Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/34846
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMillimet, Daniel L.en_US
dc.contributor.authorTchernis, Rustyen_US
dc.date.accessioned2008-09-22en_US
dc.date.accessioned2010-07-07T11:30:02Z-
dc.date.available2010-07-07T11:30:02Z-
dc.date.issued2008en_US
dc.identifier.piurn:nbn:de:101:1-20080820174en_US
dc.identifier.urihttp://hdl.handle.net/10419/34846-
dc.description.abstractWe characterize the bias of propensity score based estimators of common average treatment effect parameters in the case of selection on unobservables. We then propose a new minimum biased estimator of the average treatment effect. We assess the finite sample performance of our estimator using simulated data, as well as a timely application examining the causal effect of the School Breakfast Program on childhood obesity. We find our new estimator to be quite advantageous in many situations, even when selection is only on observables.en_US
dc.language.isoengen_US
dc.publisher|aInstitute for the Study of Labor (IZA) |cBonnen_US
dc.relation.ispartofseries|aIZA Discussion Papers |x3632en_US
dc.subject.jelC21en_US
dc.subject.ddc330en_US
dc.subject.keywordTreatment effectsen_US
dc.subject.keywordpropensity scoreen_US
dc.subject.keywordbiasen_US
dc.subject.keywordunconfoundednessen_US
dc.subject.keywordselection on unobservablesen_US
dc.subject.stwSchätztheorieen_US
dc.subject.stwBiasen_US
dc.subject.stwStichprobenverfahrenen_US
dc.subject.stwStatistischer Testen_US
dc.subject.stwSchätzungen_US
dc.subject.stwSchüleren_US
dc.subject.stwGemeinschaftsgastronomieen_US
dc.subject.stwGesundheitsrisikoen_US
dc.subject.stwUSAen_US
dc.titleMinimizing bias in selection on observables estimators when unconfoundness failsen_US
dc.type|aWorking Paperen_US
dc.identifier.ppn576953385en_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-

Files in This Item:
File
Size
576.17 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.