Out-of-sample bootstrap tests for non-nested models

Patrick Mair; Achim Zeileis

Out-of-sample bootstrap tests for non-nested models

Patrick Mair
, Achim Zeileis

Institute for Statistics and Mathematics

Publication: Chapter in book/Conference proceeding › Contribution to conference proceedings

Abstract

When testing non-nested models, the asymptotic distribution theory of the ordinary likelihood
ratio statistic is not valid anymore. Several test statistics, some of them based on
information criteria, have been proposed in order to test such non-nested hypotheses. Concerning
bootstrap approaches to simulate goodness-of-fit measures such as the likelihood ratio
value, have been elaborated as well. Based on these methods, we extend existing bootstrap
simulations towards out-of-sample bootstrap evaluation. As an application, a parametric
bootstrap on simulated regression data is provided.

Original language	English
Title of host publication	Proceedings of the 22nd Workshop on Statistical Modelling
Editors	Joan del Castillo, Anna Espinal, Pedro Puig
Pages	427 - 430
Publication status	Published - 1 Dec 2007

Cite this

@inproceedings{be54760872714029a0e07ddbd25e6112,

title = "Out-of-sample bootstrap tests for non-nested models",

abstract = "When testing non-nested models, the asymptotic distribution theory of the ordinary likelihood ratio statistic is not valid anymore. Several test statistics, some of them based on information criteria, have been proposed in order to test such non-nested hypotheses. Concerning bootstrap approaches to simulate goodness-of-fit measures such as the likelihood ratio value, have been elaborated as well. Based on these methods, we extend existing bootstrap simulations towards out-of-sample bootstrap evaluation. As an application, a parametric bootstrap on simulated regression data is provided.",

author = "Patrick Mair and Achim Zeileis",

year = "2007",

month = dec,

day = "1",

language = "English",

pages = "427 -- 430",

editor = "\{Joan del Castillo, Anna Espinal, Pedro Puig\}",

booktitle = "Proceedings of the 22nd Workshop on Statistical Modelling",

}

TY - GEN

T1 - Out-of-sample bootstrap tests for non-nested models

AU - Mair, Patrick

AU - Zeileis, Achim

PY - 2007/12/1

Y1 - 2007/12/1

N2 - When testing non-nested models, the asymptotic distribution theory of the ordinary likelihood ratio statistic is not valid anymore. Several test statistics, some of them based on information criteria, have been proposed in order to test such non-nested hypotheses. Concerning bootstrap approaches to simulate goodness-of-fit measures such as the likelihood ratio value, have been elaborated as well. Based on these methods, we extend existing bootstrap simulations towards out-of-sample bootstrap evaluation. As an application, a parametric bootstrap on simulated regression data is provided.

AB - When testing non-nested models, the asymptotic distribution theory of the ordinary likelihood ratio statistic is not valid anymore. Several test statistics, some of them based on information criteria, have been proposed in order to test such non-nested hypotheses. Concerning bootstrap approaches to simulate goodness-of-fit measures such as the likelihood ratio value, have been elaborated as well. Based on these methods, we extend existing bootstrap simulations towards out-of-sample bootstrap evaluation. As an application, a parametric bootstrap on simulated regression data is provided.

UR - http://statmath.wu.ac.at/~zeileis/papers/Mair+Zeileis-2007.pdf

M3 - Contribution to conference proceedings

SP - 427

EP - 430

BT - Proceedings of the 22nd Workshop on Statistical Modelling

A2 - Joan del Castillo, Anna Espinal, Pedro Puig, null

ER -

Out-of-sample bootstrap tests for non-nested models

Abstract

Other files and links

Cite this