Need help to estimate the Coef matrices in mAr

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

Need help to estimate the Coef matrices in mAr

Arun.stat
Dear R users,

I am using mAr package to fit a Vector autoregressive model to my data. But
here I want to put some predetermined values for some elements in
coefficient matrix that mAr.est going to estimate. For example if p=3 then I
want to put A3[1,3] = 0 and keep rest of the elements of coefficient
matrices to be determined by mAr.est.

Can anyone please tell me how can I do that?

Sincerely yours,
Arun

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Need help to estimate the Coef matrices in mAr

Spencer Graves
      Have you tried 'RSiteSearch("multivariate autoregression",
"functions")'?  This produced 14 hits for me just now, the first of
which mentions a package 'MSBVAR'.  Have you looked at that?

      If that failed, I don't think it would be too hard to modify
'mAr.est' to do what you want.  If it were my problem, I might a local
copy of the function, then add an argument accepting a 2 or
3-dimensional array with numbers for AR coefficients to be fixed and NAs
for the coefficients.  Then I'd use 'debug' to walk through the function
line by line until I figured out how to modify the function to do what I
wanted.  I haven't checked all the details, so I don't know for sure if
this would work, but the function contains a line 'R = qr.R(qr((rbind(K,
diag(scale)))), complete = TRUE)' which I would start by decomposing,
possibly starting as follows:

      Z <-     rbind(K, diag(scale)

I'd figure out how the different columns of Z relate to my problem, then
modify it appropriately to get what I wanted.

      Another alternative would be to program it from scratch using
something like 'optim' to minimize the sum of squares of residuals over
the free parameters in my AR matrices.   I'm confident I could make this
work, even if the I somehow could not get it with either of the other two.

      There may be something else  better, e.g., a Kalman filter
representation, but I can't think how to do that off the top if my head.

      Hope this helps.
      Spencer Graves

Arun Kumar Saha wrote:

> Dear R users,
>
> I am using mAr package to fit a Vector autoregressive model to my data. But
> here I want to put some predetermined values for some elements in
> coefficient matrix that mAr.est going to estimate. For example if p=3 then I
> want to put A3[1,3] = 0 and keep rest of the elements of coefficient
> matrices to be determined by mAr.est.
>
> Can anyone please tell me how can I do that?
>
> Sincerely yours,
> Arun
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: [R] Need help to estimate the Coef matrices in mAr

Arun.stat
Dear Spencer,



Thank you very much for your attention on my problem. According to your
advice I did some home work on this problem, but unfortunately I could not
solve my problem.





Suppose I have a dataset of length 300 with 2 variables. And I want to fit a
VAR model on this of order 2.



I went through the function mAr.est and got understand that, here 'K' is a
matrix with (300-2) rows and 7 columns. the first col. consists only 1, next
two columns consist of lagged values of two variables with lag-length 2,
next two col. consist of lagged value with lag length-1, and next two cols
are for lag-length-0.



Next, they add additional a 7-7 matrix to K. For this matrix diagonal
elements are the square root of sum of square of elements of K (col. wise)
and rest of the elements are 0.



I feel that this matrix, that is added to K, is the key matrix for any type
of modification that you prescribed. Therefore for experimental purpose I
put NA against one of its off-diagonal elements. But I got error.



However I cannot understand why they put such figures for diagonal and
off-diagonal elements of that matrix.



Can you suggest me any solution more specifically?





Thanks and regards,

Arun


On 9/4/06, Spencer Graves <[hidden email]> wrote:

>
>       Have you tried 'RSiteSearch("multivariate autoregression",
> "functions")'?  This produced 14 hits for me just now, the first of
> which mentions a package 'MSBVAR'.  Have you looked at that?
>
>       If that failed, I don't think it would be too hard to modify
> 'mAr.est' to do what you want.  If it were my problem, I might a local
> copy of the function, then add an argument accepting a 2 or
> 3-dimensional array with numbers for AR coefficients to be fixed and NAs
> for the coefficients.  Then I'd use 'debug' to walk through the function
> line by line until I figured out how to modify the function to do what I
> wanted.  I haven't checked all the details, so I don't know for sure if
> this would work, but the function contains a line 'R = qr.R(qr((rbind(K,
> diag(scale)))), complete = TRUE)' which I would start by decomposing,
> possibly starting as follows:
>
>       Z <-     rbind(K, diag(scale)
>
> I'd figure out how the different columns of Z relate to my problem, then
> modify it appropriately to get what I wanted.
>
>       Another alternative would be to program it from scratch using
> something like 'optim' to minimize the sum of squares of residuals over
> the free parameters in my AR matrices.   I'm confident I could make this
> work, even if the I somehow could not get it with either of the other two.
>
>       There may be something else  better, e.g., a Kalman filter
> representation, but I can't think how to do that off the top if my head.
>
>       Hope this helps.
>       Spencer Graves
>
> Arun Kumar Saha wrote:
> > Dear R users,
> >
> > I am using mAr package to fit a Vector autoregressive model to my data.
> But
> > here I want to put some predetermined values for some elements in
> > coefficient matrix that mAr.est going to estimate. For example if p=3
> then I
> > want to put A3[1,3] = 0 and keep rest of the elements of coefficient
> > matrices to be determined by mAr.est.
> >
> > Can anyone please tell me how can I do that?
> >
> > Sincerely yours,
> > Arun
> >
> >       [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > [hidden email] mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> >
>



--
Arun Kumar Saha, M.Sc.[C.U.]
S T A T I S T I C I A N    [Analyst]
RISK  MANAGEMENT  DIVISION
Transgraph Consulting [www.transgraph.com]
Hyderabad, INDIA
Contact #  Home: (91-033) 25558038
                Office: (91-040) 30685012 Ext. 17
                  FAX: (91-040) 55755003
               Mobile: 919989122010
E-Mail: [hidden email]
            [hidden email]

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: [R] Need help to estimate the Coef matrices in mAr

Spencer Graves
      I'm sorry, but I can't follow what you are asking.  If you'd like
more help, please provide commented, minimal, self-contained,
reproducible code, as suggested in the posting guide
"www.R-project.org/posting-guide.html".
<http://www.R-project.org/posting-guide.html>  Please include a minimal
data set, e.g., 10 simulated observations on 2 variables, with comments
describing what you tried and what you don't understand about it.

      Hope this helps.
      Spencer Graves

Arun Kumar Saha wrote:

>
> Dear Spencer,
>
>  
>
> Thank you very much for your attention on my problem. According to
> your advice I did some home work on this problem, but unfortunately I
> could not solve my problem.
>
>  
>
>  
>
> Suppose I have a dataset of length 300 with 2 variables. And I want to
> fit a VAR model on this of order 2.
>
>  
>
> I went through the function mAr.est and got understand that, here 'K'
> is a matrix with (300-2) rows and 7 columns. the first col. consists
> only 1, next two columns consist of lagged values of two variables
> with lag-length 2, next two col. consist of lagged value with lag
> length-1, and next two cols are for lag-length-0.
>
>  
>
> Next, they add additional a 7-7 matrix to K. For this matrix diagonal
> elements are the square root of sum of square of elements of K (col.
> wise) and rest of the elements are 0.
>
>  
>
> I feel that this matrix, that is added to K, is the key matrix for any
> type of modification that you prescribed. Therefore for experimental
> purpose I put NA against one of its off-diagonal elements. But I got
> error.
>
>  
>
> However I cannot understand why they put such figures for diagonal and
> off-diagonal elements of that matrix.
>
>  
>
> Can you suggest me any solution more specifically?
>
>  
>
>  
>
> Thanks and regards,
>
> Arun
>
>
>
> On 9/4/06, *Spencer Graves* <[hidden email]
> <mailto:[hidden email]>> wrote:
>
>           Have you tried 'RSiteSearch("multivariate autoregression",
>     "functions")'?  This produced 14 hits for me just now, the first of
>     which mentions a package 'MSBVAR'.  Have you looked at that?
>
>           If that failed, I don't think it would be too hard to modify
>     'mAr.est' to do what you want.  If it were my problem, I might a local
>     copy of the function, then add an argument accepting a 2 or
>     3-dimensional array with numbers for AR coefficients to be fixed
>     and NAs
>     for the coefficients.  Then I'd use 'debug' to walk through the
>     function
>     line by line until I figured out how to modify the function to do
>     what I
>     wanted.  I haven't checked all the details, so I don't know for
>     sure if
>     this would work, but the function contains a line 'R =
>     qr.R(qr((rbind(K,
>     diag(scale)))), complete = TRUE)' which I would start by decomposing,
>     possibly starting as follows:
>
>           Z <-     rbind(K, diag(scale)
>
>     I'd figure out how the different columns of Z relate to my
>     problem, then
>     modify it appropriately to get what I wanted.
>
>           Another alternative would be to program it from scratch using
>     something like 'optim' to minimize the sum of squares of residuals
>     over
>     the free parameters in my AR matrices.   I'm confident I could
>     make this
>     work, even if the I somehow could not get it with either of the
>     other two.
>
>           There may be something else  better, e.g., a Kalman filter
>     representation, but I can't think how to do that off the top if my
>     head.
>
>           Hope this helps.
>           Spencer Graves
>
>     Arun Kumar Saha wrote:
>     > Dear R users,
>     >
>     > I am using mAr package to fit a Vector autoregressive model to
>     my data. But
>     > here I want to put some predetermined values for some elements in
>     > coefficient matrix that mAr.est going to estimate. For example
>     if p=3 then I
>     > want to put A3[1,3] = 0 and keep rest of the elements of
>     coefficient
>     > matrices to be determined by mAr.est.
>     >
>     > Can anyone please tell me how can I do that?
>     >
>     > Sincerely yours,
>     > Arun
>     >
>     >       [[alternative HTML version deleted]]
>     >
>     > ______________________________________________
>     > [hidden email] <mailto:[hidden email]>
>     mailing list
>     > https://stat.ethz.ch/mailman/listinfo/r-help
>     <https://stat.ethz.ch/mailman/listinfo/r-help>
>     > PLEASE do read the posting guide
>     http://www.R-project.org/posting-guide.html
>     > and provide commented, minimal, self-contained, reproducible code.
>     >
>
>
>
>
> --
> Arun Kumar Saha, M.Sc.[C.U.]
> S T A T I S T I C I A N    [Analyst]
> RISK  MANAGEMENT  DIVISION
> Transgraph Consulting [ www.transgraph.com <http://www.transgraph.com>]
> Hyderabad, INDIA
> Contact #  Home: (91-033) 25558038
>                 Office: (91-040) 30685012 Ext. 17
>                   FAX: (91-040) 55755003
>                Mobile: 919989122010
> E-Mail: [hidden email]
> <mailto:[hidden email]>
>             [hidden email] <mailto:[hidden email]>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.