s-news
[Top] [All Lists]

Re: simulate correlation matrices

To: Willi.Weber@aventis.com
Subject: Re: simulate correlation matrices
From: Giovanni Petris <GPetris@uark.edu>
Date: Tue, 26 Feb 2002 08:15:02 -0600 (CST)
Cc: vograno@arbitrade.com, ezivot@u.washington.edu, s-news@lists.biostat.wustl.edu
In-reply-to: <D63B2E2DA19A974794F1DBBCE9CFBA35168D27@frasmxsusr14.pharma.aventis.com> (Willi.Weber@aventis.com)
References: <D63B2E2DA19A974794F1DBBCE9CFBA35168D27@frasmxsusr14.pharma.aventis.com>
Reply-to: Giovanni Petris <GPetris@uark.edu>
You want t(x)%*%x, not t(x)%%x.

Giovanni

> I thought so far, that a covariance matrix is symmetric to the diagonal
> axis?
> I tried:
> x <- matrix(rnorm(5*5), ncol=5)
> > t(x)%%x
>            [,1]        [,2]        [,3]        [,4]       [,5] 
> [1,]  0.0000000 -0.15417309  0.03567755  0.61815453  1.3748462
> [2,] -0.0895276  0.00000000  0.20452335 -0.16291966 -0.6726954
> [3,] -0.4599585  0.02824674  0.00000000 -0.05002809  0.2847527
> [4,] -0.2125452 -0.73217427 -0.11275733  0.00000000  0.4920405
> [5,]  0.3828471  0.10637537 -0.07138546  0.05963281  0.0000000
> 
> I may add t(x)%%x + diag(nrow(x))*sd*sd to get a full covariance matrix, but
> would like to mirror the lower triangle matrix to the upper triangle matrix
> before calculating the correlation matrix.
> Any help?
> 
> Willi Weber, MD PhD

-- 

 __________________________________________________
[                                                  ]
[ Giovanni Petris                 GPetris@uark.edu ]
[ Department of Mathematical Sciences              ]
[ University of Arkansas - Fayetteville, AR 72701  ]
[ Ph: (501) 575-6324, 575-8630 (fax)               ]
[ http://definetti.uark.edu/~gpetris/              ]
[__________________________________________________]


<Prev in Thread] Current Thread [Next in Thread>