Nonparametric significance testing

Pascal Lavergne, Quang Vuong

    Research output: Contribution to journalArticle

    Abstract

    A procedure for testing the significance of a subset of explanatory variables in a nonparametric regression is proposed. Our test statistic uses the kernel method. Under the null hypothesis of no effect of the variables under test, we show that our test statistic has an nh p2/2 standard normal limiting distribution, where p 2 is the dimension of the complete set of regressors. Our test is one-sided, consistent against all alternatives and detects local alternatives approaching the null at rate slower than n -1/2 h -p2/4. Our Monte-Carlo experiments indicate that it outperforms the test proposed by Fan and Li (1996, Econometrica 64, 865-890).

    Original languageEnglish (US)
    Pages (from-to)576-601
    Number of pages26
    JournalEconometric Theory
    Volume16
    Issue number4
    StatePublished - 2000

    Fingerprint

    statistics
    fan
    Testing
    regression
    experiment
    Test statistic
    Limiting distribution
    Monte Carlo experiment
    Nonparametric regression
    Kernel methods
    Local alternatives

    ASJC Scopus subject areas

    • Economics and Econometrics
    • Social Sciences (miscellaneous)

    Cite this

    Lavergne, P., & Vuong, Q. (2000). Nonparametric significance testing. Econometric Theory, 16(4), 576-601.

    Nonparametric significance testing. / Lavergne, Pascal; Vuong, Quang.

    In: Econometric Theory, Vol. 16, No. 4, 2000, p. 576-601.

    Research output: Contribution to journalArticle

    Lavergne, P & Vuong, Q 2000, 'Nonparametric significance testing', Econometric Theory, vol. 16, no. 4, pp. 576-601.
    Lavergne P, Vuong Q. Nonparametric significance testing. Econometric Theory. 2000;16(4):576-601.
    Lavergne, Pascal ; Vuong, Quang. / Nonparametric significance testing. In: Econometric Theory. 2000 ; Vol. 16, No. 4. pp. 576-601.
    @article{cd9aa86ec9624c06a62c1372857d2b6a,
    title = "Nonparametric significance testing",
    abstract = "A procedure for testing the significance of a subset of explanatory variables in a nonparametric regression is proposed. Our test statistic uses the kernel method. Under the null hypothesis of no effect of the variables under test, we show that our test statistic has an nh p2/2 standard normal limiting distribution, where p 2 is the dimension of the complete set of regressors. Our test is one-sided, consistent against all alternatives and detects local alternatives approaching the null at rate slower than n -1/2 h -p2/4. Our Monte-Carlo experiments indicate that it outperforms the test proposed by Fan and Li (1996, Econometrica 64, 865-890).",
    author = "Pascal Lavergne and Quang Vuong",
    year = "2000",
    language = "English (US)",
    volume = "16",
    pages = "576--601",
    journal = "Econometric Theory",
    issn = "0266-4666",
    publisher = "Cambridge University Press",
    number = "4",

    }

    TY - JOUR

    T1 - Nonparametric significance testing

    AU - Lavergne, Pascal

    AU - Vuong, Quang

    PY - 2000

    Y1 - 2000

    N2 - A procedure for testing the significance of a subset of explanatory variables in a nonparametric regression is proposed. Our test statistic uses the kernel method. Under the null hypothesis of no effect of the variables under test, we show that our test statistic has an nh p2/2 standard normal limiting distribution, where p 2 is the dimension of the complete set of regressors. Our test is one-sided, consistent against all alternatives and detects local alternatives approaching the null at rate slower than n -1/2 h -p2/4. Our Monte-Carlo experiments indicate that it outperforms the test proposed by Fan and Li (1996, Econometrica 64, 865-890).

    AB - A procedure for testing the significance of a subset of explanatory variables in a nonparametric regression is proposed. Our test statistic uses the kernel method. Under the null hypothesis of no effect of the variables under test, we show that our test statistic has an nh p2/2 standard normal limiting distribution, where p 2 is the dimension of the complete set of regressors. Our test is one-sided, consistent against all alternatives and detects local alternatives approaching the null at rate slower than n -1/2 h -p2/4. Our Monte-Carlo experiments indicate that it outperforms the test proposed by Fan and Li (1996, Econometrica 64, 865-890).

    UR - http://www.scopus.com/inward/record.url?scp=0034401133&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0034401133&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:0034401133

    VL - 16

    SP - 576

    EP - 601

    JO - Econometric Theory

    JF - Econometric Theory

    SN - 0266-4666

    IS - 4

    ER -