Significance in PDLs

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

firefoxxp
Posts: 2
Joined: Sun Apr 17, 2016 8:18 am

Significance in PDLs

Postby firefoxxp » Sun Apr 17, 2016 8:48 am

Hi, everyone,
When I use PDLs to estimate a distributed lag model, how could I know each explanatory variable is significant or not?
As in Eviews help, PDL01 to PDL06 are all not significant to the t-statistic, The original coefficients seems also insignificant, can I ingore all these informations and only see the sum of lags? How can I judge whether the explanatory variables are significant or not?
Many thanks!

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

Re: Significance in PDLs

Postby startz » Sun Apr 17, 2016 9:42 am

Look at the representations view. You will see that an equation like

Code: Select all

LS Y C PDL(X,3,2)
is estimated as
Y = C(1) + C(2)*PDL01 + C(3)*PDL02 + C(4)*PDL03

Use View/Coefficient diagnostics/Wald to test the hypothesis

Code: Select all

c(2)=c(3)=c(4)=0

firefoxxp
Posts: 2
Joined: Sun Apr 17, 2016 8:18 am

Re: Significance in PDLs

Postby firefoxxp » Sun Apr 17, 2016 7:55 pm

Many thanks!
I still don't know if all the PDLs are significant according to Wald test, then the related sum of lags must be significant? As the t-statistic indicate that sum of lags is not significant.
How to know the significance of the "sum of lags" at the bottom of the table?
Many thanks!


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests