Translator Disclaimer
August 1998 Maximin clusters for near-replicate regression lack of fit tests
Forrest R. Miller, James W. Neill, Brian W. Sherfey
Ann. Statist. 26(4): 1411-1433 (August 1998). DOI: 10.1214/aos/1024691249


To assess the adequacy of a nonreplicated linear regression model, Christensen introduced the concepts of orthogonal between- and within-cluster lack of fit with corresponding optimal tests. However, the properties of these tests depend on the choice of near-replicate clusters. In this paper, a graph theoretic framework is presented to represent candidate clusterings. A clustering is then selected according to a proposed maximin power criterion from among the clusterings consistent with a specified graph on the predictor settings. Examples are given to illustrate the methodology.


Download Citation

Forrest R. Miller. James W. Neill. Brian W. Sherfey. "Maximin clusters for near-replicate regression lack of fit tests." Ann. Statist. 26 (4) 1411 - 1433, August 1998.


Published: August 1998
First available in Project Euclid: 21 June 2002

zbMATH: 0932.62075
MathSciNet: MR1647726
Digital Object Identifier: 10.1214/aos/1024691249

Primary: 62J05
Secondary: 62F03

Rights: Copyright © 1998 Institute of Mathematical Statistics


Vol.26 • No. 4 • August 1998
Back to Top