Variance Decomposition in Eviews

[Reynaldo2007]

Hello,

I am performing cointegration analysis using Eviews and the DOLS estimator in the cointegrating equation. After saving the residuals of this equation (they are stationary then the variables are cointegrated), I estimated the short run equation including the lagged error term, one lag of the dependent and independent variables taken in differences (my sample is not large), and a constant. I got the coefficients of the VECM. However, I want to perform a Variance Decomposition analysis, but I did not find how (please, remember that I apply DOLS that is a two step procedure, because using VAR or VECM it is very easy to find the way to do it in Eviews), there is not any option in Eviews to do that under the methodology I chose.

Trying to find a way i check how is obtained the Variance Decomposition under Johansen and the output show me the variables in levels, lets say logarithm of GDP and I read some research papers and everything is confusing for me because several works clearly seem that they worked in differences (when i see their tables), but others seem to do it in levels. This is my first question: Under cointegration, are the variables included in the Variance decomposition taken in levels or differences?

I ask this because I was thinking that in this case that I have included only one lag for all variables in the ECM, if I estimate an unrestricted VAR including the difference of the dependent variable and the independent variables and the estimated error term, the coefficients of the VAR in the case of the difference of the exogenous variable that I considered in the DOLS are EXACTLY the same of the ECM that I estimated. The only difference is that when estimating the VAR, I will get also the equations considering the independent variable and the error term as dependent variable.

Then if the Variance Decomposition under VECM is done for the variables in differences (and not in levels) I may solve my problem by estimating the VAR that i describe in the previous paragraph.

Kind Regard