandwidth can lead to unstable estimates of the function or its derivatives. We derive a new expression for the leading term of the bias by using the eigenvalues of the weighted design matrix where the bias depends on the arrangement of the X-values in the bandwidth window. We then use this result to determine a local data-driven bandwidth selection method and to provide a diagnostic for poor bandwidths that are chosen by using other methods. We show that our data-driven bandwidth is asymptotically equivalent to the optimal local bandwidth and that it performs well for relatively small samples when compared with other methods. In addition, we provide simulation results for first-derivative estimation. We illustrate its performance with data from Mars Global Surveyor.Keywords
Funding Information
- National Science Foundation (0105852)
This publication has 19 references indexed in Scilit:
- Efficient Bandwidth Selection in Non‐parametric RegressionScandinavian Journal of Statistics, 2003
- Data sharpening methods for bias reduction in nonparametric regressionThe Annals of Statistics, 2000
- The Structure of the Upper Atmosphere of Mars: In Situ Accelerometer Measurements from Mars Global SurveyorScience, 1998
- Empirical-Bias Bandwidths for Local Polynomial Nonparametric Regression and Density EstimationJournal of the American Statistical Association, 1997
- Finite-Sample Variance of Local Polynomials: Analysis and SolutionsJournal of the American Statistical Association, 1996
- An Effective Bandwidth Selector for Local Least Squares RegressionJournal of the American Statistical Association, 1995
- Adaptive Bandwidth Choice for Kernel RegressionJournal of the American Statistical Association, 1995
- Design-adaptive Nonparametric RegressionJournal of the American Statistical Association, 1992
- Kernel estimation of regression functions1979
- Consistent Nonparametric RegressionThe Annals of Statistics, 1977