Near singular matrix

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

kzmh78
Posts: 15
Joined: Mon Nov 08, 2010 9:27 am

Near singular matrix

Postby kzmh78 » Mon Nov 14, 2011 8:58 am

Hi !

When we estimated a VAR(2) model, we got a result of estimation.

But, When we individually estimated the each equation.
Then, error message 'Near singular matrix error.Regressors may be perfectly collinear' was displayed.

Is this Bug?
Attachments
testvar.wf1
(11.61 KiB) Downloaded 658 times

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

Re: Near singular matrix

Postby startz » Mon Nov 14, 2011 9:36 am

Your data is perfectly multicollinear. Note the R^2 of 1.0 in the VAR. EViews just didn't catch it in the VAR most likely because computer arithmetic is imperfect.

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13305
Joined: Tue Sep 16, 2008 5:38 pm

Re: Near singular matrix

Postby EViews Gareth » Mon Nov 14, 2011 9:50 am

It looks as though X = 10 + 0.99*X(-1) exactly (or as close to exact as a computer gets).
Follow us on Twitter @IHSEViews

kzmh78
Posts: 15
Joined: Mon Nov 08, 2010 9:27 am

Re: Near singular matrix

Postby kzmh78 » Tue Nov 15, 2011 5:04 am

Hi

Thank you very much for useful reply.


Return to “Bug Reports”

Who is online

Users browsing this forum: No registered users and 19 guests