000270439 001__ 270439
000270439 005__ 20180402232842.0
000270439 037__ $$a2068-2018-2021
000270439 041__ $$aeng
000270439 084__ $$aC21
000270439 084__ $$aC26
000270439 245__ $$aDefying the LATE? Identication of local treatment eects when the instrument violates monotonicity.
000270439 260__ $$c2013-08
000270439 269__ $$a2013-08
000270439 300__ $$a36
000270439 336__ $$aWorking or Discussion Paper
000270439 490__ $$aWERP 1020
000270439 520__ $$aThe instrumental variable method relies on a strong no-deers condition, which requires that the instrument aect every subject's treatment decision in the same direction. This paper shows that no-deers can be replaced by a weaker compliersdeers condition, which requires that a subgroup of compliers have the same size and the same distribution of potential outcomes as deers. This condition is necessary and sucient for IV to capture causal eects for the remaining part of compliers. In many applications, compliers-deers is a very weak condition. For instance, in Angrist & Evans (1998), 94% of DGPs compatible with the data satisfy compliers-deers, while 0% satisfy no-deers.
000270439 542__ $$fBy depositing this Content ('Content') in AgEcon Search, I agree that  I am solely responsible for any consequences of uploading this Content to AgEcon Search and making it publicly available, and I represent and warrant that: I am either the sole creator and the owner of the copyrights and all other rights in the Content; or, without obtaining another’s permission, I have the right to deposit the Content in an archive such as AgEcon Search. To the extent that any portions of the Content are not my own creation, they are used with the copyright holder’s express permission or as permitted by law. Additionally, the Content does not infringe the copyrights or other intellectual property rights of another, nor does the Content violate any laws or another’s rights of privacy or publicity. The Content contains no restricted, private, confidential, or otherwise protected data or information that should not be publicly shared. I understand that AgEcon Search will do its best to provide perpetual access to my Content. In order to support these efforts, I grant the Regents of the University of Minnesota ('University'), through AgEcon Search, the following non-exclusive, irrevocable, royalty-free, world-wide rights and licenses: to access, reproduce, distribute and publicly display the Content, in whole or in part, in order to secure, preserve and make it publicly available, and to make derivative works based upon the Content in order to migrate the Content to other media or formats, or to preserve its public access. These terms do not transfer ownership of the copyright(s) in the Content. These terms only grant to the University the limited license outlined above.
000270439 546__ $$aEnglish
000270439 650__ $$aFinancial Economics
000270439 6531_ $$ainstrumental variable
000270439 6531_ $$aheterogeneous effects
000270439 6531_ $$adefiers
000270439 6531_ $$asingle index model
000270439 700__ $$ade Chaisemartin, Clement
000270439 8560_ $$fsheeh247@umn.edu
000270439 8564_ $$s489127$$uhttp://ageconsearch.umn.edu/record/270439/files/twerp_1020_chaisemartin.pdf
000270439 8564_ $$s1752327$$uhttp://ageconsearch.umn.edu/record/270439/files/twerp_1020_chaisemartin.pdf?subformat=pdfa$$xpdfa
000270439 909CO $$ooai:ageconsearch.umn.edu:270439$$pGLOBAL_SET
000270439 980__ $$a2068