11:07 a.m.
Dear Marvin,
You must use the VAR residuals covariance matix. From what I see in your
Excel icons, the covariance matrix you employ is (named Omega there) the
covaiance matrix of your data series.
Best,
11:36 a.m.
New subject: Function of the AIC in VAR lag selection (Marvin Berndt) (Marvin Berndt)
12:21 p.m.
New subject: Function of the AIC in VAR lag selection (Marvin Berndt) (Marvin Berndt)
Am 02.03.2018 um 12:36 schrieb Marvin Berndt:
Dear Ioannis,
the residual in the Excel-sheets are those from the VAR regresison. I
extracted them from the VAR regression Output via '/Save --> Residuals
from equation 1/2/'. I used those residuals in order to try to recreate
the AIC in gretl.
With such a short sample I suspect it makes a big difference whether 1/T
or 1/(T-K) is used for the (co)variance calculation. Both variants are
"correct" in that the method is for large samples anyway.
There was a discussion on this (ore the devel) mailing list about
whether to apply a d.o.f.-correction for VARs but I cannot find it. I
agree it could be documented better, the VAR chapter in the guide is
--alas-- still not finished.
I _believe_, however, that gretl for VARs does it without this
small-sample correction (this would also apply to the $sigma accessor,
to those who know what that is).
In principle we could all look it up in the source, right? Hehe. (Apart
from the fact that currently sourceforge is not accessible.)
cheers,
sven
12:56 p.m.
New subject: Function of the AIC in VAR lag selection (Marvin Berndt) (Marvin Berndt)
Chapter 25 (Model Selection Criteria) in the Gretl user's guide defines the
AIC as
AIC = -2‘(θ ˆ) + 2k - *(Pasted formula not quite correct - see Guide ) *
The formulas that you quote are both monotonic transformations of this
formula. That is the order of the models is not changed under these
transformations. All formulas lead to the same conclusion. I would
presume that some formulas are easier to calculate for certain types of
models.
I would also comment that estimating 10 coefficients and co-variances
with 10 observations (and 2 obs to initialize) will not lead to reliable
results.
John C Frain
3 Aranleigh Park
Rathfarnham
Dublin 14
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:frainj@tcd.ie
mailto:frainj@gmail.com
On 2 March 2018 at 12:21, Sven Schreiber <svetosch(a)gmx.net> wrote:
Am 02.03.2018 um 12:36 schrieb Marvin Berndt:
> Dear Ioannis,
> the residual in the Excel-sheets are those from the VAR regresison. I
> extracted them from the VAR regression Output via '/Save --> Residuals from
> equation 1/2/'. I used those residuals in order to try to recreate the AIC
> in gretl.
>
With such a short sample I suspect it makes a big difference whether 1/T
or 1/(T-K) is used for the (co)variance calculation. Both variants are
"correct" in that the method is for large samples anyway.
There was a discussion on this (ore the devel) mailing list about whether
to apply a d.o.f.-correction for VARs but I cannot find it. I agree it
could be documented better, the VAR chapter in the guide is --alas-- still
not finished.
I _believe_, however, that gretl for VARs does it without this
small-sample correction (this would also apply to the $sigma accessor, to
those who know what that is).
In principle we could all look it up in the source, right? Hehe. (Apart
from the fact that currently sourceforge is not accessible.)
cheers,
sven
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
1:10 p.m.
New subject: Fwd: Function of the AIC in VAR lag selection (Marvin Berndt) (Marvin Berndt)
I have just noticed that Chapter 25 of the user's guide contains a very
good discussion of the transformations of the AIC.
---------- Forwarded message ----------
From: John C Frain <frainj(a)gmail.com>
Date: 2 March 2018 at 12:56
Subject: Re: [Gretl-users] Function of the AIC in VAR lag selection (Marvin
Berndt) (Marvin Berndt)
To: Gretl list <gretl-users(a)lists.wfu.edu>
Chapter 25 (Model Selection Criteria) in the Gretl user's guide defines the
AIC as
AIC = -2‘(θ ˆ) + 2k - *(Pasted formula not quite correct - see Guide ) *
The formulas that you quote are both monotonic transformations of this
formula. That is the order of the models is not changed under these
transformations. All formulas lead to the same conclusion. I would
presume that some formulas are easier to calculate for certain types of
models.
I would also comment that estimating 10 coefficients and co-variances
with 10 observations (and 2 obs to initialize) will not lead to reliable
results.
John C Frain
3 Aranleigh Park
Rathfarnham
Dublin 14
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:frainj@tcd.ie
mailto:frainj@gmail.com
On 2 March 2018 at 12:21, Sven Schreiber <svetosch(a)gmx.net> wrote:
Am 02.03.2018 um 12:36 schrieb Marvin Berndt:
> Dear Ioannis,
> the residual in the Excel-sheets are those from the VAR regresison. I
> extracted them from the VAR regression Output via '/Save --> Residuals from
> equation 1/2/'. I used those residuals in order to try to recreate the AIC
> in gretl.
>
With such a short sample I suspect it makes a big difference whether 1/T
or 1/(T-K) is used for the (co)variance calculation. Both variants are
"correct" in that the method is for large samples anyway.
There was a discussion on this (ore the devel) mailing list about whether
to apply a d.o.f.-correction for VARs but I cannot find it. I agree it
could be documented better, the VAR chapter in the guide is --alas-- still
not finished.
I _believe_, however, that gretl for VARs does it without this
small-sample correction (this would also apply to the $sigma accessor, to
those who know what that is).
In principle we could all look it up in the source, right? Hehe. (Apart
from the fact that currently sourceforge is not accessible.)
cheers,
sven
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
2487
days inactive
2487
days old
4 comments
4 participants
participants (4)
-
Ioannis A. Venetis -
John C Frain -
Marvin Berndt -
Sven Schreiber