Author: Seth Roberts

Buried Treasure (part 2)

Seth Roberts4 Comments

Before the invention of statistical tests, such as the t test, science moved forward. People gathered data, computed averages, drew reasonable conclusions. As far as I can tell, modern ways of analyzing data improved the linkage between data and conclusion because they reduced a big source of noise: How the data were analyzed. Procedures became standardized. Hypothesis testing improved. Hypothesis formation, however, did not improve. Knowing how to do a t test and the philosophy behind it will not help you come up with new ideas. Yet data can be used to generate new ideas, not just test the ones you already have.

Our understanding of outliers is in a kind of pre-t-test era. People use them in an unstructured way. As Howard Wainer’s analysis of his blood sugar data indicates, better use of them will improve hypothesis formation. A kind of standardized treatment should help generate ideas, just as the t test and related ideas helped test ideas. Here are some questions I think can be answered:

1. Cause. What causes outliers? It’s a step forward to realize that outliers are often caused by other outliers. Howard has found that unusually high blood sugar readings are caused by eating unusual (for him) foods.

2. Inference. I’m fond of saying lightning doesn’t strike twice in one place for different reasons. The longer version is if two outliers could have the same explanation, they probably do. I think this principle can be improved.

3. Methodology. To test ideas, you want variation to be low. To generate ideas, you want outlier rate to be high. Howard could make progress in understanding what controls his blood sugar by deliberately testing foods that might produce outliers. In genetics, x-rays and chemical mutagens have been used to increase mutation rates; mutations are outliers. (Discovery of a white-eyed mutant fruit fly led to a wealth of new genetic ideas.) In physics, particle accelerators increase the outlier rate in order to discover new subatomic particles. There are no comparable procedures for psychology. Self-experimentation increased my rate of new ideas because it increased my outlier detection rate. It increased that rate for three reasons: 1. I kept numerical records. 2. I analyzed my data using the same methods as Howard. 3. I did experiments. Travel is like experimentation; there too it helps to keep numerical records and analyze them. The question: What are the basic principles for increasing outlier rate?
Part 1.

More from Holland

Seth Roberts1 Comment

My friend in Holland wrote again:

Last year, the Dutch Supreme Court ruled that it was OK to have sex with animals, as long as the animals enjoyed it.

She attached a newspaper article in the Hague/Amsterdam Times dated 20 March 2008 that began:

Under a new law being debated by the government, sex with animals will be allowed as long as people don’t enjoy it.

It ended:

The Animal Party was mainly disappointed about the fact that the new bill does not refer to the animals’ dignity.

Buried Treasure (part 1)

Seth Roberts4 Comments

Not long ago, Howard Wainer, the statistician I mentioned recently, learned that his blood sugar was too high. His doctor told him to lose weight or risk losing his sight. He quickly lost about 50 pounds, which put him below 200 pounds. He also started making frequent measurements of his blood sugar, on the order of 6 times per day, with the goal of keeping it low.

It was obvious to him that the conventional (meter-supplied) analysis of these measurements could be improved. The conventional analysis emphasized means. You could get the mean of your last n (20?) readings, for example. That told you how well you were doing, but didn’t help you do better.

Howard, who had written a book about graphical discovery, made a graph: blood sugar versus time. It showed that his measurements could be divided into three parts:

measurement = average + usual variation + outlier (= unusual variation)

Of greatest interest to Howard were the outliers. Most were high. They always happened shortly after he ate unusual food. Before a reading of 170, for example, he had eaten a pretzel. He had not realized a pretzel could do this. He stopped eating pretzels.

When Howard told me this, it was like a door had opened a tiny crack. Recently a deep-sea treasure-hunting company found a shipwreck off the coast of Spain. They named it Black Swan, apparently a reference to Nassim Taleb’s book. Shipwrecks are black swans on the ocean floor; black-swan weather had sunk the ship. For Howard, outliers were another kind of buried treasure: the key to saving his sight.

It isn’t just Howard. Outliers are buried treasure in all science. They are a source of new ideas, especially the new ideas that lead to whole new theories. The Shangri-La Diet derived from an outlier: Unusually low hunger in Paris. My self-experimentation about faces and mood started with an outlier: One morning I felt remarkably good. My discovery that standing improved my sleep started with a series of days when I slept unusually well.

Modern statistics began a hundred years ago with the t test and the analysis of variance and p values — very useful tools. Almost all scientists use them or their descendants. Almost all statistics professors devote themselves to improvements along these lines. However, conventional statistical methods, the t test and so on, deal only with usual variance. (Exploratory data analysis is still unconventional.) As Taleb has emphasized, outliers remain not studied, not understood, and, especially, not exploited.

Praying With Lior and Labors of Love

Seth RobertsLeave a comment

Last night I saw Praying with Lior, a documentary about the bar mitzvah of a boy with Down’s Syndrome. Easily the best movie I’ve seen this year, better than There Will Be Blood, Mary Poppins (leaving aside the great song Feed the Birds), Blade Runner, and several documentaries, for example. I asked a friend why she liked the TV show ER. “It makes you feel happy and sad,” she said. Praying for Lior made me sad again and again, which is part of why I liked it so much. I also liked seeing someone with a handicap struggle and succeed; Praying with Lior has a lot in common with My Left Foot, one of my favorite movies.

The person responsible for the film is Ilana Tractman, who met Lior at a religious retreat. Her day job is making television documentaries. She got the money to make the film — from a large number of foundations and people — while she was making it. As far as I can tell, she had almost total freedom, in contrast to her TV documentaries. I use the term superhobby to describe activities that combine the skills and resources of a professional with the freedom of a hobbyist. All of the blogs I read regularly are superhobbies. My self-experimentation was (and is) a superhobby. Writing open-source software is a superhobby. Most books are superhobbies. When a superhobby produces art, we call the product a labor of love. As we get richer and richer — thus can afford more freedom — and skills and knowledge improve, these labors of love become better, more possible, and more common.

The Praying with Lior website revealed to me that the film had/has a “mission”: “to change the way people with disabilities are perceived and received by faith communities.” Perhaps that is another reason why such a good film was made: This purpose helped it get funding and other help (a lot of people worked on it). And maybe it was part of why Ms. Tractman began and continued a difficult and uncertain project.

Human Subjects Research at Drexel University

Seth Roberts5 Comments

I am visiting Philadelphia. Yesterday I learned that if you want to do human subjects research at Drexel University you must:

1. Include indemnification language in the consent form. The subject must promise to not sue Drexel no matter what happens. This is a bluff: You cannot sign away your ability to sue. Of course this requirement leaves subjects more vulnerable, not less, the usual purpose of consent forms. Shades of twisted skepticism.

2. Never contact subjects via email.

3. Never advertise your research on the web.

4. Never contact subjects who have been in a previous experiment.

The Drexel IRB (Institutional Review Board) will never approve any study that involves giving any drug to a non-patient. This means the very important studies by David Healy that involved giving Prozac to ordinary (non-depressed) people — some of whom became suicidal — wouldn’t be possible.

I suppose it’s no surprise that Drexel IRB members, such as literature professors, criticize research designs. In an NPR piece, a former IRB member boasted about the accomplishments of her membership, which included correcting faulty designs. At UC Berkeley a few years ago, I submitted to the animal research IRB a proposal to test with rats a key observation behind the Shangri-La Diet: Drinking sugar water caused me to lose weight. The proposal was turned down: It couldn’t possibly be true that sugar water can cause weight loss, said the IRB. Testing this idea was a waste of time.

IRB Watch. Earlier post about IRBs.

Blood Sugar Measurements?

Seth RobertsLeave a comment

Speaking of blegs, Howard Wainer, a renowned statistician at the National Board of Medical Examiners, is looking for sets of blood sugar measurements in Excel format. The ideal set would be measurements six or more times per day for several months. He is writing a paper about better ways to analyze such measurements, which are commonly made by diabetics and persons at risk for diabetes. He has collected such measurements himself; he wants to see how well the methods he developed using data from himself work with data from someone else. You can reach him at hwainer at nmbe dot org.

I told Howard: You will be the first statistician (a) to use your professional skills to improve your own life and (b) publish the results. (Which is what I did with my self-experimentation.) Lots of statisticians must have done something similar, said Howard. For example? I asked. He mentioned John Tukey making traffic measurements to help his wife push a change in traffic rules. However, Tukey didn’t publish the results and the relevance to Tukey’s own life was tiny. If anyone reading this knows of an example, please let me know. Statistics is hundreds of years old; there are thousands of professional statisticians. It seems strange that it has taken this long for such a thing to happen but that seems to be the case.

Cramps and Self-Experimentation

Seth Roberts2 Comments

Does too little potassium cause cramps? Quite possibly:

Dr. Stephen Liggett, a professor of medicine and physiology at the University of Maryland, . . . got terrible cramps in his calf during yoga. The culprit, he decided, was the drugs he takes for asthma, which can diminish the body’s supply of potassium. He knew that potassium is sold over the counter. But because high levels of potassium can be dangerous, store-bought potassium supplements are not very strong. . . . Before he does yoga, he measures the potassium levels in his blood before and after taking what he describes as a hefty dose of over-the-counter supplement. Then he calculates how much additional potassium he thinks he needs, securing it from concentrated potassium tablets from his research lab — how much he declined to say.”I didn’t want to drink two gallons of Gatorade,” Dr. Liggett explained. He hasn’t had cramps since he began ”preloading,” as he calls it, with potassium. But, he said, ”I haven’t done a controlled trial.”

Thanks to Evelyn Mitchell.

Addendum. Someone commented that the potassium/cramps connection is widely known. And he or she is right. No wonder Dr. Liggett didn’t do a “controlled trial”.