Grouped Patterns of Heterogeneity in Panel Data

Stéphane Bonhomme, Elena Manresa

    Research output: Contribution to journalArticle

    Abstract

    This paper introduces time-varying grouped patterns of heterogeneity in linear panel data models. A distinctive feature of our approach is that group membership is left unrestricted. We estimate the parameters of the model using a "grouped fixed-effects" estimator that minimizes a least squares criterion with respect to all possible groupings of the cross-sectional units. Recent advances in the clustering literature allow for fast and efficient computation. We provide conditions under which our estimator is consistent as both dimensions of the panel tend to infinity, and we develop inference methods. Finally, we allow for grouped patterns of unobserved heterogeneity in the study of the link between income and democracy across countries.

    Original languageEnglish (US)
    Pages (from-to)1147-1184
    Number of pages38
    JournalEconometrica
    Volume83
    Issue number3
    DOIs
    StatePublished - May 1 2015

    Fingerprint

    Panel data
    Estimator
    Clustering
    Unobserved heterogeneity
    Least squares
    Fixed effects
    Group membership
    Democracy
    Grouping
    Inference
    Time-varying
    Income

    Keywords

    • Clustering
    • Democracy
    • Discrete heterogeneity
    • Fixed-effects
    • Panel data

    ASJC Scopus subject areas

    • Economics and Econometrics

    Cite this

    Grouped Patterns of Heterogeneity in Panel Data. / Bonhomme, Stéphane; Manresa, Elena.

    In: Econometrica, Vol. 83, No. 3, 01.05.2015, p. 1147-1184.

    Research output: Contribution to journalArticle

    Bonhomme, S & Manresa, E 2015, 'Grouped Patterns of Heterogeneity in Panel Data', Econometrica, vol. 83, no. 3, pp. 1147-1184. https://doi.org/10.3982/ECTA11319
    Bonhomme, Stéphane ; Manresa, Elena. / Grouped Patterns of Heterogeneity in Panel Data. In: Econometrica. 2015 ; Vol. 83, No. 3. pp. 1147-1184.
    @article{9914330a0b064cb6905234da3a65e7bd,
    title = "Grouped Patterns of Heterogeneity in Panel Data",
    abstract = "This paper introduces time-varying grouped patterns of heterogeneity in linear panel data models. A distinctive feature of our approach is that group membership is left unrestricted. We estimate the parameters of the model using a {"}grouped fixed-effects{"} estimator that minimizes a least squares criterion with respect to all possible groupings of the cross-sectional units. Recent advances in the clustering literature allow for fast and efficient computation. We provide conditions under which our estimator is consistent as both dimensions of the panel tend to infinity, and we develop inference methods. Finally, we allow for grouped patterns of unobserved heterogeneity in the study of the link between income and democracy across countries.",
    keywords = "Clustering, Democracy, Discrete heterogeneity, Fixed-effects, Panel data",
    author = "St{\'e}phane Bonhomme and Elena Manresa",
    year = "2015",
    month = "5",
    day = "1",
    doi = "10.3982/ECTA11319",
    language = "English (US)",
    volume = "83",
    pages = "1147--1184",
    journal = "Econometrica",
    issn = "0012-9682",
    publisher = "Wiley-Blackwell",
    number = "3",

    }

    TY - JOUR

    T1 - Grouped Patterns of Heterogeneity in Panel Data

    AU - Bonhomme, Stéphane

    AU - Manresa, Elena

    PY - 2015/5/1

    Y1 - 2015/5/1

    N2 - This paper introduces time-varying grouped patterns of heterogeneity in linear panel data models. A distinctive feature of our approach is that group membership is left unrestricted. We estimate the parameters of the model using a "grouped fixed-effects" estimator that minimizes a least squares criterion with respect to all possible groupings of the cross-sectional units. Recent advances in the clustering literature allow for fast and efficient computation. We provide conditions under which our estimator is consistent as both dimensions of the panel tend to infinity, and we develop inference methods. Finally, we allow for grouped patterns of unobserved heterogeneity in the study of the link between income and democracy across countries.

    AB - This paper introduces time-varying grouped patterns of heterogeneity in linear panel data models. A distinctive feature of our approach is that group membership is left unrestricted. We estimate the parameters of the model using a "grouped fixed-effects" estimator that minimizes a least squares criterion with respect to all possible groupings of the cross-sectional units. Recent advances in the clustering literature allow for fast and efficient computation. We provide conditions under which our estimator is consistent as both dimensions of the panel tend to infinity, and we develop inference methods. Finally, we allow for grouped patterns of unobserved heterogeneity in the study of the link between income and democracy across countries.

    KW - Clustering

    KW - Democracy

    KW - Discrete heterogeneity

    KW - Fixed-effects

    KW - Panel data

    UR - http://www.scopus.com/inward/record.url?scp=84930701347&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84930701347&partnerID=8YFLogxK

    U2 - 10.3982/ECTA11319

    DO - 10.3982/ECTA11319

    M3 - Article

    VL - 83

    SP - 1147

    EP - 1184

    JO - Econometrica

    JF - Econometrica

    SN - 0012-9682

    IS - 3

    ER -