Identification of a class of index models: A topological approach. Issue 1 (17th June 2020)

• Record Type: Journal Article
• Authors: Fosgerau, Mogens; Kristensen, Dennis
• Is Part Of: Econometrics journal. Volume 24:Issue 1(2021)
• Page Start: 121
• Page End: 133
• Publication Date: 2020-06-17
• Subjects: Competing risks -- discrete choice -- index model -- nonparametric identification; Econometrics -- Periodicals; 330.015195
• DOI: 10.1093/ectj/utaa016
• Languages: English
• ISSNs: 1368-4221

Abstract

Summary: We establish nonparametric identification in a class of so-called index models by using a novel approach that relies on general topological results. Our proof strategy requires substantially weaker conditions on the functions and distributions characterising the model than those required by existing strategies; in particular, it does not require any large-support conditions on the regressors of our model. We apply the general identification result to additive random utility and competing risk models.