Limited information estimators and exogeneity tests for simultaneous probit models

Douglas Rivers, Quang Vuong

    Research output: Contribution to journalArticle

    Abstract

    A two-step maximum likelihood procedure is proposed for estimating simultaneous probit models and is compared to alternative limited information estimators. Conditions under which each estimator attains the Cramer-Rao lower bound are obtained. Simple tests for exogeneity based on the new two-step estimator are proposed and are shown to be asymptotically equivalent to one another and to have the same local asymptotic power as classical tests based on the limited information maximum likelihood estimator. Finite sample comparisons between the new and alternative estimators are presented based on some Monte Carlo evidence. The performance of the proposed tests for exogeneity is also assessed.

    Original languageEnglish (US)
    Pages (from-to)347-366
    Number of pages20
    JournalJournal of Econometrics
    Volume39
    Issue number3
    DOIs
    StatePublished - 1988

    Fingerprint

    Probit Model
    Maximum likelihood
    Estimator
    Cramer-Rao Lower Bound
    Asymptotic Power
    Asymptotically equivalent
    Alternatives
    Maximum Likelihood Estimator
    Maximum Likelihood
    Probit model
    Exogeneity
    Limited information

    ASJC Scopus subject areas

    • Economics and Econometrics
    • Applied Mathematics
    • History and Philosophy of Science

    Cite this

    Limited information estimators and exogeneity tests for simultaneous probit models. / Rivers, Douglas; Vuong, Quang.

    In: Journal of Econometrics, Vol. 39, No. 3, 1988, p. 347-366.

    Research output: Contribution to journalArticle

    Rivers, Douglas ; Vuong, Quang. / Limited information estimators and exogeneity tests for simultaneous probit models. In: Journal of Econometrics. 1988 ; Vol. 39, No. 3. pp. 347-366.
    @article{06f8b5eaccbb4013922dff5388e6ae79,
    title = "Limited information estimators and exogeneity tests for simultaneous probit models",
    abstract = "A two-step maximum likelihood procedure is proposed for estimating simultaneous probit models and is compared to alternative limited information estimators. Conditions under which each estimator attains the Cramer-Rao lower bound are obtained. Simple tests for exogeneity based on the new two-step estimator are proposed and are shown to be asymptotically equivalent to one another and to have the same local asymptotic power as classical tests based on the limited information maximum likelihood estimator. Finite sample comparisons between the new and alternative estimators are presented based on some Monte Carlo evidence. The performance of the proposed tests for exogeneity is also assessed.",
    author = "Douglas Rivers and Quang Vuong",
    year = "1988",
    doi = "10.1016/0304-4076(88)90063-2",
    language = "English (US)",
    volume = "39",
    pages = "347--366",
    journal = "Journal of Econometrics",
    issn = "0304-4076",
    publisher = "Elsevier BV",
    number = "3",

    }

    TY - JOUR

    T1 - Limited information estimators and exogeneity tests for simultaneous probit models

    AU - Rivers, Douglas

    AU - Vuong, Quang

    PY - 1988

    Y1 - 1988

    N2 - A two-step maximum likelihood procedure is proposed for estimating simultaneous probit models and is compared to alternative limited information estimators. Conditions under which each estimator attains the Cramer-Rao lower bound are obtained. Simple tests for exogeneity based on the new two-step estimator are proposed and are shown to be asymptotically equivalent to one another and to have the same local asymptotic power as classical tests based on the limited information maximum likelihood estimator. Finite sample comparisons between the new and alternative estimators are presented based on some Monte Carlo evidence. The performance of the proposed tests for exogeneity is also assessed.

    AB - A two-step maximum likelihood procedure is proposed for estimating simultaneous probit models and is compared to alternative limited information estimators. Conditions under which each estimator attains the Cramer-Rao lower bound are obtained. Simple tests for exogeneity based on the new two-step estimator are proposed and are shown to be asymptotically equivalent to one another and to have the same local asymptotic power as classical tests based on the limited information maximum likelihood estimator. Finite sample comparisons between the new and alternative estimators are presented based on some Monte Carlo evidence. The performance of the proposed tests for exogeneity is also assessed.

    UR - http://www.scopus.com/inward/record.url?scp=45449123614&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=45449123614&partnerID=8YFLogxK

    U2 - 10.1016/0304-4076(88)90063-2

    DO - 10.1016/0304-4076(88)90063-2

    M3 - Article

    VL - 39

    SP - 347

    EP - 366

    JO - Journal of Econometrics

    JF - Journal of Econometrics

    SN - 0304-4076

    IS - 3

    ER -