Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/23173 
Kompletter Metadatensatz
DublinCore-FeldWertSprache
dc.contributor.authorCorradi, Valentinaen
dc.contributor.authorSwanson, Norman R.en
dc.date.accessioned2009-01-29T15:49:11Z-
dc.date.available2009-01-29T15:49:11Z-
dc.date.issued2003-
dc.identifier.urihttp://hdl.handle.net/10419/23173-
dc.description.abstractForecasters and applied econometricians are often interested in comparing the predictive accuracy ofnested competing models. A leading example of nestedness is when predictive ability is equated with?out-of-sample Granger causality?. In particular, it is often of interest to assess whether historicaldata from one variable are useful when constructing a forecasting model for another variable, andhence our use of terminology such as ?out-of-sample Granger causality? (see e.g. Ashley, Grangerand Schmalensee (1980)). In this paper we examine and discuss three key issues one is faced withwhen constructing predictive accuracy tests, namely: the contribution of parameter estimationerror, the choice of linear versus nonlinear models, and the issue of (dynamic) misspecification,with primary focus on the latter of these issues. One of our main conclusions is that there are anumber of easy to apply statistics constructed using out of sample conditional moment conditionswhich are robust to the presence of dynamic misspecification under both hypothesis. We providesome new Monte Carlo findings and empirical evidence based on the use of such tests. In particular,we analyze the finite sample properties of the consistent out of sample test of Corradi and Swanson(2002) using data generating processes calibrated with U.S. money and output, and empiricallyinvestigate the (non)linear marginal predictive content of money for output. Our Monte Carloevidence suggests that the tests perform adequately in finite samples, and our empirical evidencesuggests that there is non useful (non)linear information in money growth that is not alreadycontained in lags of output growth, when the objective is output growth prediction.en
dc.language.isoengen
dc.publisher|aRutgers University, Department of Economics |cNew Brunswick, NJen
dc.relation.ispartofseries|aWorking Paper |x2003-16en
dc.subject.jelC51en
dc.subject.jelC22en
dc.subject.ddc330en
dc.subject.keywordConditional p-valueen
dc.subject.keywordbootstrapen
dc.subject.keywordforecastingen
dc.subject.keywordout-of-sample predictive accuracyen
dc.subject.keywordparameter estimation erroren
dc.subject.stwStatistischer Testen
dc.subject.stwPrognoseverfahrenen
dc.subject.stwBootstrap-Verfahrenen
dc.subject.stwTheorieen
dc.titleSome Recent Developments in Predictive Accuracy Testing With Nested Models and (Generic) Nonlinear Alternatives-
dc.typeWorking Paperen
dc.identifier.ppn375470077en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen
dc.identifier.repecRePEc:rut:rutres:200316en

Datei(en):
Datei
Größe
236.23 kB





Publikationen in EconStor sind urheberrechtlich geschützt.