identifying a stats formula

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

identifying a stats formula
Message posted by Robert Dennys on November 23, 2000 at 12:00 AM (ET)

I'm hoping someone can help me identify what a formula in a poorly documented statistical computer program was supposed to calculate, presuming it is a commonly used statistic.

The formula appeared as

( ( C_MAX - C_AVG ) / C_AVG )
+( C_AVG - C_MIN ) / C_AVG )
and was compared with a critrial value of 0.15.

Any ideas?

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

Re: identifying a stats formula
Message posted by Phil on November 23, 2000 at 12:00 AM (ET)

It looks to me like some form of the coefficient of variation, using the range. I don't recognize it as having any specific use in the world of statistics. Many people dislike ratios of variation over the mean.

I could be some form of home-made signal-to-noise ratio (ala Taguchi).

Maybe some else has something more enlightening to say.

Re: identifying a stats formula
Message posted by Darius on November 24, 2000 at 12:00 AM (ET)

I don愒 recognize the formula but in a mathematical way:

(A-B)/B+(B-C)/B
=>(A-B+B-C)/B=(A-C)/B

So: (C_MAX-C_MIN)/C_AVG

==> Range/Mean

It looks strange, are you sure the equation is right?.

Your $5 contribution helps cover part the $500 annual cost of keeping this site online.