On the Distribution of the Residual Cross-Correlations between Two Uncorrelated Infinite Order Vector Autoregressive Series

Chafik Bouhaddioui and Roch Roy

CIRANO Working Papers from CIRANO

Abstract: Here we derive the asymptotic distribution of an arbitrary vector of residual cross-correlations resulting from the fitting of finite autoregressions to two uncorrelated infinite order vector autoregressive series. Its asymptotic distribution is the same multivariate normal as the one of the corresponding vector of cross-correlations between the two innovation series. The application of that result for testing the uncorrelatedness of two series is also discussed. Dans ce travail, nous obtenons la loi asymptotique d'un vecteur quelconque de corrélations croisées résiduelles résultant de l'ajustement d'autorégressions finies à deux séries non corrélées décrites par des processus autorégressifs multivariés d'ordre infini. La loi asymptotique est la même que celle du vecteur correspondant de corrélations croisées entre les deux séries d'innovations correspondantes qui est une loi multinormale. Nous discutons aussi l'application de ce résultat afin de tester l'hypothèse de non corrélation de deux séries multivariées.

Keywords: Finite autoregression; residual cross-correlations; asymptotic distribution; tests for independence; portmanteau statistics, Autorégression finie, corrélations croisées résiduelles, distribution asymptotique, tests d'indépendance, statistique Portmanteau (search for similar items in EconPapers)
Date: 2003-06-01
New Economics Papers: this item is included in nep-ecm and nep-ets
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://cirano.qc.ca/files/publications/2003s-41.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cir:cirwor:2003s-41

Access Statistics for this paper

More papers in CIRANO Working Papers from CIRANO Contact information at EDIRC.
Bibliographic data for series maintained by Webmaster ().