[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: VAR or VEC model

From   "Villa Lora, Juan Miguel" <>
To   <>
Subject   st: RE: VAR or VEC model
Date   Mon, 24 Aug 2009 16:34:35 -0400

I'm not an expert but let me tell you what I know:
Both are multivariate model of time series and the main difference
regards to the final part of you question. You need to run first a
causality test as well as a unit root test in order to explore if there
is a endogenous or exogenous relation among your variables. 

Let's say you have var1 and var1, if var1 causes "Grangerly" to var2 and
both don't have jointly a unit root you might run a VAR. If var1 doesn't
cause "Grangerly" var2 but they jointly have a unit root the correct
model is the error correction.

Nevertheless, any explanation by mail would be incomplete. You might
review the Ender's book "Applied Econometrics of Time Series". Good

-----Original Message-----
[] On Behalf Of Ihtesham
Sent: Lunes, 24 de Agosto de 2009 03:51 p.m.
Subject: st: VAR or VEC model

I would like to test the relationship between the FTSE100 index and a
variety of macroeconomic variables.
What is the difference between the VAR and VEC models in estimating the
relationships and so how do I decide which one to use in my estimation.
I am looking to do the Cointegration and Granger Causality Tests if that
makes a difference.
Kind Regards.
Windows Live Messenger: Thanks for 10 great years-enjoy free winks and
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index