Adaptive Kernel in Meshsize Boosting Algorithm in KDE

Abstract

This paper proposes the use of adaptive kernel in a meshsize boosting
algorithm in kernel density estimation. The algorithm is a bias reduction
scheme like other existing schemes but uses adaptive kernel instead of the
regular fixed kernels. An empirical study for this scheme is conducted and
the findings are comparatively attractive.

Key Words: Boosting, kernel density estimates, bias reduction, adaptive
kernel, meshsize, noises