Tests for Serial Independence and Linearity Based on Correlation Integrals
Abstract We propose information theoretic tests for serial independence and linearity in time series against nonlinear dependence on lagged variables, based on the conditional mutual information. The conditional mutual information, which is a general measure for dependence, is estimated using the co...
Gespeichert in:
| Veröffentlicht in: | Studies in Nonlinear Dynamics & Econometrics 2002-07, Vol.6 (2), p.2 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Zusammenfassung: | Abstract
We propose information theoretic tests for serial independence and
linearity in time series against nonlinear dependence on lagged variables,
based on the conditional mutual information.
The conditional mutual information, which is a general measure for dependence,
is estimated using the correlation integral from chaos theory.
The significance of the test statistics is determined by means of
bootstrap methods. The size and power properties of the tests are examined
by simulation and illustrated with applications to real US GNP data.
Recommended Citation
Cees Diks and Sebastiano Manzan
(2002)
"Tests for Serial Independence and Linearity Based on Correlation Integrals",
Studies in Nonlinear Dynamics & Econometrics:
Vol. 6:
No. 2,
Article 2.
http://www.bepress.com/snde/vol6/iss2/art2
Related Files
datacode.zip (13 kB) Data & Code |
|---|---|
| ISSN: | 1558-3708 1558-3708 |
| DOI: | 10.2202/1558-3708.1005 |