Forecasting with VECM Model

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

UBS
Posts: 3
Joined: Sat Feb 20, 2021 11:10 am

Forecasting with VECM Model

Postby UBS » Sat Feb 20, 2021 11:22 am

Hi, i have two variables - hpi and sp500. My training data set is from 2011m2 to 2019m12. Using a VAR VECM model I am trying to forecast hpi from 2020m1 through 2020m11. I already have the forecasts for sp500 through 2020m11. But I keep getting this error in Eviews (see attached). Please advice.


eviews_error1.jpg
eviews_error1.jpg (35.77 KiB) Viewed 3035 times


Also is there a step by step guide or examples on how to use a VECM model to forecast 2-3 years into the future if only one variable's forecasts are available and the other variable (e.g. hpi) only has actuals (history)? Also attaching working file.


hpiursandp.wf1
(90.53 KiB) Downloaded 204 times

Thanks in advance!

startz
Non-normality and collinearity are NOT problems!
Posts: 3775
Joined: Wed Sep 17, 2008 2:25 pm

Re: Forecasting with VECM Model

Postby startz » Sat Feb 20, 2021 12:00 pm

I opened var_vecm and changed the forecast to 2020m1 to 2020m11 and hit the forecast button. It worked perfectly, (I realize that's not very helpful.)

Any chance you have an out-of-date version of EViews?

UBS
Posts: 3
Joined: Sat Feb 20, 2021 11:10 am

Re: Forecasting with VECM Model

Postby UBS » Sat Feb 20, 2021 1:01 pm

Thanks, that worked on my end too. Simple enough!


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 32 guests