On equivalencies between design-based and regression-based variance estimators for randomized experiments

Cyrus Samii, Peter M. Aronow

    Research output: Contribution to journalArticle

    Abstract

    This paper demonstrates that the randomization-based "Neyman" and constant-effects estimators for the variance of estimated average treatment effects are equivalent to a variant of the White "heteroskedasticity-robust" estimator and the homoskedastic ordinary least squares (OLS) estimator, respectively.

    Original languageEnglish (US)
    Pages (from-to)365-370
    Number of pages6
    JournalStatistics and Probability Letters
    Volume82
    Issue number2
    DOIs
    StatePublished - Feb 2012

    Fingerprint

    Average Treatment Effect
    Randomized Experiments
    Ordinary Least Squares Estimator
    Heteroskedasticity
    Robust Estimators
    Variance Estimator
    Randomisation
    Regression
    Estimator
    Demonstrate
    Design
    Randomization
    Ordinary least squares
    Randomized experiments
    Average treatment effect
    Robust estimators
    Least squares estimator

    Keywords

    • Potential outcomes
    • Randomized experiments
    • Robust variance estimators

    ASJC Scopus subject areas

    • Statistics, Probability and Uncertainty
    • Statistics and Probability

    Cite this

    On equivalencies between design-based and regression-based variance estimators for randomized experiments. / Samii, Cyrus; Aronow, Peter M.

    In: Statistics and Probability Letters, Vol. 82, No. 2, 02.2012, p. 365-370.

    Research output: Contribution to journalArticle

    @article{fd07dacf333b4e03afcb486d532d8a9f,
    title = "On equivalencies between design-based and regression-based variance estimators for randomized experiments",
    abstract = "This paper demonstrates that the randomization-based {"}Neyman{"} and constant-effects estimators for the variance of estimated average treatment effects are equivalent to a variant of the White {"}heteroskedasticity-robust{"} estimator and the homoskedastic ordinary least squares (OLS) estimator, respectively.",
    keywords = "Potential outcomes, Randomized experiments, Robust variance estimators",
    author = "Cyrus Samii and Aronow, {Peter M.}",
    year = "2012",
    month = "2",
    doi = "10.1016/j.spl.2011.10.024",
    language = "English (US)",
    volume = "82",
    pages = "365--370",
    journal = "Statistics and Probability Letters",
    issn = "0167-7152",
    publisher = "Elsevier",
    number = "2",

    }

    TY - JOUR

    T1 - On equivalencies between design-based and regression-based variance estimators for randomized experiments

    AU - Samii, Cyrus

    AU - Aronow, Peter M.

    PY - 2012/2

    Y1 - 2012/2

    N2 - This paper demonstrates that the randomization-based "Neyman" and constant-effects estimators for the variance of estimated average treatment effects are equivalent to a variant of the White "heteroskedasticity-robust" estimator and the homoskedastic ordinary least squares (OLS) estimator, respectively.

    AB - This paper demonstrates that the randomization-based "Neyman" and constant-effects estimators for the variance of estimated average treatment effects are equivalent to a variant of the White "heteroskedasticity-robust" estimator and the homoskedastic ordinary least squares (OLS) estimator, respectively.

    KW - Potential outcomes

    KW - Randomized experiments

    KW - Robust variance estimators

    UR - http://www.scopus.com/inward/record.url?scp=82055163154&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=82055163154&partnerID=8YFLogxK

    U2 - 10.1016/j.spl.2011.10.024

    DO - 10.1016/j.spl.2011.10.024

    M3 - Article

    VL - 82

    SP - 365

    EP - 370

    JO - Statistics and Probability Letters

    JF - Statistics and Probability Letters

    SN - 0167-7152

    IS - 2

    ER -