Non-asymptotic tests of model performance

Sylvain Chassang

    Research output: Contribution to journalArticle

    Abstract

    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.

    Original languageEnglish (US)
    Pages (from-to)495-514
    Number of pages20
    JournalEconomic Theory
    Volume41
    Issue number3
    DOIs
    StatePublished - Sep 2009

    Keywords

    • Model selection
    • Non-asymptotic tests
    • Selection bias

    ASJC Scopus subject areas

    • Economics and Econometrics

    Fingerprint Dive into the research topics of 'Non-asymptotic tests of model performance'. Together they form a unique fingerprint.

  • Cite this