Using the Central Limit Theorem* and a z-score table, I have computed
the probabilities of seeing average temp depatures for the specific
days of the week over the actual period Jan 1 - May 8, 2003. . For
example, we expect to see the average Wednesday departure of -.1 or
higher 15% of the time. Since 14% of days are Wednesdays, this
departure or higher not a rare thing at all. A bit rarer is the
Thursay -5.0 departure or lower, happening 10% of the time. However,
be no means is this out of the loop.

Wed -0.1 15% Probability GREATER than this departure
Sun -0.9 25% Probability GREATER than this departure
Sat -1.3 32% Probability GREATER than this departure
Mon -1.9 42% Probability GREATER than this departure
Tue -3.3 32% Probability LESS than this departure
Fri -3.6 27% Probability LESS than this departure
Thu -5.0 10% Probability LESS than this departure
AVG -2.3

On the other hand, lets say we came up with a day of the week where
the departure averaged -7.0. This would be rare, as the probability
of such a negative average departure or greater would be just 1%..
Now lets say we happened upon a -10.0 or greater negative deparure
for a given day of the week.. The probibility associated with this is
..01% or 1 out of 10,000!.

*I will not get into what this is all about. However, in a nutshell
it has to do with normal (Bell Curve) distributions, means, population
and sample standard deviations etc.

Jot - Ashland


--
This article was auto-posted by the ne.weather.moderated Weatherbot
program. The author is solely responsible for its content.

ne.weather.moderated FAQ/Charter: http://www.panix.com/~newm/faq.txt
ne.weather.moderated moderators e-mail:
(Please put "wx" or "weather" in the subject line to avoid the spam block.)