Maximin clusters for near-replicate regression lack of fit tests
Miller, Forrest R. ; Neill, James W. ; Sherfey, Brian W.
Ann. Statist., Tome 26 (1998) no. 3, p. 1411-1433 / Harvested from Project Euclid
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.
Publié le : 1998-08-14
Classification:  Regression,  lack of fit,  nonreplication,  between clusters,  within clusters,  maximin power,  graph theory,  62J05,  62F03
@article{1024691249,
     author = {Miller, Forrest R. and Neill, James W. and Sherfey, Brian W.},
     title = {Maximin clusters for near-replicate regression lack of fit
		 tests},
     journal = {Ann. Statist.},
     volume = {26},
     number = {3},
     year = {1998},
     pages = { 1411-1433},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1024691249}
}
Miller, Forrest R.; Neill, James W.; Sherfey, Brian W. Maximin clusters for near-replicate regression lack of fit
		 tests. Ann. Statist., Tome 26 (1998) no. 3, pp.  1411-1433. http://gdmltest.u-ga.fr/item/1024691249/