Vis enkel innførsel

dc.contributor.authorAndersson, Jonas
dc.date.accessioned2007-12-05T11:17:16Z
dc.date.available2007-12-05T11:17:16Z
dc.date.issued2007-06
dc.identifier.issn1500-4066
dc.identifier.urihttp://hdl.handle.net/11250/163913
dc.description.abstractIn this paper, the problem of calculating covariances and correlations between time series which are observed irregularly and at different points in time, is treated. The problem of dependence between the time stamp process and the return process is especially highlighted and the solution to this problem for a special case is given. Furthermore, estimators based on different interpolation methods are investigated. The covariances are in turn used to estimate a simple regression on such data. In particular, the difference of first order integrated processes, I(1) processes, are considered. These methods are relevant for stock returns and consequently of importance in e.g. portfolio optimizationen
dc.language.isoengen
dc.publisherNorwegian School of Economics and Business Administration. Department of Finance and Management Scienceen
dc.relation.ispartofseriesDiscussion paperen
dc.relation.ispartofseries2007:19en
dc.subjectIrregularly spaced time seriesen
dc.subjectcovarianceen
dc.subjectcorrelationen
dc.subjectfinancial returnsen
dc.titleOn the estimation of correlations for irregularly spaced time seriesen
dc.typeWorking paperen
dc.subject.nsiVDP::Samfunnsvitenskap: 200::Økonomi: 210en
dc.subject.nsiVDP::Matematikk og Naturvitenskap: 400::Matematikk: 410::Analyse: 411en


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel