Generalizations of the arc sine laws are shown to provide insight into the operating characteristics of certain techniques for selecting models to fit a given data set, when the available models are nested. As a corollary, one sees that a popular technique may be expected to include about one superfluous parameter, even if the sample size is large.
Publié le : 1982-12-14
Classification:
Akaike's criterion,
Asymptotic distributions,
Mallows $C_p$,
Random walks,
62F99,
62J05
@article{1176345983,
author = {Woodroofe, Michael},
title = {On Model Selection and the ARC Sine Laws},
journal = {Ann. Statist.},
volume = {10},
number = {1},
year = {1982},
pages = { 1182-1194},
language = {en},
url = {http://dml.mathdoc.fr/item/1176345983}
}
Woodroofe, Michael. On Model Selection and the ARC Sine Laws. Ann. Statist., Tome 10 (1982) no. 1, pp. 1182-1194. http://gdmltest.u-ga.fr/item/1176345983/