The Annals of Statistics

Bootstrap Simultaneous Error Bars for Nonparametric Regression

W. Hardle and J. S. Marron

Full-text: Open access

Abstract

Simultaneous error bars are constructed for nonparametric kernel estimates of regression functions. The method is based on the bootstrap, where resampling is done from a suitably estimated residual distribution. The error bars are seen to give asymptotically correct coverage probabilities uniformly over any number of gridpoints. Applications to an economic problem are given and comparison to both pointwise and Bonferroni-type bars is presented through a simulation study.

Article information

Source
Ann. Statist., Volume 19, Number 2 (1991), 778-796.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176348120

Digital Object Identifier
doi:10.1214/aos/1176348120

Mathematical Reviews number (MathSciNet)
MR1105844

Zentralblatt MATH identifier
0725.62037

JSTOR
links.jstor.org

Subjects
Primary: 62G05: Estimation
Secondary: 62G99: None of the above, but in this section

Keywords
Bootstrap error bars kernel smoothing nonparametric regression variability bound

Citation

Hardle, W.; Marron, J. S. Bootstrap Simultaneous Error Bars for Nonparametric Regression. Ann. Statist. 19 (1991), no. 2, 778--796. doi:10.1214/aos/1176348120. https://projecteuclid.org/euclid.aos/1176348120


Export citation