Kip,

You are focusing on a key point here, imo.
After all typically the argument to 6!:2 is not a SRS in the sense
that the data being processed is changing, because the data is not
changing. What is changing is the processor environment which is a
sequential process, not a random process, at least to the extent that
the left argument of 6!:2 is the "sample size". And sequential samples
are notoriously non-random in many situations.

So, maybe Mike Day and others who mentioned how fine variations are
not important, and Devon who mentioned using other processors and
other sample sizes need to be listened to much more than statistical
mavens.

On Fri, Oct 21, 2011 at 10:57 AM, Kip Murray <[email protected]> wrote:

[snip]

> It is a matter of judgment whether those ten executions would qualify as a
> simple random sample.  At first glance they appear to be a special kind of
> sample in which the ten executions are very close together in time.  (I am
> ducking the question of what population the sample is chosen from.)
>
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to