Bias reduction by imputation for linear panel data models with nonrandom missing

Goeun Lee, Chirok Han

    Research output: Contribution to journalArticlepeer-review

    Abstract

    When no variables are observed for endogenous non-respondents of panel data, bias correction is available only for a limited class of instrumental variable estimators, which require strong conditions for consistency and often suffer from substantial efficiency loss. In this paper we examine a convenient alternative method of imputing the missing explanatory variables and then using standard bias-correction procedures for sample selection. Various bias-corrected estimators are derived and their performances are compared by Monte Carlo experiments. Results verify efficiency loss by the instrumental variable estimators and suggest that the imputation method is practically useful if it is applied to first-difference regression.

    Original languageEnglish
    Pages (from-to)1-25
    Number of pages25
    JournalJournal of Economic Theory and Econometrics
    Volume29
    Issue number1
    Publication statusPublished - 2018 Mar

    Bibliographical note

    Funding Information:
    ∗This work was supported by the Korean Government (NRF-2014S1A2A2027803) and by Korea University (K1802771). The authors thank Professor Sangsoo Park for valuable comments and suggestions. †First author. Department of Economics, Korea University, 145 Anam-ro Seongbuk-gu, Seoul 02841, Republic of Korea. E-mail: [email protected]. ‡Corresponding author. Department of Economics, Korea University, 145 Anam-ro Seongbuk-gu, Seoul 02841, Republic of Korea. E-mail: [email protected].

    Publisher Copyright:
    © 2018, Korean Econometric Society. All rights reserevd.

    Keywords

    • Attrition
    • Bias-correction
    • Imputation
    • Missing
    • Nonresponse
    • Panel data
    • Selection

    ASJC Scopus subject areas

    • Economics and Econometrics

    Fingerprint

    Dive into the research topics of 'Bias reduction by imputation for linear panel data models with nonrandom missing'. Together they form a unique fingerprint.

    Cite this