Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/20231 
Kompletter Metadatensatz
DublinCore-FeldWertSprache
dc.contributor.authorPaserman, Marco Danieleen
dc.date.accessioned2009-01-28T16:12:35Z-
dc.date.available2009-01-28T16:12:35Z-
dc.date.issued2004-
dc.identifier.urihttp://hdl.handle.net/10419/20231-
dc.description.abstractThis paper describes a semiparametric Bayesian method for analyzing duration data. Theproposed estimator specifies a complete functional form for duration spells, but allowsflexibility by introducing an individual heterogeneity term, which follows a Dirichlet mixturedistribution. I show how to obtain predictive distributions for duration data that correctlyaccount for the uncertainty present in the model. I also directly compare the performance ofthe proposed estimator with Heckman and Singer's (1984) Non Parametric MaximumLikelihood Estimator (NPMLE). The methodology is applied to the analysis of youthunemployment spells. Compared to the NPMLE, the proposed estimator reflects moreaccurately the uncertainty surrounding the heterogeneity distribution.en
dc.language.isoengen
dc.publisher|aInstitute for the Study of Labor (IZA) |cBonnen
dc.relation.ispartofseries|aIZA Discussion Papers |x996en
dc.subject.jelC41en
dc.subject.jelC11en
dc.subject.ddc330en
dc.subject.keywordduration dataen
dc.subject.keywordDirichlet processen
dc.subject.keywordBayesian inferenceen
dc.subject.keywordMarkov chain Monte Carlo simulationen
dc.subject.stwStatistische Bestandsanalyseen
dc.subject.stwNichtparametrisches Verfahrenen
dc.subject.stwBayes-Statistiken
dc.subject.stwMaximum-Likelihood-Methodeen
dc.subject.stwSchätzungen
dc.subject.stwJugendarbeitslosigkeiten
dc.subject.stwTheorieen
dc.subject.stwVereinigte Staatenen
dc.titleBayesian inference for duration data with unobserved and unknown heterogeneity : Monte Carlo evidence and an application-
dc.typeWorking Paperen
dc.identifier.ppn378234463en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen

Datei(en):
Datei
Größe
523.58 kB





Publikationen in EconStor sind urheberrechtlich geschützt.