Correlation Does Not Mean Causation
This was a phrase that was quite popular as a Marketing Major at Berry College. Basically in our Marketing Research classes we would “do a study” to try to figure out/solve a problem or question. We always had to be aware that just because two data sets had correlation (when something happened, something else also happened), that didn’t mean they were the reason for causing change.
At Chick-fil-A this is something I think about quite a bit… probably more than I should. Team members and store leaders are always trying to “figure out” what causes certain increases/changes in productivity, sales or store metrics.
For example, our store leadership team has put an extreme emphasis on raising our Operational Excellence (OE) score this year. The OE Score basically is the number of customers that take a survey that rate us as “excellent” in every category we’re judged on… it’s very hard to get this score raised.
We changed the time we did our stock list and our OE score jumped up. One of the first changes to “fix” OE was doing the stock list later in the evening because it will allow someone extra to be in the front counter area and serving guests. I thought this was a great idea, but the more I think about it becomes apparent that “doing a stock list at a different time,” does not affect our OE score directly. I’ve had co-workers tell me we can’t change that ‘stock list time’ because “our scores have risen since we made that change.” It’s the total store re-focus that our leadership team has embraced that has increased our OE scores for the year… not stocking at a certain time.
Another example is that the drive-thru’s speed of service is slower when it is raining outside. This is easily a false statement. When it is raining the drive-thru is much busier because customers do not want to get out of their car/get wet. The increased traffic in the drive-thru causes more custom orders and applies more pressure to the drive-thru bottleneck (the window). You see it’s not the rain that causes the drive-thru to be slower, but human nature to avoid getting wet that causes the drive-thru to be busier. A busier drive-thru causes more custom orders that can only go out at one location (the window/bottleneck).
To quote Wikipedia…
“Correlation does not imply causation” (related to “ignoring a common cause” and questionable cause) is a phrase used in science and statistics to emphasize that correlation between two variables does not automatically imply that one causes the other (though correlation is necessary for linear causation in the absence of any third and countervailing causative variable, and can indicate possible causes or areas for further investigation; in other words, correlation is a hint).
(Source: http://en.wikipedia.org/wiki/Correlation_does_not_imply_causation)
So, do I over analyze my life? Yes, probably. But I think that it is very important for leaders to Reinvent Continuously and studying correlation/causation will allow you to make better decisions that affect results.
What examples do you have of Correlation/Causation in your life/work?
