Please use this identifier to cite or link to this item:
https://hdl.handle.net/10419/64705
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nevo, Aviv | en |
dc.contributor.author | Rosen, Adam | en |
dc.date.accessioned | 2012-10-16T13:17:53Z | - |
dc.date.available | 2012-10-16T13:17:53Z | - |
dc.date.issued | 2008 | - |
dc.identifier.pi | doi:10.1920/wp.cem.2008.1608 | en |
dc.identifier.uri | http://hdl.handle.net/10419/64705 | - |
dc.description.abstract | Dealing with endogenous regressors is a central challenge of applied research. The standard solution is to use instrumental variables that are assumed to be uncorrelated with unobservables. We instead assume (i) the correlation between the instrument and the error term has the same sign as the correlation between the endogenous regressor and the error term, and (ii) that the instrument is less correlated with the error term than is the endogenous regressor. Using these assumptions, we derive analytic bounds for the parameters. We demonstrate the method in two applications. | en |
dc.language.iso | eng | en |
dc.publisher | |aCentre for Microdata Methods and Practice (cemmap) |cLondon | en |
dc.relation.ispartofseries | |acemmap working paper |xCWP16/08 | en |
dc.subject.ddc | 330 | en |
dc.subject.stw | Ökonometrie | en |
dc.subject.stw | Korrelation | en |
dc.subject.stw | Fehlerkorrekturmodell | en |
dc.title | Identification with imperfect instruments | - |
dc.type | Working Paper | en |
dc.identifier.ppn | 574283404 | en |
dc.rights | http://www.econstor.eu/dspace/Nutzungsbedingungen | en |
dc.identifier.repec | RePEc:ifs:cemmap:16/08 | en |
Files in This Item:
Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.