Nonlinear Financial Econometrics: Markov Switching Models, Persistence and Nonlinear Cointegration by Greg N. Gregoriou & Razvan Pascalau

Nonlinear Financial Econometrics: Markov Switching Models, Persistence and Nonlinear Cointegration by Greg N. Gregoriou & Razvan Pascalau

Author:Greg N. Gregoriou & Razvan Pascalau
Language: eng
Format: epub
Publisher: Palgrave Macmillan
Published: 2011-06-14T16:00:00+00:00


where the union is taken over all persistence decay patterns. A transformation g belongs in space Eb.t. (0) if and only if predictor E[g(Xt+h)|Zt] to infinity.

In Section 3, we noted that a regular, stationary process is such that Eb.t.(0)is equal to the set of all scalar functions. In general, this space is strictly smaller, and the behavior of some transformations of a process can resemble the behavior of a stationary process, while the behavior of other transformations may look nonstationary. This leads to the following definition of nonlinear integration.

Definition 7.2. If g belongs in Eb.t.(0), the transformed process is nonlinearly integrated of order 0 (NLI(0)). If g does not belong in Eb.t.(0), the transformed process is NLI (nonlinearly integrated).

The above definition of nonlinear integration is used in the sequel to define nonlinear cointegration.



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.