Bandwidth Selection for Weighted Kernel Density Estimation

  title={Bandwidth Selection for Weighted Kernel Density Estimation},
  author={Bin Wang and Xiaofeng Wang},
Abstract: Weighted kernel-density estimates (wKDE) are broadly used in many statistical areas, for instant, density estimation under right-censoring. However, bandwidth selection could be a problem by reweighting the kernels. In this paper, we investigate the methods of bandwidth selection for wKDE. Three mean integrated squared error based bandwidth selection methods are introduced. The least-squares cross-validation method, the adaptive weight kernel density estimator and boundary problems… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 34 references

Density Estimation for Statistics and Data Analysis

  • B. W. Silverman
  • Chapman and Hall. Monographs on Statistics and…
  • 1986
Highly Influential
5 Excerpts

Density Estimation for Statistics and Data Analy

  • B. W. Silverman
  • Monographs on Statistics and Applied Probability
  • 1986
Highly Influential
1 Excerpt

On estimation of a probability density function and mode

  • E. Parzen
  • Ann. Math. Statist
  • 1962
Highly Influential
1 Excerpt

Inferences from biased samples with a memory effect

  • B. Wang, J. Sun
  • Journal of Statistical planning and inference…
  • 2007
1 Excerpt

Bayes bandwidth selection in kernel density estimation with censored data

  • K. B. Kulasekera, W. J. Padgett
  • Nonparametric Statistics
  • 2006
1 Excerpt

Survival Analysis: Techniques for Censored and Truncated Data, Second Edition

  • J. P. Klein, M. L. Moeschberger
  • 2003
1 Excerpt

Weighted samples, kernel density estimators and convergence

  • Gisbert, Francisco J. Goerlich
  • Empirical Economics
  • 2003
2 Excerpts

Similar Papers

Loading similar papers…