Injectivity of a class of integral operators with compactly supported kernels

Yingyao Hu, Susanne Schennach and Ji-Liang Shiu

Journal of Econometrics, 2017, vol. 200, issue 1, 48-58

Abstract: Injectivity of integral operators is related to completeness conditions of their corresponding kernel functions. Completeness provides a useful way of obtaining nonparametric identification in various models including nonparametric regression models with instrumental variables, nonclassical measurement error models, and auction models, etc. However, the condition is quite abstract for empirical work and lacks a proper economic interpretation. We rely on known results regarding the Volterra equation to provide sufficient conditions for completeness conditions for densities with compact support. Our conditions include various smoothness assumptions and monotonously moving support assumptions on the kernel function of the operator. We apply our results to establish nonparametric identification in nonparametric IV regression models, nonclassical measurement error models, and auction models with an accessible interpretation and without specific functional form restrictions.

Keywords: Nonparametric identification; Instrumental variable; Completeness; Endogeneity (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (11)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0304407617300751
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:econom:v:200:y:2017:i:1:p:48-58

DOI: 10.1016/j.jeconom.2017.05.013

Access Statistics for this article

Journal of Econometrics is currently edited by T. Amemiya, A. R. Gallant, J. F. Geweke, C. Hsiao and P. M. Robinson

More articles in Journal of Econometrics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().