Measurement and disestimation


In his book Proofiness: How You’re Being Fooled by the Numbers, Charles Seife coined the term disestimation, defining it as “the act of taking a number too literally, understating or ignoring the uncertainties that surround it. Disestimation imbues a number with more precision that it deserves, dressing a measurement up as absolute fact instead of presenting it as the error-prone estimate that it really is.”

Are you running a fever?

You know, for example, that normal body temperature is 98.6 degrees Fahrenheit (37 degrees Celsius). Using the apparent precision of that measurement standard, if you take your temperature and it exceeds 98.6 degrees, you assume you have a fever. But have you ever wondered where that measurement standard came from?

Carl Wunderlich, a German physician who conducted research on body temperature in the late 1860s, claimed to have measured the body temperature of a million people to conclude normal was 37 degrees Celsius—a nice round number in the temperature scale used by most of the world. And it’s a number that sounds even more wonderfully precise when converted into Fahrenheit to yield 98.6 degrees.

Beyond it sounding dubious that Wunderlich really measured a million people, his precision also smells funny since he took his subjects’ body temperature in their armpits. Even if 98.6 degrees is normal for armpits, it would not match body temperatures taken from the mouth or other orifices since body temperature is not uniform—it varies depending on where you take the measurement.

98.6 degrees Fuzzy

“This is a huge source of error,” Seife explained, “that most people don’t take into account. Neither do they seem to compensate for the fact that body temperatures can change dramatically throughout the day, and that normal is very different from person to person. There is no hard-and-fast definition of normal, much less one that’s precise to within a tenth of a degree as the 98.6° F number seems to be. Yet it’s a fiction that we still cling to—even medical dictionaries sometimes define a fever as a body temperature above 98.6° F. We all imbue the highly precise number with tremendous importance, even though in truth the definition of normal body temperature is imprecise, fuzzy and somewhat arbitrary. It’s a disestimation, yet one that’s persisted for a century and a half.”

Don’t dis your decisions with disestimations

Data-driven organizations take many measurements, many of which are displayed in dashboards and reports, imbuing these numbers with tremendous importance since they impact business decisions. In previous posts, I explained how measuring is intrinsically fuzzy and what is being measured is intrinsically fuzzy. Nonetheless, we use measurements as if they were not fuzzy, but fact.

Just as you may not have a fever despite a body temperature of 99° F, you may not be making a fact-based decision despite a 99 percent certainty about your measurements.


About Author

Jim Harris

Blogger-in-Chief at Obsessive-Compulsive Data Quality (OCDQ)

Jim Harris is a recognized data quality thought leader with 25 years of enterprise data management industry experience. Jim is an independent consultant, speaker, and freelance writer. Jim is the Blogger-in-Chief at Obsessive-Compulsive Data Quality, an independent blog offering a vendor-neutral perspective on data quality and its related disciplines, including data governance, master data management, and business intelligence.

Leave A Reply

Back to Top