On Tue, Feb 23, 2010 at 5:54 PM, Dan Bron <[email protected]> wrote:
> I'd be interested in learning which applications have such
> appetites for random numbers that this period is too short for them (and
> do they really run models over the course of a month?).

Perhaps the issue is that the series can be predicted?

If someone obtained samples from a million different
spots in the cycle, evenly spaced, and each sample
was 100 sequential elements, how long could a
sequence run before becoming predictable?

-- 
Raul
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to