Long-time readers may recall our spring blog post, “On Skittles and Financial Fortune,” in which we announced an in-house Skittles-counting contest to test the market theory on group intelligence. Results are in! Most of the guesses (55 of 62) were cast in our Connecticut office, on a jar of 830 Skittles. Their average was 1,205.
This isn’t quite as close as we’d hoped for, but real life will sometimes throw curve balls without necessarily striking out the underlying theory.
- If we disregard two wildly high guesses of 8,800 and 10,000 (the “outliers” in statistical analysis) the average drops to a much closer 902, with a still-wide range of guesses from a low of 225 to a high of 3,415.
- Also of significance, only three individual guesses were closer to being correct than the 902 group average.
- Drop out the 3,415 nearly outlying guess, and the group gets even smarter, with an average of 855 and only two individuals guessing more closely than that.
To recap, our mini-experiment did a good, if not perfect job of demonstrating group intelligence. In fact, we ended up illustrating another important aspect of academic inquiry. In a Fortune article, “The best advice I ever got,” University of Chicago Professor and Nobel Laureate Eugene F. Fama observed: “You should use market data to understand markets better, not to say this or that hypothesis is literally true or false. No model is ever strictly true. The real criterion should be: Do I know more about markets when I’m finished than I did when I started?”
On that count, we can affirm that the power of group intelligence for determining market pricing – and for counting candy – seems very much alive and well.