The Annals of Statistics

A bandwidth selector for local linear density estimators

Ming-Yen Cheng

Full-text: Open access

Abstract

Local linear density estimators achieve automatic boundary corrections and enjoy some typical optimal properties. Proper choice of the smoothing parameters is crucial for their performance. A data-based bandwidth selector is developed in the spirit of plug-in rules. Consistency and asymptotic normality of the selected bandwidth are demonstrated. The bandwidth is very efficient regardless of whether there are non-smooth boundaries in the support of the density or not.

Article information

Source
Ann. Statist., Volume 25, Number 3 (1997), 1001-1013.

Dates
First available in Project Euclid: 20 November 2003

Permanent link to this document
https://projecteuclid.org/euclid.aos/1069362735

Digital Object Identifier
doi:10.1214/aos/1069362735

Mathematical Reviews number (MathSciNet)
MR1447738

Zentralblatt MATH identifier
0876.62031

Subjects
Primary: 62G07: Density estimation

Keywords
Bandwidth boundary effects data binning local linear density estimation plug-in bandwidth selector

Citation

Cheng, Ming-Yen. A bandwidth selector for local linear density estimators. Ann. Statist. 25 (1997), no. 3, 1001--1013. doi:10.1214/aos/1069362735. https://projecteuclid.org/euclid.aos/1069362735


Export citation