At 4:42 PM -0500 5/1/07, Richard Lynch wrote:
Little help here?
Richard:
Let me estate the problem. From your dB of things (the population),
you're going to pull out the top 100 most popular items and then
divide them into five groups using labels t1 through t5. Considering
that it's css guy asking for this, he's probably making a "tag
cloud". They are kind of neat, you can look it up.
In any event, any population can be measured by it's distribution
about it's mean (i.e., the average of the population).
Some distributions are gathered close to the mean while others are
spread out from the mean. The measurement we use to describe this
dispersion from the mean is standard deviation.
In your problem, I believe by using the standard deviation as a
measure, you can break your population into divisions based how many
fall with the first standard deviation, the second standard
deviation, the third standard deviation, and so on.
Here's a demo I prepared for you:
http://sperling.com/a/stdev.php
It shows a simple population and it's standard deviation. From there
you should be able see how you can use the standard deviation to do
your divisions. I would be interested in reviewing your solution.
Cheers,
tedd
--
-------
http://sperling.com http://ancientstones.com http://earthstones.com
--
PHP General Mailing List (http://www.php.net/)
To unsubscribe, visit: http://www.php.net/unsub.php
