English

Limitations Of Richardson Extrapolation For Kernel Density Estimation

Probability 2018-12-21 v1

Abstract

This paper develops the process of using Richardson Extrapolation to improve the Kernel Density Estimation method, resulting in a more accurate (lower Mean Squared Error) estimate of a probability density function for a distribution of data in RdR_d given a set of data from the distribution. The method of Richardson Extrapolation is explained, showing how to fix conditioning issues that arise with higher-order extrapolations. Then, it is shown why higher-order estimators do not always provide the best estimate, and it is discussed how to choose the optimal order of the estimate. It is shown that given n one-dimensional data points, it is possible to estimate the probability density function with a mean squared error value on the order of only n1ln(n)n^{-1}\sqrt{\ln(n)}. Finally, this paper introduces a possible direction of future research that could further minimize the mean squared error.

Keywords

Cite

@article{arxiv.1812.08619,
  title  = {Limitations Of Richardson Extrapolation For Kernel Density Estimation},
  author = {Ruben G. Ascoli},
  journal= {arXiv preprint arXiv:1812.08619},
  year   = {2018}
}

Comments

14 pages, 3 figures

R2 v1 2026-06-23T06:51:25.875Z