Local Identification in Instrumental Variable Multivariate Quantile Regression Models

Haruki Kono

Papers from arXiv.org

Abstract: In the instrumental variable quantile regression (IVQR) model of Chernozhukov and Hansen (2005), a one-dimensional unobserved rank variable monotonically determines a single potential outcome. Even when multiple outcomes are simultaneously of interest, it is common to apply the IVQR model to each of them separately. This practice implicitly assumes that the rank variable of each regression model affects only the corresponding outcome and does not affect the other outcomes. In reality, however, it is often the case that all rank variables together determine the outcomes, which leads to a systematic correlation between the outcomes. To deal with this, we propose a nonlinear IV model that allows for multivariate unobserved heterogeneity, each of which is considered as a rank variable for an observed outcome. We show that the structural function of our model is locally identified under the assumption that the IV and the treatment variable are sufficiently positively correlated.

Date: 2024-01, Revised 2024-06
New Economics Papers: this item is included in nep-ecm
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2401.11422 Latest version (application/pdf)

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:arx:papers:2401.11422

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().