## VAR Data Members

For requesting general information about EViews, sharing your own tips and tricks, and information on EViews training or guides.

Moderators: EViews Gareth, EViews Moderator

RDS
Posts: 86
Joined: Thu Feb 17, 2011 9:50 am

### VAR Data Members

I need to save the Schwarz criterion and the log likelihood of a specific equation of a VAR.

This for example doe not work:
var example_var.ls 1 2 x1 x2 x3
scalar loglikelihood = example_var.@eqlogl(1)
scalar SC = example_var.@schwarz(1)

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12420
Joined: Tue Sep 16, 2008 5:38 pm

### Re: VAR Data Members

VAR data members are located at the start of the VAR section of the Object Reference.

Each object's data members are located at the start of its section in the Object Reference.

RDS
Posts: 86
Joined: Thu Feb 17, 2011 9:50 am

### Re: VAR Data Members

Yes, I looked at the Object reference. As said this does not worK:

var example_var.ls 1 2 x1 x2 x3
scalar loglikelihood_x1 = example_var.@eqlogl(1)
scalar SC_x1 = example_var.@sc(1)

The numbers I get are not those reproduced by EVIEWS in its Vector Autoregression Estimates.

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12420
Joined: Tue Sep 16, 2008 5:38 pm

### Re: VAR Data Members

Ah, sorry, I missed the part where you said you wanted the equation specific one. Only the system wide ICs are available from the VAR, not the equation specific ones.

You can, of course calculate it though:

Code: Select all

create u 100
series x1=nrnd
series x2=nrnd
series x3=nrnd

var example_var.ls 1 2 x1 x2 x3
scalar loglikelihood_x1 = example_var.@eqlogl(1)
!t = example_var.@eqregobs(1)
!l = example_var.@eqlogl(1)
!n = example_var.@eqncoef(1)
scalar SC_x1 = -2*!l/!t + !n*@log(!t)/!t

show example_var
show sc_x1

RDS
Posts: 86
Joined: Thu Feb 17, 2011 9:50 am

### Re: VAR Data Members

These are the number of your VAR
x1 x2 x3
Log likelihood -144.4427 -132.9798 -138.4324
Schwarz SC 3.275307 3.041371 3.152648

and these are the values of your scalar sc_x1 = 8.78354 and loglikelihood_x1 = -414.34622

They are very different.

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12420
Joined: Tue Sep 16, 2008 5:38 pm

### Re: VAR Data Members

In mine they match. What's the version and build date of your copy of EViews (Help->About EViews)?

RDS
Posts: 86
Joined: Thu Feb 17, 2011 9:50 am

### Re: VAR Data Members

Version 7.2
Enterprise edition Sep 23 2011 buid

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12420
Joined: Tue Sep 16, 2008 5:38 pm

### Re: VAR Data Members

RDS
Posts: 86
Joined: Thu Feb 17, 2011 9:50 am

### Re: VAR Data Members

There is a bug in eviews 7.2?

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 12420
Joined: Tue Sep 16, 2008 5:38 pm

### Re: VAR Data Members

Well that might explain why you're not getting matching results. Your copy is very out of date. There have been 46 patches since your version, each of which contains multiple bug fixes.