Re: [R] Fixing AR coefficients in VAR model

From: Spencer Graves <spencer.graves_at_pdf.com>
Date: Fri 10 Feb 2006 - 04:14:21 EST

          I know of no existing functions in R that support fitting a multivariate autoregression while fixing some of the parameters.

          Of course, as Simon Blomberg famously said in April 2005, "This is R. There is no if. Only how." [With library(fortunes), try 'fortune("This is R")'.] If I had to do fit a multivariate AR today with some parameters fixed, I might write a function to compute the determinant of the sample covariance matrix, and give it to "optim" or "nlminb".

          I hope someone else will provide us with an easier way.

	  hope this helps,
	  spencer graves

Daniel Medina wrote:

> Dear Colleague,
>
> I would like to set a few AR coefficients (not order) to zero in the
> multivariate AR function (mAr.est; mAr library); however, the manual for
> this function does not provide this information. I would appreciate any
> suggestions along this line.
>
> Thankfully yours,
>
> Daniel C Medina
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Fri Feb 10 05:28:15 2006

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:42:27 EST