skewed data curve
Message posted by Jeanette (via 12.27.228.66) on October 25, 2001 at 7:25 PM (ET)

I work at a company that sponsors an incentive program depending on the average number of invoices we send to a customer during a new project. The goal is to have 2, but the threshold is 9. we sometimes have trouble during the new project and end up with more than 9, but most of the time, it is within the range of 2-9. There was one new project that generated 22 invoices. Unfortunately, they used this data, even though it was WAY OUT THERE compared to all others. My question is this: Isn't there something that has to do with skewed results that I could submit to my boss in order to get them to stop taking the average of all and drop off the lowest and the highest figure????? If I can prove there is something to this, I can get the measure changed in my incentive program, and ultimately make more money.... any help would be greatly appreciated.

READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: skewed data curve
Message posted by Darius (via 200.23.217.10) on October 26, 2001 at 11:42 AM (ET)

there are links to Grubbs

http://www.graphpad.com/Calculators/Grubbs1.cfm

or

http://www.itl.nist.gov/div898/handbook/eda/section3/eda35h.htm