On 4 Apr 2003, Tim Witort wrote in part: > dennis roberts seemed to utter in ... > > > but, i will bet you a dime to a donut that the REAL interest in the > > case being originally posed is ... what evidence do we have that there > > is a CURRENT DIFFERENCE in salaries ... sufficiently large that we need > > to do something about it with THESE employees ... or else they are > > going to take us to court and sue the dickens out of us > > You are correct. > > > this sort of issue has to do with current payroll employees and whether > > you are compensating them ... males and females doing the same sorts of > > jobs ... fairly > > Exactly.
If "fairness" is an issue, you may find informative (I'm not sure you'll find it helpful, which is another thing altogether!) an article of Richard B. Darlington's in the Journal of Educational Measurement about 1971 (I think: say 1969 +/- 3). At the time there was a lot of discussion about how to make paper-and-pencil tests "fair" to different populations with apparently different aptitudes for tests. Dick lifted four definitions of "fair" from the then-current discussions in assorted journals; these were definitions that on the surface, if you read the English sentences with reasonable attention, seemed to be at least approximately synonymous. He then translated each of them into quantitative form involving certain correlation coefficients, and showed that (so far from being synonymous) the four definitions called for behavior of one correlation coefficient in terms of another (sorry, the technical details are not in my memory and I haven't convenient access to JEM at this time), the several regimes corresponding to "fair", each represented by a line in a two-dimensional space, intersected in at most one point and were otherwise incompatible. He concluded that it was not possible to construct an instrument that was "fair" according to all four definitions, and about the best one could do was to decide, in any given context, what kind(s) of "unfairness" one was willing to live with. Or, to put it more succinctly, "fair" is not a well-defined concept. This will probably not be a whole lot of help in your immediate problem, but the background may be useful in other conversations sometime. ----------------------------------------------------------------------- Donald F. Burrill [EMAIL PROTECTED] 56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
