October 1, 2016 by Shawn Smith
Here’s a fact of life as comforting as it is troubling: most everything regresses to the mean. The good news: every sweltering day will eventually be followed by a cooler one. The bad news: every eight-year-old with a stratospheric IQ will be closer to average by the time they’re 10. Numbers are so beautiful and so heartless. Here are five (5) stories on the subject. No more, no less.
1. There’s a Good Chance You’re Bad at Probabilities
People struggle to comprehend probabilities. This story has some interesting thoughts on why we overestimate our own prescience. So your Aunt Mable had a premonition about someone dying? And then someone actually died!? According to numbers, we should be surprised if she didn’t predict it.
“Sociologists tell us that each of us knows about 150 people fairly well, thus producing a social-network grid of 45 billion personal relationship connections. With an annual death rate of 2.4 million Americans, it is inevitable that some of those 54.7 billion [premonitions] will be about some of these 2.4 million deaths among the 300 million Americans and their 45 billion relationship connections.”
2. Remember that “Opposites Attract” Business? Well…
That first story mentioned confirmation bias. So does this one. (I just knew it would!) Part of the reason we’re rather daft with large numerical trends is that we limit our own datasets by connecting with people who are similar to ourselves. “…the quest for similarity in friends could result in a lack of exposure to other ideas, values and perspectives.”
3. Twice a Small Number Is Still a Small Number
David Spiegelhalter doesn’t suffer fools or their poorly conceived graphs. He has a few thoughts on realistic representation of numerical data. For example:
“The probability of winning the UK [lottery] jackpot is about 1 in 45 million. The way to illustrate that is: Think about a big bath, fill it to the brim with rice. That’s about 45 million grains of rice. Then take one grain of rice, paint it gold, and bury it somewhere in there. Then you ask people to pay £2 to put their hand in and pull out that golden grain of rice.”
4. Hey Science, What’s In Your Drawers?
The “file drawer problem” refers to the fact that most studies remain unpublished. The majority of data—especially negative or null findings—remain hidden from the public and from other researchers. These particular researchers, who focus on “the love hormone,” have decided to expose what’s in their drawers. Let’s hope all scientists start exposing themselves.
5. We Need a Smaller Hammer
This story fits loosely under the category of how we think about numbers and quantities. Patients can often benefit from taking fewer medications, but doctors rarely deintensify treatment. The article says doctors are hesitant to do so because they lack the clinical guidelines for deintensification and they fear patient dissatisfaction. (I wish our system didn’t encourage informed doctors to fear offending uninformed patients.) I think there’s a simple psychology at play. One that also explains why we rarely eliminate outmoded laws or the junk in our garages: Humans like more more than we like less.
Finally, do you know why they didn’t serve beer at the statistician’s birthday party? Because you shouldn’t drink and derive. Until next time…