On Tue, Dec 12, 2000 at 09:52:19AM -0600, Donald J Bindner wrote:
> It is incorrect, but the spirit is right, since you don't get
> your assignment until you reach the end of the queue. When
> applicants see the "average", they expect that it is a measure of
> how long they should expect to wait. I know; I was recently in
> the queue.
I've changed things around now so the times are a sample of what has
happened in the past two months. This means you still have some
things that can go wrong but at least it will tell people what they
can expect if the last two months is similar to what will happen now.
Also the average has been removed and is now replaced by a median.
This was needed as we often have a very small number of people who
take a long time, making mean a little unrealistic.
> I teach statistics, and I had the wrong impression. I should
> think someone who doesn't teach math at university has even less
> of a chance. There ought to be some way to improve this.
I hope this gives better and more accurate numbers. If someone can
suggest a better set of calculations then I will be happy to hear
about them. The only restriction is it has to be able to be phrased in
SQL, though this is pretty flexible and I can do the phrasing. The
median function is two SQL calls.
Craig Small VK2XLZ GnuPG:1C1B D893 1418 2AF4 45EE 95CB C76C E5AC 12CA DFA5
Eye-Net Consulting http://www.eye-net.com.au/ <email@example.com>
MIEEE <firstname.lastname@example.org> Debian developer <email@example.com>