While those questions may sound absurd, various studies have found a way to prove them true through statistical manipulation of numbers and data. The tendency of academics, politicians and pundits to generate such numerical falsehoods from data — and the tendency of the public to believe the results — is a phenomenon cleverly explored in the new book “Proofiness: The Dark Arts of Mathematical Deception,” by Charles Seife.
Mr. Seife, a writer and professor of journalism at New York University, makes a compelling case that numbers have a unique hold on the human mind, and that we are routinely bamboozled by phony data, bogus statistics and bad math. I recently spoke with Mr. Seife, whose work has appeared in The New York Times, The Economist and elsewhere, about the role that proofiness plays in health and medical research. Here’s our conversation.
Q.
What is “proofiness?”A.
It’s the mathematical analog of Stephen Colbert’s “truthiness.” It’s using numbers to prove what you know in your heart is true, even when you know it’s not. Numbers have a particular ability to fool us. It’s using that ability to turn nonsense into something that is believable with numbers.Q.
Was there any particular case or event that inspired you to dedicate an entire book to this phenomenon?A.
I’ve been gathering thread about the book since my college days. I was always a split personality, studying to be a mathematician but drawn to writing and journalism. One of the things that drove me to journalism was my annoyance at how innumerate the media seemed to be. We just don’t seem to be able to handle numbers. I wound up picking out little stories where people were deceived by numbers. I thought initially it would be a fun little book about the silly ways people’s thinking can go wrong, but it turned into something much more sinister — the idea that mathematical deception is playing a large role in the way our society was run.Q.
You write about the fact that numbers have enormous power over our thinking. Why is that?A.
From school days, we are trained to treat numbers as platonic, perfect objects. They are the closest we get to absolute truth. Two plus two always equals four. Numbers in the abstract are pure, perfect creatures. The numbers we deal with in the real world are different. They’re created by humans. And we humans are fallible. Our measurements have errors. Our research misses stuff, and we lie sometimes. The numbers we create aren’t perfect platonic ideals. They are mixed with falsehood, but we don’t recognize that.Q.
In the book you make the point that bad math can undermine both the political and judicial process. How can it affect medicine and health?A.
One of the things our minds are designed to do is pick up patterns. If you eat a bit of bad shrimp and get sick, your mind makes that association and you get an aversion to that food. We are extraordinary pattern-matchers. Anytime there is something that is happening, we try to find a cause. But sometimes in medicine, sometimes things are absolutely random. Our minds don’t accept that. We must find a cause for every effect.A really good example is the autism issue. Whenever a parent has a child who ends up being autistic, the parent more than likely says, “What caused it? How did it happen? Is there anything I could have done differently?” This is part of the reason why people have been so down on the M.M.R. vaccine, because that seems like a proximate cause. It’s something that usually happened shortly before the autism symptoms appeared. So our minds immediately leap to the fact that the vaccine causes autism, when in fact the evidence is strong that there is no link between the M.M.R. vaccine or any other vaccines and autism.
Q.
In the chapter titled “Rorschach’s Demon,” you coin the term “causuistry.” Can you explain the word?A.
Casuistry is using bogus arguments through seemingly sound principles. Causuistry is my shorthand for wrongly implying causation. The issue is that in medicine or any other field of study, it’s really easy to show that two things are linked in some manner. Something rises, something else falls. As energy consumption rises, so does life expectancy. However, it’s a fallacy to say without other evidence that one is causing the other. You can’t say building more power plants will cause us to live longer. In fact, what’s going on in this example, there is an underlying cause affecting both. The more technological a society is, the more power plants it has, the longer its people live. It’s very easy for a researcher to mistake a correlation for causation. It’s very hard to show that one thing causes the other.Q.
Can you give me another example of causuistry?A.
A number of years ago there was a study that showed the higher your credit card debt, the worse your health. The conclusion seemed to be “Don’t carry a balance on your credit card, otherwise you’ll get sick.” It’s probably just the opposite. People who are sick are running up medical bills, missing work or maybe have lost their jobs. It’s not that credit cards cause bad health. It’s that bad health causes unpaid bills on your credit card.Q.
Another word you use is “randumbness.” Can you explain it?A.
We’re hard wired to reject the idea that there’s no reason for something happening. This is how Las Vegas makes its money. You’ll have people at the craps table thinking they’re set for a winning streak because they’ve been losing. And you’ll have people who have been winning so they think they’ll keep winning. Neither is true. These events are completely random. The universe doesn’t care if you’ve been winning or losing, but our minds see these pattens we think we can exploit, and this leads us to phony beliefs.Randumbness is our stupidity about true randomness. We are unable to accept the fact that there’s not a pattern in certain things, so we project our own beliefs and patterns on data, which is pattern-free. In the journal Nature a few years ago, some researchers analyzed a number of Olympic sports and saw that people who wore red were winning more than people who wore blue. They concluded that red confers an advantage. This is nonsense. It was a random event. In the 2008 Beijing Olympics, you can analyze the same events in the same way, and you find just the opposite. People who wore blue had a statistically significant advantage over people who wore red.
Q.
One of the tools researchers use to find patterns in data is the regression analysis. Why do you call this “regression to the moon?”A.
A regression analysis is a tool for taking a set of data, a collection of points, and making sense of it with a formula. It’s a powerful technique because it allows you to present data in terms of things you think are relevant. A good example is in economics. If you think elections are affected by the inflation rate and G.D.P. and the unemployment rate, you turn all of these things into a regression model, and you come up with a formula that predicts the president based on these variables. The problem is that if your initial assumptions don’t have a basis in reality, then it’s going to come up with an answer that makes it look like there’s a connection when in fact there isn’t. This straight regression analysis assumes everything is linear, that there’s a very simple equation that relates to these variables. But the real world isn’t linear. It’s complex.
Q.
How are we harmed by “causuistry,” “randumbness” and “regression to the moon?”A.
There’s harm in bad research, and there’s harm in biased research. This is a problem the medical research community has been dealing with. We tend to think things work better or work at all when they in fact don’t. It’s undermining not just the information that doctors and consumers use, but also the scientific process in general. As people recognize that scientific studies are often not as objective and scientific as they seem, that they include biases and bad numbers, it undermines the credibility of an evidence-based medicine system.Q.
So should we be skeptical of all scientific research? Can we believe anything we read?A.
I think the biggest thing to take home is that you have the right to question research, the right to think this number doesn’t make sense. I think the best thing to do is if something doesn’t make sense to you, you’re going to learn something by examining it. Sniff it. Figure out where it’s coming from. A little degree of skepticism is usually warranted, especially when there is a number that doesn’t make sense.
No comments:
Post a Comment