File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Multivariate modelling of the autoregressive random variance process

TitleMultivariate modelling of the autoregressive random variance process
Authors
KeywordsAutoregressive random variance process
EM algorithm
Observed information matrix
Stochastic volatility
Issue Date1997
PublisherBlackwell Publishing Ltd.
Citation
Journal Of Time Series Analysis, 1997, v. 18 n. 4, p. 429-446 How to Cite?
AbstractThe autoregressive random variance (ARV) model proposed by Taylor (Financial returns modelled by the product of two stochastic processes, a study of daily sugar prices 1961-79. In Time Series Analysis: Theory and Practice 1 (ed. O. D. Anderson). Amsterdam: North-Holland, 1982, pp. 203-26) is useful in modelling stochastic changes in the variance structure of a time series. In this paper we focus on a general multivariate ARV model. A traditional EM algorithm is derived as the estimation method. The proposed EM approach is simple to program, computationally efficient and numerically well behaved. The asymptotic variance-covariance matrix can be easily computed as a by-product using a well-known asymptotic result for extremum estimators. A result that is of interest in itself is that the dimension of the augmented state space form used in computing the variance-covariance matrix can be shown to be greatly reduced, resulting in greater computational efficiency. The multivariate ARV model considered here is useful in studying the lead-lag (causality) relationship of the variance structure across different time series. As an example, the leading effect of Thailand on Malaysia in terms of variance changes in the stock indices is demonstrated.
Persistent Identifierhttp://hdl.handle.net/10722/82822
ISSN
2023 Impact Factor: 1.2
2023 SCImago Journal Rankings: 0.875
References

 

DC FieldValueLanguage
dc.contributor.authorSo, MKPen_HK
dc.contributor.authorLi, WKen_HK
dc.contributor.authorLam, Ken_HK
dc.date.accessioned2010-09-06T08:33:48Z-
dc.date.available2010-09-06T08:33:48Z-
dc.date.issued1997en_HK
dc.identifier.citationJournal Of Time Series Analysis, 1997, v. 18 n. 4, p. 429-446en_HK
dc.identifier.issn0143-9782en_HK
dc.identifier.urihttp://hdl.handle.net/10722/82822-
dc.description.abstractThe autoregressive random variance (ARV) model proposed by Taylor (Financial returns modelled by the product of two stochastic processes, a study of daily sugar prices 1961-79. In Time Series Analysis: Theory and Practice 1 (ed. O. D. Anderson). Amsterdam: North-Holland, 1982, pp. 203-26) is useful in modelling stochastic changes in the variance structure of a time series. In this paper we focus on a general multivariate ARV model. A traditional EM algorithm is derived as the estimation method. The proposed EM approach is simple to program, computationally efficient and numerically well behaved. The asymptotic variance-covariance matrix can be easily computed as a by-product using a well-known asymptotic result for extremum estimators. A result that is of interest in itself is that the dimension of the augmented state space form used in computing the variance-covariance matrix can be shown to be greatly reduced, resulting in greater computational efficiency. The multivariate ARV model considered here is useful in studying the lead-lag (causality) relationship of the variance structure across different time series. As an example, the leading effect of Thailand on Malaysia in terms of variance changes in the stock indices is demonstrated.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.subjectAutoregressive random variance processen_HK
dc.subjectEM algorithmen_HK
dc.subjectObserved information matrixen_HK
dc.subjectStochastic volatilityen_HK
dc.titleMultivariate modelling of the autoregressive random variance processen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0143-9782&volume=18&issue=4&spage=429&epage=446&date=1997&atitle=Multivariate+Modelling+of+the+Autoregressive+Random+Variance+Processen_HK
dc.identifier.emailLi, WK: hrntlwk@hku.hken_HK
dc.identifier.authorityLi, WK=rp00741en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.scopuseid_2-s2.0-0011714398en_HK
dc.identifier.hkuros23978en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0011714398&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume18en_HK
dc.identifier.issue4en_HK
dc.identifier.spage429en_HK
dc.identifier.epage446en_HK
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridSo, MKP=7004473851en_HK
dc.identifier.scopusauthoridLi, WK=14015971200en_HK
dc.identifier.scopusauthoridLam, K=36492945700en_HK
dc.identifier.issnl0143-9782-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats