Cointegration

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

ElineP
Posts: 5
Joined: Tue Apr 05, 2011 7:17 am

Cointegration

Postby ElineP » Fri Apr 15, 2011 4:36 am

Hi everybody,

Since we don't understand that much of Eviews, we need your help.
We're trying to estimate the income elasticity by modelling the money demand.
I have the following equation:

RMBt = K(y) Yt + K(Tau) T - K(i) It + Sommation from s=-3 to 3 ( (K(y)s)*d(y(t+s)) + (K(i)s)*d(i(t+s)) ) + Et

where It = Long term interest rate - short term interest rate

Since we are not sure whether or not the sommation term has to be included we decided first to try equation

RMBt = K(y) Yt + K(tau) T + K(i1) short term rate + K(i2) long term rate + Et

We already did unit root tests and found out that RMBt (= Mt - Pt), Yt, T and the interest rates all are I(1).

But that's where we get stuck. Ultimatly we want the K(y), K(i1) and K(i2) values. We are guessing that we have to do something with cointegrating vectors but we are not able to find these . We also are clueless about the rank (Johannson trace test), so we don't know how to find out how many vectors we have to use.
Do we have to include the time trend as a variable or do we include the fact that there is a time trend in the settings of the tests?

We don't have much knowledge about econometrics and read a bunch of articles and chapters about cointegration but we fail to use these to get our results out of eviews ( version 7 student version) and any help is very much appreciated since we have a deadline.

thank you

Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests