Bad Science by Ben Goldacre Read Free Book Online Page B

feels like a more dramatic intervention. We know that the color of pills, their packaging, how much you pay for them, and even the beliefs of the people handing the pills over are all important factors. We know that placebo operations can be effective for knee pain and even for chest pain. The placebo effect works on animals and children. It is highly potent, and very sneaky, and you won’t know the half of it until you read the placebo chapter in this book.
    So when our homeopathy fan says that homeopathic treatment makes them feel better, we might reply: “I accept that, but perhaps your improvement is because of the placebo effect,” and they cannot answer no, because they have no possible way of knowing whether they got better through the placebo effect or not. They cannot tell. The most they can do is restate, in response to your query, their original statement: “All I know is, I feel as if it works. I get better when I take homeopathy.”
    Next, you might say: “OK, I accept that, but perhaps, also, you feel you’re getting better because of ‘regression to the mean.’” This is just one of the many “cognitive illusions” described in this book, the basic flaws in our reasoning apparatus that lead us to see patterns and connections in the world around us, when closer inspection reveals that in fact, there are none.
    “Regression to the mean” is basically another phrase for the phenomenon whereby, as alternative therapists like to say, all things have a natural cycle. Let’s say you have back pain. It comes and goes. You have good days and bad days, good weeks and bad weeks. When it’s at its very worst, it’s going to get better, because that’s the way things are with your back pain.
    Similarly, many illnesses have what is called a natural history: they are bad, and then they get better. As Voltaire said, “The art of medicine consists in amusing the patient while nature cures the disease.” Let’s say you have a cold. It’s going to get better after a few days, but at the moment you feel miserable. It’s quite natural that when your symptoms are at their very worst, you will do things to try to get better. You might take a homeopathic remedy. You might sacrifice a goat and dangle its entrails around your neck. You might bully your physician into giving you antibiotics. (I’ve listed these in order of increasing ridiculousness.)
    Then, when you get better—as you surely will from a cold—you will naturally assume that whatever you did when your symptoms were at their worst must be the reason for your recovery. Post hoc, ergo propter hoc , and all that. Every time you get a cold from now on, you’ll be back at your physician, hassling her for antibiotics, and she’ll be saying, “Look, I don’t think this is a very good idea,” but you’ll insist, because they worked last time, and community antibiotic resistance will increase, and ultimately old ladies die from multiple-drug-resistant bacteria, because of this kind of irrationality, but that’s another story. 6
    You can look at regression to the mean more mathematically, if you prefer. On Card Sharks , when the host puts a three on the board, the audience all shout, “Higher!” because they know the odds are that the next card is going to be higher than a three. “Do you want to go higher or lower than a jack? Higher? Higher?” “Lower!”
    An even more extreme version of regression to the mean is what is known as the Sports Illustrated jinx. Whenever a sportsman appears on the cover of Sports Illustrated , goes the story, he is soon to fall from grace. But to get on the cover of the magazine, you have to be at the absolute top of your game, one of the best sportsmen in the world, and to be the best in that week, you’re probably also having an unusual run of luck. Luck, or “noise,” generally passes; it “regresses to the mean” by itself, as happens with throws of a die. If you fail to understand that, you start looking