Defying the LATE? Identication of local treatment eects when the instrument violates monotonicity

Clément de Chaisemartin

No 270439, Economic Research Papers from University of Warwick - Department of Economics

Abstract: The instrumental variable method relies on a strong no-deers condition, which requires that the instrument aect every subject's treatment decision in the same direction. This paper shows that no-deers can be replaced by a weaker compliersdeers condition, which requires that a subgroup of compliers have the same size and the same distribution of potential outcomes as deers. This condition is necessary and sucient for IV to capture causal eects for the remaining part of compliers. In many applications, compliers-deers is a very weak condition. For instance, in Angrist & Evans (1998), 94% of DGPs compatible with the data satisfy compliers-deers, while 0% satisfy no-deers.

Keywords: Financial; Economics (search for similar items in EconPapers)
Pages: 36
Date: 2013-08
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://ageconsearch.umn.edu/record/270439/files/twerp_1020_chaisemartin.pdf (application/pdf)
https://ageconsearch.umn.edu/record/270439/files/t ... n.pdf?subformat=pdfa (application/pdf)

Related works:
Journal Article: Tolerating defiance? Local average treatment effects without monotonicity (2017)
Working Paper: Defying the LATE? Identification of local treatment effects when the instrument violates monotonicity (2013)
Working Paper: Late again, whithout Monotonicity (2012)
Working Paper: Late Again with Defiers (2012)
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:ags:uwarer:270439

DOI: 10.22004/ag.econ.270439

Access Statistics for this paper

More papers in Economic Research Papers from University of Warwick - Department of Economics
Bibliographic data for series maintained by AgEcon Search ().