Hello Eviews users and moderators
Please assist with the following. Eviews 10: I am estimating two linear equations that have the same explanatory variables, except for one variable that is defined differently for one equation versus another one. I need to test for statistical significance of the coefficients on this differently defined variable across two regressions. The possible solution I came across online is to implement such a test manually using the formula for two coefficients of interest:
his approach is to use the following Z test:
Z=(β1−β2)/square root of[(SEβ1)^2+(SEβ2)^2]
Where SEβ
is the standard error of β.
Is there any way to implement such a testing of equality of coefficients across models in Eviews 10 without manual derivations? Thank you in advance.
Comparing coefficients accross regressions
Moderators: EViews Gareth, EViews Moderator
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: Comparing coefficients accross regressions
Set up the equations in a system object.
Re: Comparing coefficients accross regressions
Thanks! Would you suggest setting up an equation via a code or there is some built in algorithm that can estimate a system? How would I test for the equality of coefficients once the system is estimated? Thanks again!
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: Comparing coefficients accross regressions
Object/New object/System
opens a system object. Look at the help system for info on how to enter the equations in that object.
opens a system object. Look at the help system for info on how to enter the equations in that object.
Who is online
Users browsing this forum: No registered users and 27 guests