Seth’s blog

This article (”Ten statisticians and their impacts for psychologists”) impressed me. It’s a lot more accessible and basic than the usual academic article. However, my list — of the statisticians who’ve had the biggest effect on how I analyze data — is much different than his. From more to less influential:

1. John Tukey. From Exploratory Data Analysis I learned to plot my data and to transform it. A Berkeley statistics professor once told me this book wasn’t important!

2. John Chambers. Main person behind S. I use R (open-source S) all the time.

3. Ross Ihaka and Robert Gentleman. Originators of R. R is much better than S: Fewer bugs, more commands, better price.

4. William Cleveland. Inventor of loess (local regression). I use loess all the time to summarize scatterplots.

5. Ronald Fisher. I do ANOVAs.

6. William Gosset. I do t tests.

My data analysis is 90% graphs, 10% numerical summaries (e.g., means) and statistical tests (e.g., ANOVA). Whereas most statistics texts are about 1% graphs, 99% numerical summaries and statistical tests.

I try to connect my self-experimentation to other intellectual activity. One broader category is the stunning single case — the single example that makes you think new thoughts. Another is superhobbies (activities done with the freedom of hobbyists but the skills of professionals). Superhobbies lie between hobbies and skilled jobs. A third is my position as an insider/outsider. I was close enough to sleep research to understand it but far enough away to ignore all their rules about what you can and cannot do. I had the knowledge of an insider but the freedom of an outsider.

A fourth broader category is the science of everyday life — meaning science that involves everyday life and can be done by most of us. My experiments cost almost nothing, required no special equipment or circumstances. They involved common concerns (e.g., how to sleep better) and tested treatments available to everyone (e.g., standing more, eating more animal fat). A post by Mark Liberman at Language Log has a nice non-experimental example of this category. The question is about word order in gender pairs. Why do we say “boys and girls” more often than “girls and boys”? Or “husbands and wives” more often than “wives and husbands”? There are plenty of such pairs, not all with male first (e.g., “ladies and gentlemen”). The several possible explanations can be tested in lots of ways that require no fancy equipment or data. As Liberman says,

A smart high-school student could do a neat science-fair project along these general lines.

A great feature of what Liberman is proposing is that the answer isn’t obvious. There isn’t a “correct” answer as there is in so much of the way that science is taught (e.g., physics labs, demonstrations). If I searched for examples of “science of everyday life” i would merely find canned demos, which have little in common with the practice of science. Whereas Liberman’s idea gets to the heart of it, at least the hypothesis-testing part.

Thanks to Stephen Marsh.

In an earlier post I pointed out that modern molecular biology has one big feature in common with cargo-cult science (activities with the trappings but not the substance of science): relentless over-promising. David Horrobin, in a 2003 essay, agreed with me:

Those familiar with medical research funding know the disgraceful campaigns waged in the 70s and 80s by scientists hunting the genes for such diseases as cystic fibrosis. Give us the money, we’ll find the gene and then your problems will be solved was the message. The money was found, the genes were found - and then came nothing but a stunned contemplation of the complexity of the problem, which many clinicians had understood all along.

During the question period of a talk by Laurie Garrett about science writing at the UC Berkeley School of Journalism, I said there was a kind of conspiracy between scientists and journalists to make research results (in biology/health) appear more important than they really were. Oh, no, said Garrett. If she’s right, then journalists are completely credulous. They have no idea they’re being scammed. If I wrote a book called The Real Scientific Method, there would be a whole chapter on better ways (cool data) and worse ways (over-promising) to promote your work.

The discovery of leptin, the hormone that tells the brain how much fat you have, was front-page news in 1994. Supposedly this discovery would help people lose weight. It is now abundantly clear that it hasn’t and won’t. The discoverer of leptin, Jeffrey Friedman, gave a talk at UC Berkeley several years ago and resembled a deer caught in the headlights. All he knew — following the party line — was that genetics was important. That genetics was so obviously not the reason for the obesity epidemic . . . he didn’t mention. This interview gives a sampling of his views. He really does believe in the primacy of genes:

Over the years, Dr. Friedman says, he has watched the scientific data accumulate to show that body weight, in animals and humans, is not under conscious control. Body weight, he says, is genetically determined, as tightly regulated as height.

Never mind animal and human experiments that show adult body weight is controlled by recent diet. Adult height is not controlled by recent diet. What about the obesity epidemic? Well,

“Before calling it an epidemic, people really need to understand what the numbers do and don’t say,” he said.

This is what one molecular biologist — a professor at Rockefeller University — is reduced to: telling us what data collected by other people “do and don’t say”. Not to mention qualifying the obvious (Americans are much fatter now than 50 years ago). I’m sure his lab has all the trappings of modern science. But the planes don’t land.

A journalist named David Freedman has figured this out.

After I mentioned appreciative thinking in a recent post, my friend Carl Willat wrote me:

Part of Buddhism I think is that gratitude is the secret to happiness.  It’s always possible to want more, so you won’t be happy by trying to get all the things you want. Instead, being grateful for what you have is where happiness lies.

That’s a good way to put it. Not matter what article you read, no matter what study you do, there are always ways it could be better (what others call flaws). Be grateful for what the article or study tells you. That’s how to learn something from it.

Here is a statement from Hal Lewis, a physics professor at UC Santa Barbara, in answer to a question from CBS News:

I know of nobody who denies that the Earth has been warming for thousands of years without our help (and specifically since the Little Ice Age a few hundred years ago), and is most likely to continue to do so in its own sweet time. The important question is how much warming does the future hold, is it good or bad, and if bad is it too much for normal adaptation to handle. The real answer to the first is that no one knows, the real answer to the second is more likely good than bad (people and plants die from cold, not warmth), and the answer to the third is almost certainly not. And nobody doubts that CO2 in the atmosphere has been increasing for the better part of a century, but the disobedient temperature seems not to care very much. And nobody denies that CO2 is a greenhouse gas, along with other gases like water vapor, but despite the claims of those who are profiting by this craze, no one knows whether the temperature affects the CO2 or vice versa. The weight of the evidence [suggests] the former.

That’s reasonable. Here is a statement from another physicist, a friend of mine and Andrew Gelman’s:

Like a lot of scientists — I’m a physicist — I assumed the “Climategate” flap would cause a minor stir but would not prompt any doubt about the threat of global warming, at least among educated, intelligent people. The evidence for anthropogenic (that is, human-caused) global warming is strong, comes from many sources, and has been subject to much scientific scrutiny. Plenty of data are freely available. The basic principles can be understood by just about anyone, and first- and second-order calculations can be performed by any physics grad student. Given these facts, questioning the occurrence of anthropogenic global warming seems crazy. (Predicting the details is much, much more complicated). [He seems to miss the point here. The usual claim is that man-made warming is large relative to other global temperature changes. That’s not predictable “by any physics grad student” and to call it a “detail” is misleading. — Seth] And yet, I have seen discussions, articles, and blog posts from smart, educated people who seem to think that anthropogenic climate change is somehow called into question by the facts that (1) some scientists really, deeply believe that global warming skeptics are wrong in their analyses and should be shut out of the scientific discussion of global warming, and (2) one scientist may have fiddled with some of the numbers in making one of his plots. This is enough to make you skeptical of the whole scientific basis of global warming? Really?

At risk of sounding v smug, my views have changed only a little. I already thought the consensus was more fragile than it appeared. That’s just a general truth about modern science. I was already skeptical of climate models because I knew how easily modelers fool themselves. I began to believe the consensus was not just fragile but wrong when I heard the story of the Yamal tree ring data — the long refusal to supply the raw data and, when the researcher’s hand was forced and the data finally supplied, the way it contradicted the claims that had been made. Climategate didn’t vastly change what I thought; it provided more evidence for ideas I already had.

Another friend of mine used to be a math professor. He has views similar to the views of my physicist friend. “Look,” I said to him, “if you want to argue that humans are causing major global warming you should at least show it’s warmer now than in the past. Even that isn’t true. The Medieval Warm Period.” “That was only in Europe,” he replied. Actually, there is evidence of the same thing in the Gulf of Mexico.