Author: Seth Roberts

A Statistics Package in the News

Seth Roberts7 Comments

I use R, the open-source version of S, several times/day. More often than I use Word. It works far better than S — fewer bugs, much cheaper (R is free) — and S worked a lot better than what it replaced (STATGRAPHICS). I was pleased to see a NY Times article about it:

R has also quickly found a following because statisticians, engineers and scientists without computer programming skills find it easy to use.

“Easy to use” — haha! Non-statisticians and non-engineers don’t find it easy to use, in my experience, but it’s true that I found it easy to use. “R has a steep learning curve” some people say, twisting the meaning of “steep learning curve” (which should mean fast learning, since that’s what a steep learning curve describes).

The popularity of R at universities could threaten SAS Institute, the privately held business software company that specializes in data analysis software. SAS, with more than $2 billion in annual revenue, has been the preferred tool of scholars and corporate managers. . .SAS says it has noticed R’s rising popularity at universities, despite educational discounts on its own software, but it dismisses the technology as being of interest to a limited set of people working on very hard tasks.“I think it addresses a niche market for high-end data analysts that want free, readily available code,” said Anne H. Milley, director of technology product marketing at SAS. She adds, “We have customers who build engines for aircraft. I am happy they are not using freeware when I get on a jet.”

Ah, “freeware.” You may remember when “Made in Japan” was derogatory. Most psychology departments, including Berkeley, use SPSS (Statistical Package for the Social Sciences). Like SAS and its ten feet of manuals, it is horrible. One of my students wanted to make a scatterplot of her data. She went to the psych departmental statistics consultant (a psych grad student who had taken courses in the statistics department). The statistics consultant didn’t know how to do this! A scatterplot! It’s like Vladimir Nabokov’s observation at Cornell and other schools of language professors who couldn’t speak the language they taught. Nothing But the Best describes a Julliard composition teacher who couldn’t read music. To be a scientist and not be able to analyze your own data is pretty much the same thing. With R making a scatterplot is easy.

To me, the value of R is that it makes high-quality data analysis available to everyone — something very new in the history of mankind. R makes self-experimentation easier because it makes data analysis easier and allows you to learn more from the data you have collected (e.g., make better graphs). I also use it for data collection — measuring how well my brain is working.

Via Andrew Gelman.

Kafkaesque Research Regulation

Seth RobertsLeave a comment

From the BMJ:

The local research ethics subcommittee, which comprised a pharmacist and layman with limited clinical experience, had concerns about possible drug interactions between amiloride and other drugs being taken by the study participants and hyperkalaemia and requested resubmission. Although we pointed out that the pilot was identical to one limb of the amendment that it had already approved, in September 2007 the full committee rejected the application for the pilot to be considered as a study amendment. We therefore had to make new submissions to the local ethics committee, Medicines and Healthcare Products Regulatory Agency (MHRA), pharmacy, insurance company, research and development department, and the local (Wellcome Trust) clinical research facility.

In Spain it takes years to get approval. By the time you get approval someone else has published the study you wanted to do. A nightmarish research environment is one more reason that persons with health problems should do their own research: try to find solutions themselves. I started long-term self-experimentation because I knew that conventional sleep research would never — at least, in my lifetime — help me understand why I often woke up too early. A common problem, easy to measure — but conventional sleep research is nearly impossible.

Can it get worse? Yes, in Russia.

Lipid Values after 2 Years on the Shangri-La Diet

Seth Roberts6 Comments

Stephen Marsh has been doing the Shangri-La Diet for 2 years, taking about 6 tablespoons of ELOO (extra light olive oil) per day. He recently got an expanded set of blood tests done. Here are the results. (10-90%ile mean 10% and 90% percentiles in the general population):

  • LDL IIIa+b (%). 10-90%ile 13.6 — 43.0; Alert Value >20; SM = 17
  • LDL IVb. 10-90%ile 1.7-9.8; Alert Value >10; SM = .9
  • HDL2b (%). 10-90%ile 7-30; Alert Value <10; SM = 29
  • Apo B. 10-90%ile 60-140; Alert Value >120; SM = 48
  • Lp(a). 10-90%ile 0-30; Alert Value >30; SM = 10
  • Lp_PLA2. 10-90%ile 155-419; Alert Value >223; SM = 197
  • Insulin. 10-90%ile 3-25; Alert Value 12; SM = 9
  • NT-proBNP. 10-90%ile 5-125; Alert Value 450; SM = 14
  • Cholesterol       134
  • Triglycerides     51
  • HDLÂ Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 67
  • LDLÂ Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â 57
  • Glucose           86

Stephen added:

Two years after the weight loss, taking in what so many of these “experts” say is a dangerous level of fat as a dietary supplement, my bloodwork, especially the important markers, is very good. Bottom line is a low level of small LDL particles and a miniscule level of the dense, dangerous ones (below the reference range). On the HDL (the “bad” cholesterol) the particles are about half of the largest or non-dangerous kind.

Tracking How Well My Brain is Working

Seth Roberts5 Comments

From my omega-3 results I got the idea that our brains may work better or worse without our noticing. I want to track how well my brain works not only to test the effects of different dietary fats (our brain is more than half fat) but also to allow the possibility of discovering new effects, both good and bad.

One test I am using is a typing test (early results here). Another is an arithmetic test. I got the idea of using arithmetic from Tim Lundeen. Like him, I found that the speed with which I could do simple arithmetic problems (8+0, 4*3) was sensitive to the amount of omega-3 in my diet.

The arithmetic test involves doing 100 problems separated into 5 blocks of 20 each. There is little time between each problem. I type the last digit in the answer; e.g., if I see 8*8 I type 4. The possible answers are 1, 2, 3, 4, 7, 8, 9, and 0 so that I don’t have to move my fingers off the keys. There is feedback after each block. I aim for 95% correct.

This is my second use of an arithmetic test. The advantages of this one compared to several other tasks I have tried are:

  • Portable. Only requires a laptop.
  • Well-learned. So I should plateau (reach a steady speed) sooner than with a task I learn from scratch. When my speed is steady it will be easier to compare different conditions — no need to correct for learning.
  • Uses eight fingers. Many tasks used by experimental psychologists have just two possible answers (yes/no). With eight possible answers there is less anticipation and less worry about repetitive strain injury.
  • No data entry. The task is written in R, the language I use to analyze the data.
  • Many measurements per minute. This allows me to correct for problem difficulty and get a standard error for each test session.

Here are early results.

In the test sessions after January 1, two sets of points are above the line — I was slower than expected, in other words. Both came from test sessions about an hour or so after I woke up. At the time of those sessions I felt fine — not tired, not groggy — and was a little surprised. This is a trivial example of what I am looking for: new environmental effects.

The bigger context of this research is that scientists know a lot about idea testing but almost nothing about idea generation — how to find new ideas worth testing. Maybe this research will teach me something about idea generation.

A talk by Tim Lundeen about related stuff.

Things That Work Much Better When Broken (part 2)

Seth Roberts2 Comments

If six months ago you had told me such things existed I would have been very skeptical. But since then I have come across two examples. Example 1: contact lenses. Forced during a trip to wear just one lens (leaving one eye without a lens), I realized my sight was much better than when I wore two. I had sharp vision both close and far away. And the unlensed eye got more oxygen than usual.

Example 2 I also discovered by accident. My bike lock no longer locks. It is hard to see this, so if I fake-lock my bike — which I got for free — it is still sufficiently protected. My bike lock is now much easier to use. No more worry about the key. No way it can become impossible to unlock, which has happened once in two months. (To any Tsinghua students reading this: Please don’t steal my bike.)

Does Innovation Require Markets?

Seth Roberts4 Comments

Andrew Gelman's table

Andrew Gelman writes:

The article [about economics professor David Galenson] then quotes art professor Michael Rushton as saying that in science or art, “innovation really requires a market.” Huh? Wha?? Tell that to my friend Seth, who spent 10 years self-experimentation. Heck, tell that to the cave painters. Or check out the American Visionary Art Museum.

I agree. I was able to do self-experimentation for 10 years because I didn’t have to sell, i.e., publish it. Not having to sell — I mean publish — it gave me the freedom to do and think whatever I wanted for as long as I wanted.

Innovation benefits not from markets but from subsidies, which provide time to experiment. In my case, I was a professor at Berkeley — subsidized by the State of California. I had tenure and free time. Sometimes the subsidies aren’t obvious. Part of my theory of human evolution is that gifts, ceremonies, holidays, fashion, and connoisseurs, not to mention love of art, subsidized artists and artisans by providing a desire for work that — in the absence of gifts, etc. — would be much harder to make a living from. Helping artists and artisans make a living helped them advance their technology. Cave paintings may have been part of a holiday observance — the artists took time off from hunting. Before trade, Thorstein Veblen’s Instinct of Workmanship motivated innovation. Andrew himself built the table in the above photo for reasons that had nothing to do with markets.

But at least an economics professor is studying innovation. A few years ago in the Berkeley Public Library I picked up an introductory economics textbook. Six or seven hundred pages. Half a page on innovation!

Assorted Links

Seth Roberts5 Comments
  1. Self-experiment on short-term memory announcement
  2. Why the Chinese government censors the Internet. James Fallows was able to figure out why they blocked the NY Times website for a few days (an article about suppression of rebellion).
  3. Nassim Taleb on iatrogenesis. “They never consider that “nothing” may be better than the best model.”
  4. The Lost Art of Walking by Geoff Nicholson.
  5. Best journalism of the year. More lists like this! One reason Spy was so good, I think, was that they covered stuff, especially New York publishing, that they knew about from personal experience. Like scientists writing about science.
  6. Six ballsiest scientific frauds.

Thanks to Dave Lull and Tyler Cowen.

Folic Acid and Birth Defects

Seth Roberts1 Comment

The researchers who discovered that too little folic acid causes birth defects haven’t gotten a Nobel Prize (and probably never will) but they should, as this article explains:

After 3 decades of epidemiologic research reporting an association between neural tube defects and maternal use of folic acid, public health organizations developed recommendations and supported interventions to increase folic acid intake among women of reproductive age. In 1992, the US Public Health Service recommended that all women of childbearing age who are capable of becoming pregnant should consume 400 µg of folic acid daily.

. . . In 2005, after the National Campaign and mandatory fortification, approximately 33% of women reported taking a daily supplement of folic acid, only a modest increase from the 25% reported in 1995. However, median blood folate levels among women of childbearing age increased from 4.8 to 13.0 ng/mL between 1994 and 2000, with a more recent study reporting median blood folate levels at least 2 times the levels prior to fortification.

To evaluate the impact of this public health intervention, 4 study groups have conducted time trend analyses among the US population, and all have reported a decline of neural tube defects after the introduction of mandatory folic acid fortification. Specifically, these studies reported an 11%—20% reduction in occurrence of anencephaly and a 21%—34% reduction in occurrence of spina bifida when comparing pre- versus postfortification rates. Similarly, the occurrence of anencephaly and spina bifida was observed to reduce 38% and 53%, respectively, in Canada and 46% and 51%, respectively, in Chile following folic acid fortification.

Here is the first article on the subject. As the dean of a school of public health put it, this discovery by itself justifies all the money ever spent on schools of public health.