The Annals of Statistics

Orthogonal Series Methods for Both Qualitative and Quantitative Data

Peter Hall

Full-text: Open access

Abstract

We introduce and describe orthogonal series methods for estimating the density of qualitative, quantitative or mixed data. The techniques are completely nonparametric in character, and so may be used in situations where parametric models are difficult to construct. Just this situation arises in the context of mixed--both qualitative and quantitative--data, where there are few parametric models.

Article information

Source
Ann. Statist., Volume 11, Number 3 (1983), 1004-1007.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176346268

Digital Object Identifier
doi:10.1214/aos/1176346268

Mathematical Reviews number (MathSciNet)
MR707952

Zentralblatt MATH identifier
0515.62036

JSTOR
links.jstor.org

Subjects
Primary: 62G05: Estimation
Secondary: 62E20: Asymptotic distribution theory

Keywords
Classification cross-validation density estimator discrete data discrimination near neighbour orthogonal series qualitative data smoothing

Citation

Hall, Peter. Orthogonal Series Methods for Both Qualitative and Quantitative Data. Ann. Statist. 11 (1983), no. 3, 1004--1007. doi:10.1214/aos/1176346268. https://projecteuclid.org/euclid.aos/1176346268


Export citation