Advances and Applications in Statistics
Volume 30, Issue 2, Pages 77 - 92
(October 2012)
|
|
A PROCEDURE TO DETECT HIDDEN COINTEGRATION WITH THE SIEVE BOOTSTRAP
M. Gerolimetto, C. Pizzi and I. Procidano
|
Abstract: In this paper, we investigate about a particular form of cointegration, called hidden cointegration, arising between positive and/or negative components of a time series and useful to model asymmetric behaviours, though requiring specific estimation and testing procedures. Consistently with this, we propose a bootstrap version of Engle and Granger [9] procedure to detect hidden cointegration and present some Monte Carlo evidences to show the performance of the procedure. |
Keywords and phrases: |
|
Number of Downloads: 361 | Number of Views: 1121 |
|