Abstract
In the absence of any trend component, the observed series y t would be completely characterised by the cycle (since y t = α + ɛ t ) and thus, in general, could be represented by an ARMA model of the form (2.30). The observed series would thus be stationary. We now consider modelling time series that contain stochastic trend components and which are therefore generally referred to as nonstationary processes.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Copyright information
© 2003 Terence C. Mills
About this chapter
Cite this chapter
Mills, T.C. (2003). Stochastic Trends and Cycles. In: Modelling Trends and Cycles in Economic Time Series. Palgrave Texts in Econometrics. Palgrave Macmillan, London. https://doi.org/10.1057/9780230595521_3
Download citation
DOI: https://doi.org/10.1057/9780230595521_3
Publisher Name: Palgrave Macmillan, London
Print ISBN: 978-1-4039-0209-2
Online ISBN: 978-0-230-59552-1
eBook Packages: Palgrave Economics & Finance CollectionEconomics and Finance (R0)