On causal and non‐causal cointegrated vector autoregressive time series

Previous‐30 treatments of multivariate non‐causal time series have assumed stationarity. In this article, we consider integrated processes in a non‐causal setting. We generalize the Johansen–Granger representation for causal vector autoregressive (VAR) models to allow for dependence on future errors...

Full description

Saved in:
Bibliographic Details
Published in:Journal of time series analysis Vol. 43; no. 2; pp. 178 - 196
Main Author: Rygh Swensen, Anders
Format: Journal Article
Language:English
Published: Oxford, UK John Wiley & Sons, Ltd 01.03.2022
Blackwell Publishing Ltd
Subjects:
Autoregressive models
Causal models
Causality
cointegration
Errors
non‐causal models
Time series
Treatment methods
Vector autoregressive models
ISSN:0143-9782, 1467-9892
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Previous‐30 treatments of multivariate non‐causal time series have assumed stationarity. In this article, we consider integrated processes in a non‐causal setting. We generalize the Johansen–Granger representation for causal vector autoregressive (VAR) models to allow for dependence on future errors and discuss how the parameters can be estimated. The asymptotic distribution of the trace statistic is also considered. Some Monte Carlo simulations are presented.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0143-9782
1467-9892
DOI:10.1111/jtsa.12607