* Taking the opportunity to share some of the more popular outtakes from the eight years of Compensation Force archives. Today's featured post - a nod to my fellow pay gear-heads but also a discourse on a consequential market compensation analysis choice - was first published in February of 2010.*

This question is the true test of compensation geekdom. The real geeks just sat forward in their chairs in eager anticipation of a meaty statistics debate. Everyone else either felt their eyes begin to glaze over, or ran for the hills.

A recent exchange with fellow Minnesota blogger Lisa Rosendahl reminded me that it's been a few years since I tackled this topic, so here it comes once again.

Pay surveys present us with a variety of *descriptic statistics* to choose from in our efforts to review or develop new compensation structures and practices. Since most of us are seeking information on the middle of the market, we are typically presented with a choice between the following two measures of central tendency:

Mean- the mathematical average, calculated by adding up all the pay rates in the data set and then dividing by the number of pay rates in the data set.

Median- the value of the pay rate that falls in the middle of all the rates in an ordered data set (that is to say, a data set which is ordered from lowest to highest rate).

(The other measure of central tendency, which rarely if ever shows up in compensation surveys, is the **mode**, or the pay rate which occurs most often in the data set.)

I have a strong preference for the median over the mean. And I found a great explanation of my preference in an old Psychology textbook (Psychology, the 8th Edition, by David G. Myers, Worth Publishers):

With income distribution, the mode, median, and mean often tell very different stories. This happens because the mean is biased by a few extreme scores. When Microsoft Chairman Bill Gates sits down in an intimate cafe, its average (mean) patron instantly becomes a billionaire.

In other words, the mean pay rate in a pay survey will be affected by any extreme pay rates in the data set, where the median will not. For this reason, I believe the median (where it is offered; some surveys only provide the mean) is a better and more reliable measure to use in pay program assessment and design.

Hit me with dissenting opinions!

*Image "Pie Chart Shows Business Graph And Charting" courtesy of Stuart Miles at FreeDigitalPhotos.net*

I am no statistician, but have come to understand from the experts that the median is a more 'stable' and preferred measure relative to the mean. No dissenting view here.

In the matter of the mode, it seems to me that too many organizations make reference to what 'most others' are doing, some suggesting that a modal stance of sorts is the 'safe' basis of their choices / proposals. In that regard they appear to be suggesting that the mode is reported. I am yet to see the modal statistics reported in well-known salary surveys (there are just too many surveys out there -- a thousand plus from WorldatWork alone --- for me to be absolute about this), although modal ‘practices’ may be discerned in some surveys.

We know that the herd instinct brings up the question (from bosses, boards, and others): what are most others doing? And the question forces some (or many) to present data and practices as being what 'most others' are doing. The question then is: Where someone reports that some statistic or pay level as what 'most others' are doing / paying, are they choosing the mean or median or other statistic as basis for their suggestion?

Posted by: E. K. Torkornoo | January 16, 2016 at 10:50 AM

If "median-based" stats are available, I would be shocked if someone is using the average (for the reasons that you outlined above).

Posted by: Robert Edward Cenek | January 16, 2016 at 11:26 AM

E.K. -

That has been my personal experience as well - that tracking and setting pay practices against the mean will typically produce a bumpier ride, more zigs and zags than using the (typically) more stable mean.

Excellent broader point about the mode. Although it rarely shows up in surveys of pay rates, it does dominate discussion about (and research on) pay practices - appealing to our instincts to flee to the middle of the herd (which only appears to be safer...)

Thanks for the thoughtful comments.

Robert -

I once had a colleague in the consulting field(now retired) who insisted on using the mean for the very reasons that most of us avoid it. He believed it important that his data set and data-based decisions reflected the outliers and the extremes in the data set.

While I appreciated his position, in the end we did agree to disagree.

I think there are survey users who continue to rely on the mean - some because they don't have a sound understanding of statistics but a few (like my colleague) who understand quite well and knowingly choose a different indicator than most.

Appreciate the comment

Posted by: Ann Bares | January 16, 2016 at 01:09 PM