EViews.com

Hello,

I am trying to perform an out of sample analysis in expanding windows automatically, but unfortunately I lack any programming skills, regardless my effort reading the Programming References.
I have a monthly sample from 1927m01 2011m12. I have defined the equation I want to use. My question is that I want to use the first 20 years of data (i.e. 1927m01 1946m12) to forecast one month (i.e. 1947m01). After that, I want to use the first 20 years and one month of actual data (i.e. 1927m01 1947m01) to forecast the next month (i.e. 1947m02), and so on, until 2011m12. The objective is to store the forecasted values in order to compute the errors between them and the actual values and be able to perform the out-of sample analysis. I have been trying to create a program in order to do this, to avoid estimating 880 different forecasts manually, but I don’t know if it is possible to do it automatically.

Looking forward to hearing some suggestions,
Best Regards,

Nuno

I presume you've read through this:?
http://forums.eviews.com/viewtopic.php?f=15&t=878

Thanks Gareth!

I looked through it, modified what was needed and it works perfectly

Hi, I want to do the same out of sample predictability test as you mentioned (I think it is called recursive forecasts to predict one month ahead). However, I do not know programming. Can you suggest any other way to do this without programming please? I would really appreciate this :D