Multivariate unit root tests

This paper presents a new multivariate test for the detection of unit roots. Use is made of the possible correlations between the disturbances of different series, and constrained and unconstrained SURE estimators are employed. The corresponding asymptotic distributions are obtained and a table with a few critical values, for the case of two series, is generated. Some simulations indicate that the procedure performs better than the existing alternatives.

MoreLess

Year of publication:	1995
Authors:	Szafarz, Ariane ; Flôres, Renato ; Preumont, Pierre-Yves
Institutions:	Centre Emile Bernheim, Solvay Brussels School of Economics and Management
Subject:	unit root \| multivariate test \| stationarity \| panel data

More details

Extent:	application/pdf
Series:	Working Papers CEB.
Type of publication:	Book / Working Paper
Notes:	Published by: The text is part of a series Working papers CEB Number 95-001.RS
Classification:	C12 - Hypothesis Testing ; C30 - Econometric Methods: Multiple/Simultaneous Equation Models. General ; C52 - Model Evaluation and Testing ; C33 - Models with Panel Data ; C32 - Time-Series Models
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005558898