Temporal Aggregation in First Order Cointegrated Vector Autoregressive

Lisbeth Funding la Cour, Anders Milhøj

Research output: Working paperResearch

10 Downloads (Pure)

Abstract

We study aggregation - or sample frequencies - of time series, e.g. aggregation from weekly to monthly or quarterly time series. Aggregation usually gives shorter time series but spurious phenomena, in e.g. daily observations, can on the other hand be avoided. An important issue is the effect of aggregation on the adjustment coefficient in cointegrated systems. We study only first order vector autoregressive processes for n dimensional time series Xt, and we illustrate the theory by a two dimensional and a four dimensional model for prices of various grades of gasoline.
Original languageEnglish
Place of PublicationFrederiksberg
PublisherCopenhagen Business School, CBS
Number of pages35
Publication statusPublished - 2006
SeriesWorking Paper / Department of Economics. Copenhagen Business School
Number14-2006

Cite this