On Local Bandwidth Selection for Density Estimation

Article type: Research Article

Authors: Rudzkis, Rimantas | Kavaliauskas, Mindaugas

Affiliations: Statistics Center of Vytautas Magnus University and Institute of Mathematics and Informatics, Vileikos 8, 3000 Kaunas, Lithuania. E-mail: rudzkis@ktl.mii.lt

Abstract: This article gives ideas for developing statistics software which can work without user intervention. Some popular methods of bandwidth selection for kernel density estimation (the nearest neighbour, least squares cross-validation, “plug-in” technique) are discussed. Modifications of the cross-validation criterion are proposed. Two-stage estimators combining these methods with multiplicative bias correction are investigated by simulation means.

Keywords: kernel density estimation, local bandwidth selection, cross-validation, multiplicative bias correction

DOI: 10.3233/INF-1998-9408

Journal: Informatica, vol. 9, no. 4, pp. 479-490, 1998