Memory properties and fractional integration in transportation time-series

Karlaftis, MG; Vlahogianni, EI

dc.contributor.author	Karlaftis, MG	en
dc.contributor.author	Vlahogianni, EI	en
dc.date.accessioned	2014-03-01T01:31:04Z
dc.date.available	2014-03-01T01:31:04Z
dc.date.issued	2009	en
dc.identifier.issn	0968-090X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/19736
dc.subject	ARIMA	en
dc.subject	Fractional integration	en
dc.subject	GARCH	en
dc.subject	Time-series	en
dc.subject	Transportation	en
dc.subject.classification	Transportation Science & Technology	en
dc.subject.other	ARIMA	en
dc.subject.other	ARIMA models	en
dc.subject.other	Artificial correlation	en
dc.subject.other	Auto-regressive integrated moving average	en
dc.subject.other	Classical model	en
dc.subject.other	Differentiation parameters	en
dc.subject.other	Fractional integration	en
dc.subject.other	GARCH	en
dc.subject.other	Generalized autoregressive conditional heteroskedasticity	en
dc.subject.other	Long-memory property	en
dc.subject.other	Memory models	en
dc.subject.other	Moving averages	en
dc.subject.other	Theoretical foundations	en
dc.subject.other	Time series models	en
dc.subject.other	Traffic Engineering	en
dc.subject.other	Transportation analysis	en
dc.subject.other	Transportation time	en
dc.subject.other	Highway engineering	en
dc.subject.other	Model structures	en
dc.subject.other	integrated approach	en
dc.subject.other	model	en
dc.subject.other	parameterization	en
dc.subject.other	theoretical study	en
dc.subject.other	time series analysis	en
dc.subject.other	transportation system	en
dc.title	Memory properties and fractional integration in transportation time-series	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.trc.2009.03.001	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.trc.2009.03.001	en
heal.language	English	en
heal.publicationDate	2009	en
heal.abstract	In transportation analyses, autoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models have been widely used mainly because of their well established theoretical foundation and ease of application. However, they lack the ability to capture long memory properties and do not jointly treat the mean and variance (variability) of a time-series. We employ fractionally integrated dual memory models and compare results to classical time-series models in a traffic engineering context. Results indicate that dual memory models offer better representation of the original time-series than classical models; further, forcing the differentiation parameter of ARIMA model to equal I leads to over-inflated moving average terms and, consequently, to questionable models with artificial correlation structures. (C) 2009 Elsevier Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	Transportation Research Part C: Emerging Technologies	en
dc.identifier.doi	10.1016/j.trc.2009.03.001	en
dc.identifier.isi	ISI:000267360500008	en
dc.identifier.volume	17	en
dc.identifier.issue	4	en
dc.identifier.spage	444	en
dc.identifier.epage	453	en