Properties of the CUE estimator and a modification with moments

Jerry Hausman, Randall Lewis, Konrad Menzel, Whitney Newey

    Research output: Contribution to journalArticle

    Abstract

    In this paper, we analyze properties of the Continuous Updating Estimator (CUE) proposed by Hansen et al. (1996), which has been suggested as a solution to the finite sample bias problems of the two-step GMM estimator. We show that the estimator should be expected to perform poorly in finite samples under weak identification, in particular, the estimator is not guaranteed to have finite moments of any order. We propose the Regularized CUE (RCUE) as a solution to this problem. The RCUE solves a modification of the first-order conditions for the CUE estimator and is shown to be asymptotically equivalent to CUE under many weak moment asymptotics. Our theoretical findings are confirmed by extensive Monte Carlo studies.

    Original languageEnglish (US)
    Pages (from-to)45-57
    Number of pages13
    JournalJournal of Econometrics
    Volume165
    Issue number1
    DOIs
    StatePublished - Nov 3 2011

    Fingerprint

    Updating
    Moment
    Estimator
    Order Conditions
    Asymptotically equivalent
    Monte Carlo Study
    First-order

    ASJC Scopus subject areas

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

    Cite this

    Properties of the CUE estimator and a modification with moments. / Hausman, Jerry; Lewis, Randall; Menzel, Konrad; Newey, Whitney.

    In: Journal of Econometrics, Vol. 165, No. 1, 03.11.2011, p. 45-57.

    Research output: Contribution to journalArticle

    Hausman, Jerry ; Lewis, Randall ; Menzel, Konrad ; Newey, Whitney. / Properties of the CUE estimator and a modification with moments. In: Journal of Econometrics. 2011 ; Vol. 165, No. 1. pp. 45-57.
    @article{d623ffd1536a4096af060d63d4f9bf13,
    title = "Properties of the CUE estimator and a modification with moments",
    abstract = "In this paper, we analyze properties of the Continuous Updating Estimator (CUE) proposed by Hansen et al. (1996), which has been suggested as a solution to the finite sample bias problems of the two-step GMM estimator. We show that the estimator should be expected to perform poorly in finite samples under weak identification, in particular, the estimator is not guaranteed to have finite moments of any order. We propose the Regularized CUE (RCUE) as a solution to this problem. The RCUE solves a modification of the first-order conditions for the CUE estimator and is shown to be asymptotically equivalent to CUE under many weak moment asymptotics. Our theoretical findings are confirmed by extensive Monte Carlo studies.",
    author = "Jerry Hausman and Randall Lewis and Konrad Menzel and Whitney Newey",
    year = "2011",
    month = "11",
    day = "3",
    doi = "10.1016/j.jeconom.2011.05.005",
    language = "English (US)",
    volume = "165",
    pages = "45--57",
    journal = "Journal of Econometrics",
    issn = "0304-4076",
    publisher = "Elsevier BV",
    number = "1",

    }

    TY - JOUR

    T1 - Properties of the CUE estimator and a modification with moments

    AU - Hausman, Jerry

    AU - Lewis, Randall

    AU - Menzel, Konrad

    AU - Newey, Whitney

    PY - 2011/11/3

    Y1 - 2011/11/3

    N2 - In this paper, we analyze properties of the Continuous Updating Estimator (CUE) proposed by Hansen et al. (1996), which has been suggested as a solution to the finite sample bias problems of the two-step GMM estimator. We show that the estimator should be expected to perform poorly in finite samples under weak identification, in particular, the estimator is not guaranteed to have finite moments of any order. We propose the Regularized CUE (RCUE) as a solution to this problem. The RCUE solves a modification of the first-order conditions for the CUE estimator and is shown to be asymptotically equivalent to CUE under many weak moment asymptotics. Our theoretical findings are confirmed by extensive Monte Carlo studies.

    AB - In this paper, we analyze properties of the Continuous Updating Estimator (CUE) proposed by Hansen et al. (1996), which has been suggested as a solution to the finite sample bias problems of the two-step GMM estimator. We show that the estimator should be expected to perform poorly in finite samples under weak identification, in particular, the estimator is not guaranteed to have finite moments of any order. We propose the Regularized CUE (RCUE) as a solution to this problem. The RCUE solves a modification of the first-order conditions for the CUE estimator and is shown to be asymptotically equivalent to CUE under many weak moment asymptotics. Our theoretical findings are confirmed by extensive Monte Carlo studies.

    UR - http://www.scopus.com/inward/record.url?scp=80053314529&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=80053314529&partnerID=8YFLogxK

    U2 - 10.1016/j.jeconom.2011.05.005

    DO - 10.1016/j.jeconom.2011.05.005

    M3 - Article

    AN - SCOPUS:80053314529

    VL - 165

    SP - 45

    EP - 57

    JO - Journal of Econometrics

    JF - Journal of Econometrics

    SN - 0304-4076

    IS - 1

    ER -