Minimum chi-square estimation and tests for model selection

Quang Vuong, Weiren Wang

    Research output: Contribution to journalArticle

    Abstract

    This paper studies the problem of model selection based on Pearson chi-square type statistics. Such goodness-of-fit statistics have been considered by Moore (1978) and diagnostic tests based on them have recently been extended to general econometric models by Andrews (1988a, b). Here we consider another important use of these statistics. Specifically, we propose some convenient asymptotically standard normal tests for model selection based on chi-square type statistics. Following Vuong (1989), the null hypothesis is that the competing models are equally close to the data-generating process (DGP) vs. the alternative hypotheses that one model is closer to the DGP where closeness of a model is measured according to the discrepancy implicit in the Pearson type statistic used. Our model selection tests have the desirable feature that neither model needs to be correctly specified nor nested in each other. As a prerequisite, we study the corresponding class of minimum chi-square estimators.

    Original languageEnglish (US)
    Pages (from-to)141-168
    Number of pages28
    JournalJournal of Econometrics
    Volume56
    Issue number1-2
    DOIs
    StatePublished - 1993

    Fingerprint

    Chi-square
    Model Selection
    Statistics
    Diagnostic Tests
    Model
    Goodness of fit
    Econometrics
    Null hypothesis
    Discrepancy
    Statistic
    Model selection
    Estimator
    Alternatives
    Data generating process

    ASJC Scopus subject areas

    • Economics and Econometrics
    • Finance
    • Statistics and Probability

    Cite this

    Minimum chi-square estimation and tests for model selection. / Vuong, Quang; Wang, Weiren.

    In: Journal of Econometrics, Vol. 56, No. 1-2, 1993, p. 141-168.

    Research output: Contribution to journalArticle

    Vuong, Quang ; Wang, Weiren. / Minimum chi-square estimation and tests for model selection. In: Journal of Econometrics. 1993 ; Vol. 56, No. 1-2. pp. 141-168.
    @article{b5c59388191549d1ba6c6bbad70ed4af,
    title = "Minimum chi-square estimation and tests for model selection",
    abstract = "This paper studies the problem of model selection based on Pearson chi-square type statistics. Such goodness-of-fit statistics have been considered by Moore (1978) and diagnostic tests based on them have recently been extended to general econometric models by Andrews (1988a, b). Here we consider another important use of these statistics. Specifically, we propose some convenient asymptotically standard normal tests for model selection based on chi-square type statistics. Following Vuong (1989), the null hypothesis is that the competing models are equally close to the data-generating process (DGP) vs. the alternative hypotheses that one model is closer to the DGP where closeness of a model is measured according to the discrepancy implicit in the Pearson type statistic used. Our model selection tests have the desirable feature that neither model needs to be correctly specified nor nested in each other. As a prerequisite, we study the corresponding class of minimum chi-square estimators.",
    author = "Quang Vuong and Weiren Wang",
    year = "1993",
    doi = "10.1016/0304-4076(93)90104-D",
    language = "English (US)",
    volume = "56",
    pages = "141--168",
    journal = "Journal of Econometrics",
    issn = "0304-4076",
    publisher = "Elsevier BV",
    number = "1-2",

    }

    TY - JOUR

    T1 - Minimum chi-square estimation and tests for model selection

    AU - Vuong, Quang

    AU - Wang, Weiren

    PY - 1993

    Y1 - 1993

    N2 - This paper studies the problem of model selection based on Pearson chi-square type statistics. Such goodness-of-fit statistics have been considered by Moore (1978) and diagnostic tests based on them have recently been extended to general econometric models by Andrews (1988a, b). Here we consider another important use of these statistics. Specifically, we propose some convenient asymptotically standard normal tests for model selection based on chi-square type statistics. Following Vuong (1989), the null hypothesis is that the competing models are equally close to the data-generating process (DGP) vs. the alternative hypotheses that one model is closer to the DGP where closeness of a model is measured according to the discrepancy implicit in the Pearson type statistic used. Our model selection tests have the desirable feature that neither model needs to be correctly specified nor nested in each other. As a prerequisite, we study the corresponding class of minimum chi-square estimators.

    AB - This paper studies the problem of model selection based on Pearson chi-square type statistics. Such goodness-of-fit statistics have been considered by Moore (1978) and diagnostic tests based on them have recently been extended to general econometric models by Andrews (1988a, b). Here we consider another important use of these statistics. Specifically, we propose some convenient asymptotically standard normal tests for model selection based on chi-square type statistics. Following Vuong (1989), the null hypothesis is that the competing models are equally close to the data-generating process (DGP) vs. the alternative hypotheses that one model is closer to the DGP where closeness of a model is measured according to the discrepancy implicit in the Pearson type statistic used. Our model selection tests have the desirable feature that neither model needs to be correctly specified nor nested in each other. As a prerequisite, we study the corresponding class of minimum chi-square estimators.

    UR - http://www.scopus.com/inward/record.url?scp=38249004085&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=38249004085&partnerID=8YFLogxK

    U2 - 10.1016/0304-4076(93)90104-D

    DO - 10.1016/0304-4076(93)90104-D

    M3 - Article

    VL - 56

    SP - 141

    EP - 168

    JO - Journal of Econometrics

    JF - Journal of Econometrics

    SN - 0304-4076

    IS - 1-2

    ER -