Partial identification in two-sided matching models

  • Federico Echenique
  • , Sang Mok Lee
  • , Matthew Shum

    Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

    2 Scopus citations

    Abstract

    We propose a methodology for estimating preference parameters in matching models. Our estimator applies to repeated observations of matchings among a fixed group of individuals. Our estimator is based on the stability conditions in matching models; we consider both transferable (TU) and nontransferable utility (NTU) models. In both cases, the stability conditions yield moment inequalities which can be taken to the data. The preference parameters are partially identified. We consider simple illustrative examples, and also an empirical application to aggregate marriage markets.

    Original languageEnglish
    Title of host publicationStructural Econometric Models
    PublisherJAI Press
    Pages117-139
    Number of pages23
    ISBN (Print)9781783500529
    DOIs
    StatePublished - 2013

    Publication series

    NameAdvances in Econometrics
    Volume31
    ISSN (Print)0731-9053

    Keywords

    • Partial identification
    • Stability
    • Two-sided matching

    Fingerprint

    Dive into the research topics of 'Partial identification in two-sided matching models'. Together they form a unique fingerprint.

    Cite this