Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/20277
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLechner, Michaelen_US
dc.date.accessioned2009-01-28T16:12:56Z-
dc.date.available2009-01-28T16:12:56Z-
dc.date.issued2004en_US
dc.identifier.urihttp://hdl.handle.net/10419/20277-
dc.description.abstractThis paper proposes sequential matching and inverse selection probability weighting toestimate dynamic causal effects. The sequential matching estimators extend simple,matching estimators based on propensity scores for static causal analysis that have beenfrequently applied in the evaluation literature. A Monte Carlo study shows that the suggestedestimators perform well in small and medium size samples. Based on the application of thesequential matching estimators to an empirical problem - an evaluation study of the Swissactive labour market policies - some implementational issues are discussed and results areprovided.en_US
dc.language.isoengen_US
dc.publisher|aInstitute for the Study of Labor (IZA) |cBonnen_US
dc.relation.ispartofseries|aIZA Discussion paper series |x1042en_US
dc.subject.jelC40en_US
dc.subject.ddc330en_US
dc.subject.keyworddynamic treatment effectsen_US
dc.subject.keywordnonparametric identificationen_US
dc.subject.keywordcausal effectsen_US
dc.subject.keywordsequential randomisationen_US
dc.subject.keywordprogramme evaluationen_US
dc.subject.keywordpanel dataen_US
dc.subject.stwKausalanalyseen_US
dc.subject.stwSchätztheorieen_US
dc.subject.stwMatchingen_US
dc.subject.stwNichtparametrisches Verfahrenen_US
dc.subject.stwArbeitsmarktpolitiken_US
dc.subject.stwWirtschaftspolitische Wirkungsanalyseen_US
dc.subject.stwTheorieen_US
dc.subject.stwSchweizen_US
dc.titleSequential Matching Estimation of Dynamic Causal Modelsen_US
dc.typeWorking Paperen_US
dc.identifier.ppn380765799en_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-

Files in This Item:
File
Size
527.77 kB





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