Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/28356 
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGolosnoy, Vasylen
dc.contributor.authorHogrefe, Jensen
dc.date.accessioned2009-06-30-
dc.date.accessioned2009-10-18T16:26:59Z-
dc.date.available2009-10-18T16:26:59Z-
dc.date.issued2009-
dc.identifier.urihttp://hdl.handle.net/10419/28356-
dc.description.abstractThe dates of U.S. business cycle are reported by NBER with a considerable delay, so an early notion of turning points is of particular interest. This paper proposes a novel sequential approach designed for timely signaling these turning points. A directional cumulated sum decision rule is adapted for the purpose of on-line monitoring of transitions between subsequent phases of economic activity. The introduced procedure shows a sound detection ability for business cycle peaks and troughs compared to the established dynamic factor Markov switching methodology. It exhibits a range of theoretical optimality properties for early signaling, moreover, it is transparent and easy to implement.en
dc.language.isoengen
dc.publisher|aKiel Institute for the World Economy (IfW) |cKielen
dc.relation.ispartofseries|aKiel Working Paper |x1528en
dc.subject.jelC44en
dc.subject.jelC50en
dc.subject.jelE32en
dc.subject.ddc330en
dc.subject.keywordBusiness cycleen
dc.subject.keywordCUSUM control charten
dc.subject.keywordDynamic Factor Markov switching modelsen
dc.subject.keywordEarly signalingen
dc.subject.keywordNBER datingen
dc.subject.stwKonjunktureller Wendepunkten
dc.subject.stwKonjunkturprognoseen
dc.subject.stwPrognoseverfahrenen
dc.subject.stwSequentialanalyseen
dc.subject.stwStatistische Qualitätskontrolleen
dc.subject.stwUSAen
dc.titleSequential methodology for signaling business cycle turning points-
dc.typeWorking Paperen
dc.identifier.ppn603369723en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen
dc.identifier.repecRePEc:zbw:ifwkwp:1528en

Files in This Item:
File
Size
316.71 kB





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