Reduced form

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

milanbouda
Posts: 2
Joined: Sat Mar 05, 2011 9:53 am

Reduced form

Postby milanbouda » Sat Mar 05, 2011 10:31 am

Hi,

I normal estimate a system in structural form. Do you know how to obtain the reduced form parameters? In the menu is not a direct link. Does anybody know a trick? I don't want to do it manually or in other software. For example SAS and PcGive have a direct command for this situation.

Thanks a lot,

Milan

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Reduced form

Postby startz » Sat Mar 05, 2011 10:47 am

If you mean for a linear simultaneuous equations system, the reduced form is just a regression of each endogenous variable on all the exogenous variables.

milanbouda
Posts: 2
Joined: Sat Mar 05, 2011 9:53 am

Re: Reduced form

Postby milanbouda » Sat Mar 05, 2011 11:49 am

Yes I know. But it is necessary to transform. It is not a regression on all the exogenous variables in the model. So I need to transform structural form to reduced form. It is not hard operation. You can do this manually or in Excel. But If you are estimating a large model, it is boring. Is possible to do it quick in EViews? With some matrix formula...or function...??
Thanks

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Reduced form

Postby startz » Sat Mar 05, 2011 12:33 pm

Why don't you post your actual problem and explain what you're planning on doing with the reduced form? Perhaps someone here will have a more specific suggestion.


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests