Slow Down, Cowboy! How BI/Analytics Users can Avoid the Texas Sharpshooter Fallacy

It is better to know nothing than to know what ain’t so.  Josh Billings

A Texas cowboy fires several rounds at a barn. Looking at the holes riddled across the barn wall, he observes there happens to be some holes clustered together. He excitedly paints a bulls-eye centered over the biggest cluster of holes and proudly shows it off as proof he is a sharpshooter.



This old joke is the namesake for a type of logical fallacy known as the Texas Sharpshooter: to cherry-pick clusters of information, be it bullet holes or data, to support one’s own personal agenda.

Examples of the Texas Sharpshooter fallacy can be seen in public health investigations, politics (a politician might accuse an opponent of a “pattern” of poor actions), and pseudosciences like “intelligent design.”

I especially like author David McRaney’s description: “If hindsight bias and confirmation bias had a baby, it would be the Texas Sharpshooter Fallacy.”

But a Texas Sharpshooter fallacy can also be the result of the mistaken assignment of meaning to what is in fact a small subset of all related data. It then occurred to me: virtually every business intelligence tool has a feature to highlight a portion of a graph to focus only on a particular data cluster, enabling every BI end-user to “draw a bulls-eye” of their own! The risk of jumping to false conclusions based on such selective data selection can be very high.

So how can business intelligence users avoid unwittingly creating their own Texas Sharpshooter fallacies, and help debunk those put forth by others in the organization?

The problem occurs when a BI end-user draws a conclusion that is based on that isolated data cluster. Suppose a sales manager using a BI tool highlights a cluster of data points, all with a noticeably low gross margin compared to the other monthly sales. The sales manager then sees that those ten data points – all sales with low gross margins – are all deals closed by Joe Bloggs.

Is Joe Bloggs giving away pricing concessions to customers? Well, if the sales manager has poor analytical, managerial and/or interpersonal skills, or even just doesn’t like Joe, this data cluster may be all the “proof” (s)he needs to “have a word” with Joe, subvert Joe’s efforts by grousing over his lousy dealmaking skills with others in the hall… you get the picture. Again quoting David McRaney, “You commit the Texas Sharpshooter Fallacy when you need a pattern to provide meaning, to console you, to lay blame.”

Of course, the sales manager does not have “proof” Joe Bloggs is “giving away margin” any more than that cluster of bullet holes is “proof” the cowboy is a sharpshooter. What the sales manager does have is a hypothesis – defined succinctly by Wikipedia as “a proposed (repeat, proposed) explanation for an observable phenomenon.” That data cluster of low margin sales should be the beginning of the sales manager’s line of inquiry, not the conclusion.

A wise user of business intelligence tools will proceed like a scientific researcher, who will begin with a hypothesis and then try to disprove it. Here are two suggestions to do so effectively:

  • Use the word ALL a lot. Seriously, asking new questions of the data with liberal use of the word “all” is wise; for example, how do Joe Bloggs’ ten low margin sales compare with “all” of his deals for the month (both in terms of currency and quantity); “all” sales of the same products by “all” sales reps; “all” sales to those customer(s), etc. Thinking and asking questions of the data in terms of “all” will effectively erase the cowboy’s bulls-eye target, so to speak, by focusing on relevant data in its entirety and not the original data cluster in isolation, which may well prove statistically insignificant in light of “all” related data.
  • The longer time series of data you can utilize in your line of inquiry, the better. Here’s a real world example: A college finance and budget department recognized a common assumption among faculty that administrative spending was out of control, leaving faculty to fight for whatever was left. The budget and reporting director produced a trending analysis that convincingly proved that growth rates in spending were the same between faculty and administration… over the last 15 years! This diminished the conventional wisdom and led to fact-focused planning and prioritization discussions and enhanced trust and communication between departments. (Of course, a cherry-picked subset of the data would no doubt have yielded “proof” of disproportionate growth in administrative spending).

If a co-worker makes an assertion based on some isolated data set, ask whether their assertion is supported by the entire spectrum of related data.

One final thought: A highly effective business intelligence implementation will make it very easy for the end-user to compare a data cluster with “all” related data and readily observe the significance, if any, of a selected data cluster. Now there’s some real data sharpshooting!

If you liked this post, you may also like:

Business Users Can Learn a Lot from Data Scientists

For Success, Grit Beats Intelligence! Or: Use Business Intelligence Software to Achieve Grit Goals

Business Intelligence is a Diagnostic Tool, but is the “Patient” Willing to Listen?

Poor Communication can Scuttle Effective BI, Your Reputation, and a Simple Bus Ride

Several years ago I flew to and from a trade show via TF Green Airport in Providence, RI instead of Boston Logan Airport as usual.  This small airport has (or at least had at the time) one large economy parking lot with shuttle buses.

Remember Ralph Kramden? The bus driver I dealt with was the Anti-Kramden.

You were supposed to give the bus driver the number of your bus stop near your car.  Running late, I rushed to catch my departing flight and didn’t make note of the number, but I knew I had parked near a certain corner of the lot.

“Excuse me,” I said to the bus driver, “but I don’t have my bus stop number. Can you just drop me off at whatever stop is nearest to the far right corner of the lot?”

“What’s the number?” grunted the bus driver.

“I don’t have the number.  But I know my car is near the far right corner of the lot from where we are right now.”

“What’s the number?” the driver again grunted, a little louder this time.

(What…?!) “I said I don’t have the number. I’m near that corner of the lot over to your right.”

“What’s the number?”

(Is this guy for real?!) “Look, can you just stop anywhere near the far corner of the lot?”

One of my colleagues from the trade show, a TF Green regular and just as annoyed with the driver as I was, shouted out a stop number he happened to know was close to my car. The bus driver, now given “The Number,” did silently agree to stop there, his eyes forward as I walked off the bus. Note that there was no language, cultural or hearing-ability issue with the driver. He was simply locked into his own way of thinking to a ridiculous degree: no stop number, no stop.

The way a person communicates is a major component of their reputation and personal brand.  And I believe the vast majority of communication problems are caused by the personal baggage we bring to the table when communicating, known in psychological terms as confirmation bias.   Continue reading