The output of the regression dosn't show the f-statistic

For notifying us of what you believe are bugs or errors in EViews.
Please ensure your copy of EViews is up-to-date before posting.

Moderators: EViews Gareth, EViews Moderator

cafps@iscte.pt
Posts: 2
Joined: Thu Mar 19, 2015 8:08 am

The output of the regression dosn't show the f-statistic

Postby cafps@iscte.pt » Thu Mar 19, 2015 8:24 am

Hy,

I'm using the 6 eviews version and the f-statistic doesn't appear in the output of a regression as you can see in the attached file.

Probably this can be solved using a command, but so far, I haven't been able to solve this problem.

Best,

Cláudio
Attachments
Output.docx
(54.22 KiB) Downloaded 446 times

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

Re: The output of the regression dosn't show the f-statistic

Postby startz » Thu Mar 19, 2015 8:31 am

EViews does not show the F-statistic if you do not include a constant. I can't think of any good reason for not showing it.

You can always compute the F-statistic manually from View/Coefficient Diagnostics/Wald test. In your case enter c(1)=0,c(2)=0,c(3)=0.

cafps@iscte.pt
Posts: 2
Joined: Thu Mar 19, 2015 8:08 am

Re: The output of the regression dosn't show the f-statistic

Postby cafps@iscte.pt » Thu Mar 19, 2015 9:13 am

Thanks for your reply. I have checked and as you said if I add the constant the f-statistic is shown. Is there any reason for this to happen? Because if I use a earlier version of eviews that problem is solved.

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13600
Joined: Tue Sep 16, 2008 5:38 pm

Re: The output of the regression dosn't show the f-statistic

Postby EViews Gareth » Thu Mar 19, 2015 10:38 am

The f-statistic calculation is made using the R-squared form, which is only valid if there is a constant.

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

Re: The output of the regression dosn't show the f-statistic

Postby startz » Thu Mar 19, 2015 10:45 am

So why not use the matrix wald form internally or use the ssr form internally. Consider the mild weirdness that these in these identical regressions the first reports the F and the second doesn't.

Code: Select all

ls y c x>0 ls y x<=0 x>0


Return to “Bug Reports”

Who is online

Users browsing this forum: No registered users and 2 guests