Jim,

Yes, you can calculate what are known as "control limits" to determine if a point falls, statistically, either above or below what the normal distribution of the data is. The limits are placed on either side of a center line, which represents the average of the data. When data points fall outside the limits, they are considered to be "special causes". These control limits are plus or minus 3 standard deviations from the center line.

That's about the extent of my knowledge in this area. We use a program called StatPack from SQC Systems that does all the calculations for us and produces charts. We simply add data by hand or through "real time" monitoring equipment. I'm certainly no statistician and know absolutely nothing about horses, but data is data and I think the same statistical rules apply no matter how it's generated.

I am curious as to why one foal would bring 200k and the next only 10k?? Does it have something to do with who the father is?



>Greg,
>
>It happens frequently that we will sell one foal for $200,000 plus and the next one for $10,000.
>
>At what point do you categorize a single sale price as shewed and therefore a "special cause" or "out of control". Is there a formula to help determine this?
>
>It looks like we need to do all the available comparisons and then try to decide which ones apply to the goal we want to achieve.
>
>We kind of get a "feel" whether a mare is a successful producer, and if there's a number that we can come up with that closely coincides with that "feeling" then maybe it can be used to help make the decision quicker.
>
>Jim
>
>
>
>
>
>>You should probably also take a look at the variance and standard deviation of those numbers as well. The variance is the standard deviation squared. The smaller the variance, the less the values vary from the average. The standard deviation measures the degree to which the values differ from the average of all the values. The smaller the standard deviation, the less the values vary from the average.
>>
>>In your original example the number 10 price, $250,000, really skews the average. Statistically it would be considered an "special cause" or "out of control" point. If you take it out the average of the 9 remaining numbers more closely approximates the median, if I'm remembering the example correctly.
>>
>>