On Thu, 12 Apr 2001 16:11:48 -0500, "Lonnie Hamm"
<[EMAIL PROTECTED]> wrote:
> Suppose I want to generate a vector of n normal deviates with the standard
> deviation the same for all elements and the covariances are zero. Since the
> covariances are zero, is there such a thing as a multivariate normal deviate
> in this case or can I just generate a univariate normal for each of the n
> components?
Both. If the covariances are 0 then the components of the vector are
independent univariate normals. Note that in general it is not true
vor every multivariate distribution that the components are
necessarily independent RVs if the covariances are 0. This is a
special property of the multivariate normal distribution.
Regards
Horst
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
