*Wall Street Journal*story Odds Lot: Statisticians Party Like It’s 2.013 x 10 Cubed, I now know our field is “sexy.”

Sure it is. At a conference last month a guy asked me what I did. I said I worked magic. He was incredulous. I said, Yes, as soon as I tell anybody what I do, they disappear. Magic.

He insisted on knowing anyway. I told him. “Oh, there’s Gary. I have to go say hi,” he said. I turned to my friend (a physicist) and said, “See? Magic.”

But I’d say that’s the second most common reaction. The first is, “I hated statistics,” meaning the person despised the class that somebody forced him to take. Now I, being a team player (right? right?), always accept responsibility and apologize for their experience. “Yes,” I admit, “It’s because we teach the subject badly.”

Most statisticians are under the impression that our subject is a branch of mathematics. An understandable mistake, but wrong. But because of this misconception we don’t feel we have taught our students anything unless we make them derive, and then memorize, a dozen or so formulas. Which, as we know, are of little value and often of great harm. We actually make them play with data *before* we say why and what it means. Strange.

The usefulness of this strategy, to any regular reader and to any who was made to suffer through a statistics class, will be obvious. Nobody ever remembers why they’re applying the formulas, nor can they recall how to derive them, but they do hold dear that wee p-values are magical.

Statistics is no more mathematical than physics. Sure, like physics statistics uses plenty of math, but it is all beside the point, not *the* point. Probability is a branch of logic, which is a branch of epistemology. Well, of course it is. We use probability to say how certain we are of things, right? And when we say how we know things, we are speaking epistemologically.

My idea is to eschew most mathematics when teaching statistics to newcomers. Speak more about what is means, how to understand, how to think. Particularly how to read and interpret evidence presented by others. Those who are intrigued—and I claim this will be a larger proportion than the old way—will stick around and learn the math.

Which, it must be admitted, isn’t easy. A minimum of calculus (a year or so) is required; having analysis is better. That’s a long haul. But then we don’t require the majority to derive results, prove theorems; we instead would like civilians to know when the wool is being pulled over their eyes.

If this panics you, don’t worry. My ideas are considered so outré that I am not trusted to be put in front of students (except for a handful two weeks a year). The old ways will continue.

From the article we learn that others have the same experiences Yours Truly does. Ron Wasserstein, a statistician, “recalls telling people back [in the 70s] about his studies and getting puzzled responses like, ‘Are there really enough numbers to memorize to get a Ph.D. in statistics?'”

Geert Molenberghs, a biostatistics professor at Belgium’s Hasselt University who helped organize the recent Belgian conference, says telling people at a cocktail party that he is a medical statistician sparks more interest than it would if he dropped the medical part.

Magic!

Categories: Statistics

And here I thought only physicists got this reaction. The best comment, as usual, is from Feynman:

“In physics,” I said.

“Oh. Well, nobody knows anything about that, so I guess we can’t talk about it.”

“On the contrary,” I answered. “It’s because somebody knows something about it that we can’t talk about physics. It’s the things that nobody knows anything about that we can discuss. We can talk about the weather; we can talk about social problems; we can talk about psychology; we can talk about international finance–gold transfers we can’t talk about, because those are understood– so it’s the subject that nobody knows anything about that we can all talk about!”

I don’t know how they do it. There’s a way of forming ice on the surface of the face, and she did it! She turned to talk to somebody else.

As to the linked article, the statistician quoted should be careful what he wishes for. As surely as night follows day popularity will destroy a field, but maybe it is already too late for statistics.

Weâ€™re 88% Through The International Year Of StatisticsFunny. I got 89.3%. There must be a tad more to it than I thought.

I said, Yes, as soon as I tell anybody what I do, they disappear. Magic.Well then, here’s a project for study: would they be less inclined to vanish if you told them you were a janitor or a busboy? The same thing happens elsewhere. Certain professions seem to inherently instill feelings of inferiority. Some likely hear “I am a statistician” as “I am Sheldon Cooper.”

Re: The Standard Way Statistics Is Taught. Students are generally provided with a dataset, courtesy of the textbook publisher or one that prof. has in his files. In both cases, from the student’s perspective, these are contrived. The data is clean; no entry errors; no missing data. Just submit the data to your favorite boxed program, and ta-da, instant results. The student does not gain an appreciation of the data, and what an enormous task it is to get to the point where analysis can begin in earnest.

Katie,

Amen, sister. This is why I make my students gather their own data. So that they can see how weak their conclusions really are.

John Tukey, in his “Sunset Salvo”, _The American Statistician_, Vol. 40, No. 1. (Feb., 1986), pp. 72-76:

“A diner in a restaurant can use a guide to gastronomy, but either a cookbook or an advanced course in cooking techniques would interfere with, rather than help, his enjoyment.”

I also remember Tukey saying, during his talk of the same title, that our students mostly need to learn gastronomy, but we mainly teach them cooking.

See also Tukey’s comments on our need for Antihubrisines.