The Annals of Statistics

$k$-Statistics and Dispersion Effects in Regression

Peter McCullagh and Daryl Pregibon

Full-text: Open access

Abstract

By the term $k$-statistic or polykay, we mean an unbiased estimate of a cumulant or product of cumulants [Fisher (1929) and Tukey (1950), 1956)]. In this paper, two sets of unbiased estimates are given for the case where the mean response, $E(Y)$, depends linearly on known covariates $x$. The $k$'s are symmetric functions of the least-squares residuals and have previously been discussed by Anscombe (1961; 1981, Appendix 2). The $l$'s are optimal in the sense of having minimum variance under the ideal assumption of normality [Pukelsheim (1980)]. The emphasis here on computability leads to the algebraic inversion of direct product matrices of order $n^3 \times n^3$ and $n^4 \times n^4$, a computation that is rarely feasible numerically, even on the fastest computers. This algebra leads to simple straightforward formulae for all statistics up to degree four. Conditions are given under which the $k$'s are nearly or asymptotically optimal in the sense of being asymptotically equivalent to the corresponding $l$'s. A small-scale simulation study provides a comparison between these statistics for finite $n$. An application to detecting heterogeneity of variance, avoiding the assumption of normality, is given. A new test statistic for detecting systematic dispersion effects is introduced and compared to existing ones. Two examples illustrate the methodology.

Article information

Source
Ann. Statist., Volume 15, Number 1 (1987), 202-219.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176350261

Digital Object Identifier
doi:10.1214/aos/1176350261

Mathematical Reviews number (MathSciNet)
MR885732

Zentralblatt MATH identifier
0659.62025

JSTOR
links.jstor.org

Subjects
Primary: 63E30
Secondary: 62J05: Linear regression 62F35: Robustness and adaptive procedures 62N10

Keywords
Polykay cumulant residual test tensor generalized inverse heterogeneity of variance

Citation

McCullagh, Peter; Pregibon, Daryl. $k$-Statistics and Dispersion Effects in Regression. Ann. Statist. 15 (1987), no. 1, 202--219. doi:10.1214/aos/1176350261. https://projecteuclid.org/euclid.aos/1176350261


Export citation