The Russian dictator Joseph Stalin is reputed to have said that while the death of one person is a tragedy, the death of one million is merely a statistic. Stalin was probably not the first to observe that statistics can not only enlarge our understanding of politics, but can be manipulated by disreputable politicians, or used by an educated electorate to expose their dishonesty.
This amazing discovery led me to pursue an education in the statistical sciences, and it can motivate Post readers to question news and opinion more critically. Two politically explosive case files illustrate its power: pipe bombers and Trump’s sexual scandals. In the first example, statistics exonerates alleged wrongdoing; in the second, it indicts.
A favorite professor of mine at the University of Northern Colorado was called as an expert witness to defend a suspected pipe bomber on Colorado’s Western Slope in the early 1990s during a rash of anti-government protests. The police collected bomb fragments from the crime scene, along with the suspectap tool kit, then initially concluded that he was guilty on the basis of inconclusive — and surprisingly biased — forensic analysis.
By using simple statistical techniques, my professor was able to destroy the prosecution’s case against the purported bomber without having a factually detailed knowledge of the case. I’ll explain how he accomplished this remarkable feat in a moment.
Our second illustration is more timely: Melania Trump’s public defense of her husband’s reported assaults on women. Her comments potentially raise troubling suspicions about her honesty and intuition when she claims that Trump’s emerging and disturbing portrayal as a sexual predator is not the “man she knows.”
Assuming that Trump is equally likely to be guilty or innocent in these complaints, we can demonstrate that the probability of 10 women accusing Trump of sexually inappropriate behavior on separate, unrelated occasions is less than one percent.
The expectation that Trump is completely innocent, given this consensus between women unknown to each other and separated by time and circumstance, is extremely remote. So remote, in fact, that statisticians have a name for this predicament that mandates abandoning our initial presumption of innocence: itap called “rejecting the null hypothesis.”
Now rejecting the null hypothesis sounds like a difficult procedure, but the Trade Center bombings in 2001 show that itap a very natural and intuitive way of making sense of the world. When the first plane struck, broadcasters speculated that it was an accident. After a second strike, we knew that terrorists were responsible for the tragedy, and rejected the presumption of mere happenstance (the null hypothesis).
This same reasoning applies to Trump’s liability for misconduct. The probability of guilt is mathematically overwhelming in the face of his phalanx of accusers. Even assigning a higher probability of innocence for each of 10 instances of alleged abuse makes his denials only slightly more plausible. Thatap the power of multiple accusers.
To be fair, a cautionary note applies to these thought experiments. They are not a substitute for a court of law, where proper vetting must take place. Our calculations are invalid if the stories attributed to these women are not completely independent and legally tenable (implying no collusion or ulterior motives). In other words, what if we discover an anti-Trump conspiracy of sorts that was responsible for this “October surprise”?
As they say in Las Vegas, such a turn of events would mean that all bets are off!
Oh, by the way, are you still wondering how my professor got the alleged bomber off the hook? He instructed the police to give the suspectap tools, along with four other bogus tool kits, to three independent labs. Only if all three labs identified the right tool kit could the prosecution dismiss the element of luck and confidently charge their suspect.
The labs were unable to meet this tougher standard, and so the presumption of innocence could not be overturned. Justice prevailed, thanks to the power of statistics!
Mark David Travis works for the Social Security Administration in Denver.
To send a letter to the editor about this article, submit or check out our for how to submit by e-mail or mail.
