Re: [R] duplication matrix

From: Gabor Grothendieck <ggrothendieck_at_gmail.com>
Date: Sat 09 Sep 2006 - 23:41:26 GMT

Note that xpnd(v), which you mentioned in your post, is a linear transform whose effect on v is the same as D_n %*% v so just pump an identity matrix through xpnd to get its matrix:

library(MCMCpack)
D_n <- function(n) apply(diag(n*(n+1)/2), 2, xpnd, n)

# test
D_n(3)

On 9/9/06, w <scip1121@yahoo.com.cn> wrote:
> Dear R-list members,
> Just wondering if there is any way to compute the duplication matrix in R.
> I tried to search for it but only found functions "xpnd" and "vech".
>
> Basically for a symmetric n by n matrix A, the duplication matrix D_n is
> a matrix of dimension n^2 by n(n+1)/2 such that
> D_n vech(A)= c(A), where c(A) just vectorizes A.
>
> The duplication matrix is defined on page 49 of the book "Matrix
> differential calculus with applications in statistics and econometrics"
> by Magnus and Neudecker (1988 )
>
> Thanks a lot!
>
>
>
>
>
> ---------------------------------
> Ż-3.5G20M
> [[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
> and provide commented, minimal, self-contained, reproducible code.
>
>
>



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 and provide commented, minimal, self-contained, reproducible code. Received on Sun Sep 10 09:54:07 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Sun 10 Sep 2006 - 01:30:04 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.