The Annals of Statistics

New Tools for Residual Analysis

A. P. Dempster and M. Gasko-Green

Full-text: Open access

Abstract

Techniques are presented for stepwise selection of observations in order of discrepancy from a linear model, and for assigning a $P$ value to each selected observation. A general class of criteria for discrepancy is defined, and leading members of the class are discussed. Two ways to define the sequence of $P$ values for a general selection criterion are discussed, and their relative advantages are compared. The techniques are illustrated on several data sets using only the computationally simpler of the two approaches to $P$ values.

Article information

Source
Ann. Statist., Volume 9, Number 5 (1981), 945-959.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176345575

Digital Object Identifier
doi:10.1214/aos/1176345575

Mathematical Reviews number (MathSciNet)
MR628751

Zentralblatt MATH identifier
0477.62052

JSTOR
links.jstor.org

Subjects
Primary: 62J05: Linear regression
Secondary: 62F07: Ranking and selection

Keywords
Linear models regression outliers residuals influence

Citation

Dempster, A. P.; Gasko-Green, M. New Tools for Residual Analysis. Ann. Statist. 9 (1981), no. 5, 945--959. doi:10.1214/aos/1176345575. https://projecteuclid.org/euclid.aos/1176345575


Export citation