On 6/30/07, John Randall <[EMAIL PROTECTED]> wrote:
Lots of stuff, starting with:

The standard terminology covers all these cases, although there are
some ambiguities.  First note that a sample space is just a set of
outcomes: is is different from a sample, which is a list of random
variables.

First off, I should note that your terminology as you have outlined
it here seems entirely consistent, though there are a few subtleties
(such as, in this quoted paragraph, the distinction between sample
space (which roughly corresponds to a result of the dyad /:[EMAIL PROTECTED])
and sample (which roughly corresponds to a result of the dyad [EMAIL 
PROTECTED])).

Anyways, thanks for spelling this out.  I'm going to have to review it
a few times to make sure I've digested it all.

However, I believe you are using the words sample and sampling in a
nonstandard sense.  Here's what I think you are doing.

You have a known population distribution f.  You now take a vector v
of length n in which x appears c(x) times, with the property that
c(x)/n is approximately f(x).  You regard this as a set of
equiprobable outcomes, and so determines a population with
distribution g satisfying g(x)=c(x)/n.  This population has

\mu=\sum x g(x)=(1/n)\sum x c(x)

\sigma^2=\sum (x-\mu)^2 g(x)=(1/n)\sum (x-\mu)^2 c(x).

So in this case using a denominator of 1/n makes sense.  However, this
is not the sample variance in any normally accepted sense: there is no
sample in sight.  There are n equiprobable outcomes defining a random
variable X with P(X=x)=c(x)/n.

Let me know if this is what you are getting it.

Yes, although I was not originally aware of the distinction between
sample variance and population variance.  (Or, at least, I had long
since forgotten about that distinction.)

Now that I have become acquainted with this distinction, I would classify
this mechanism  as describing population variance and not sample
variance.

I should probably also mention that the artifice you characterize as
f(x) = c(x)/n is just one of several approaches which I have been
considering -- I focused on it because it seemed computationally
simple.

Anyways, I think you've given me a decent set of tools for talking
about populations, sampling and individual samples.

Thanks,

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

Reply via email to