nep-ets New Economics Papers
on Econometric Time Series
Issue of 2005‒09‒02
two papers chosen by
Yong Yin
SUNY at Buffalo

  1. Unit Roots and Cointegration in Panels By Jörg Breitung; M. Hashem Pesaran
  2. Finite-Sample Simulation-Based Inference in VAR Models with Applications to Order Selection and Causality Testing By Jean-Marie Dufour; Tarek Jouini

  1. By: Jörg Breitung; M. Hashem Pesaran
    Abstract: This paper provides a review of the literature on unit roots and cointegration in panels where the time dimension (T), and the cross section dimension (N) are relatively large. It distinguishes between the first generation tests developed on the assumption of the cross section independence, and the second generation tests that allow, in a variety of forms and degrees, the dependence that might prevail across the different units in the panel. In the analysis of cointegration the hypothesis testing and estimation problems are further complicated by the possibility of cross section cointegration which could arise if the unit roots in the different cross section units are due to common random walk components.
    Keywords: Panel Unit Roots, Panel Cointegration, Cross Section Dependence, Common Effects
    JEL: C12 C15 C22 C23
    Date: 2005–08
    URL: http://d.repec.org/n?u=RePEc:cam:camdae:0535&r=ets
  2. By: Jean-Marie Dufour; Tarek Jouini
    Abstract: Statistical tests in vector autoregressive (VAR) models are typically based on large-sample approximations, involving the use of asymptotic distributions or bootstrap techniques. After documenting that such methods can be very misleading even with fairly large samples, especially when the number of lags or the number of equations is not small, we propose a general simulation-based technique that allows one to control completely the level of tests in parametric VAR models. In particular, we show that maximized Monte Carlo tests [Dufour (2005, Journal of Econometrics)] can provide provably exact tests for such models, whether they are stationary or integrated. Applications to order selection and causality testing are considered as special cases. The technique developed is applied to quarterly and monthly VAR models of the U.S. economy, comprising income, money, interest rates and prices, over the period 1965-1996. <P>Les tests statistiques sur des modèles autorégressifs multivariés (VAR) sont habituellement basés sur des approximations de grands échantillons, qui utilisent une loi asymptotique ou une technique de bootstrap. Après avoir montré que ces méthodes peuvent être très peu fiables, même avec des échantillons de taille assez grande, particulièrement lorsque le nombre des retards ou le nombre d’équations augmentent, nous proposons une technique générale basée sur la simulation qui permet de contrôler parfaitement le niveau des tests dans les modèles VAR paramétriques. En particulier, nous montrons que la technique des tests de Monte Carlo maximisés [Dufour (2005, Journal of Econometrics)] fournit des tests exacts pour de tels modèles, que ceux-ci soient stationnaires ou intégrés. Sélectionner l’ordre du modèle ainsi que tester la causalité au sens de Granger sont étudiés comme problèmes particuliers dans ce cadre. La technique proposée est appliquée à des modèles VAR, trimestriels et mensuels, de l’économie américaine, comprenant le revenu, la monnaie, un taux d’intérêt et le niveau des prix, sur la période 1965-1996.
    Keywords: bootstrap, exact test, Granger causality, inflation, interest rate, macroeconomics, maximized Monte Carlo test, money and income, Monte Carlo test, nonstationary model, order selection, VAR, vector autoregression, autorégression vectorielle, bootstrap, causalité au sens de Granger, inflation, macroéconomie, modèle non-stationnaire, monnaie et revenu, sélection de l’ordre, taux d’intérêt, test exact, test de Monte Carlo, test de Monte Carlo maximisé, VAR
    JEL: C32 C12 C15 E4 E5
    Date: 2005–08–01
    URL: http://d.repec.org/n?u=RePEc:cir:cirwor:2005s-26&r=ets

This nep-ets issue is ©2005 by Yong Yin. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.