Non-asymptotic tests of model performance

TY - JOUR

T1 - Non-asymptotic tests of model performance

AU - Chassang, Sylvain

PY - 2009/9

Y1 - 2009/9

N2 - This paper describes a non-asymptotic approach to the problem of selection bias in economic forecasting. By using non-asymptotic measure concentration results, it is possible to deal with settings in which the class of potential models is large with respect to the number of data points. The bounds on p values obtained by these methods are necessarily conservative, but they provide a useful benchmark for model selection in settings where asymptotics may not apply.

AB - This paper describes a non-asymptotic approach to the problem of selection bias in economic forecasting. By using non-asymptotic measure concentration results, it is possible to deal with settings in which the class of potential models is large with respect to the number of data points. The bounds on p values obtained by these methods are necessarily conservative, but they provide a useful benchmark for model selection in settings where asymptotics may not apply.

KW - Model selection

KW - Non-asymptotic tests

KW - Selection bias

UR - http://www.scopus.com/inward/record.url?scp=76349110990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76349110990&partnerID=8YFLogxK

U2 - 10.1007/s00199-008-0408-y

DO - 10.1007/s00199-008-0408-y

M3 - Article

SN - 0938-2259

VL - 41

SP - 495

EP - 514

JO - Economic Theory

JF - Economic Theory

IS - 3

ER -