File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A small-sample overlapping variance-ratio test

TitleA small-sample overlapping variance-ratio test
Authors
KeywordsBeta distribution
Monte Carlo experiment
Random-walk hypothesis
Variance-ratio test
Issue Date2004
PublisherBlackwell Publishing Ltd.
Citation
Journal Of Time Series Analysis, 2004, v. 25 n. 1, p. 127-135 How to Cite?
AbstractThe null distribution of the overlapping variance-ratio (OVR) test of the random-walk hypothesis is known to be downward biased and skewed to the right in small samples. As shown by Lo and MacKinlay (1989), the test under-rejects the null on the left tail seriously when the sample size is small. This property adversely affects the applicability of the OVR test to macroeconomic time series, which usually have rather small samples. In this paper, we propose a modified overlapping variance-ratio statistic and derive its exact mean under the normality assumption. We propose to approximate the small-sample distribution of the modified statistic using a beta distribution that matches the (exact) mean and the (asymptotic) variance. A Monte Carlo experiment shows that the beta approximation performs well in small samples.
Persistent Identifierhttp://hdl.handle.net/10722/82745
ISSN
2015 Impact Factor: 1.0
2015 SCImago Journal Rankings: 1.177
References

 

DC FieldValueLanguage
dc.contributor.authorTse, YKen_HK
dc.contributor.authorNg, KWen_HK
dc.contributor.authorZhang, Xen_HK
dc.date.accessioned2010-09-06T08:32:55Z-
dc.date.available2010-09-06T08:32:55Z-
dc.date.issued2004en_HK
dc.identifier.citationJournal Of Time Series Analysis, 2004, v. 25 n. 1, p. 127-135en_HK
dc.identifier.issn0143-9782en_HK
dc.identifier.urihttp://hdl.handle.net/10722/82745-
dc.description.abstractThe null distribution of the overlapping variance-ratio (OVR) test of the random-walk hypothesis is known to be downward biased and skewed to the right in small samples. As shown by Lo and MacKinlay (1989), the test under-rejects the null on the left tail seriously when the sample size is small. This property adversely affects the applicability of the OVR test to macroeconomic time series, which usually have rather small samples. In this paper, we propose a modified overlapping variance-ratio statistic and derive its exact mean under the normality assumption. We propose to approximate the small-sample distribution of the modified statistic using a beta distribution that matches the (exact) mean and the (asymptotic) variance. A Monte Carlo experiment shows that the beta approximation performs well in small samples.en_HK
dc.languageengen_HK
dc.publisherBlackwell Publishing Ltd.en_HK
dc.relation.ispartofJournal of Time Series Analysisen_HK
dc.rightsJournal of Time Series Analysis. Copyright © Blackwell Publishing Ltd.en_HK
dc.subjectBeta distributionen_HK
dc.subjectMonte Carlo experimenten_HK
dc.subjectRandom-walk hypothesisen_HK
dc.subjectVariance-ratio testen_HK
dc.titleA small-sample overlapping variance-ratio testen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0143-9782&volume=25&issue=1&spage=127&epage=135&date=2004&atitle=A+small-sample+overlapping+variance-ratio+testen_HK
dc.identifier.emailNg, KW: kaing@hkucc.hku.hken_HK
dc.identifier.authorityNg, KW=rp00765en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1046/j.0143-9782.2003.01804.x-
dc.identifier.scopuseid_2-s2.0-1242292224en_HK
dc.identifier.hkuros85434en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-1242292224&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume25en_HK
dc.identifier.issue1en_HK
dc.identifier.spage127en_HK
dc.identifier.epage135en_HK
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridTse, YK=7005116877en_HK
dc.identifier.scopusauthoridNg, KW=7403178774en_HK
dc.identifier.scopusauthoridZhang, X=7410277543en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats