Using the Bootstrap technique and the sample autocorrelation function for the identification of unit root processes
>By Panagiotis Mantalos
By using a Bootstrap procedure and the function of sample autocorrelations of a time series, we are able to distinguish between a non-stationary integrated series of order one, I(1), from a stationary AR(1) process. We investigated our Bootstrap procedure by using a Monte Carlo method and by an empirical example. The results show that by using the Bootstrap average of the sample autocorrelations function, we can easily identify a non-stationary I(1).
Bootstrap, Co-integration, Sample Autocorrelations, Unit Root
Rob J. Hyndman
READING THE ARTICLE: You can read the article in
portable document (.pdf) format (377379 bytes.)
NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.
This page has been accessed 2317 times since July 24, 2006.
Return to the Home Page.