Another take on statistics in soccer from Slate

Brian Phillips has written an interesting analysis of the uptick in statistical analysis in soccer in Slate, available here, and why a Moneyball-like analysis will, or maybe won't work for soccer. Be sure to click on the link he provides to the UK Guardian's Interactive Chalkboards feature, also available here, and submit your own tactical analysis. You can see my earlier post on the great soccer statistics book Soccernomics here.

NY Times reviews "Overdiagnosed"

Today's New York Times Science Section carries a review of Overdiagnosed: Making People Sick in the Pursuit of Health, a look by doctors at Dartmouth's medical school at the assumptions underpinning some of our preventive medicine practices. You can read the review here. There'll be more, when I've had a chance to read the book, but for now the review is worth reading for two reasons. It will make you start thinking about the right questions to ask when your doctor recommends a diagnostic procedure. And it opens with a nice analogy about Martin Luther.

Using Health Care Data to Manage High Flyers

UPDATE, Feb 14 -- The article is now available for free on the New Yorker's web site.

The January 24 New Yorker has a fascinating article by Atul Gawande, "The Hot Spotters." It's about how a couple of innovative doctors have taken a look at patients who are large consumers of medical services and come up with ways to manage their care better so they don't require so many hospitalizations, ER visits, and other costly resources. The article is available, unfortunately behind a pay wall, here. It's worth reading -- if you're someone thinking about service costs, it's useful for ideas; and since we're all taxpayers, it's also an interesting policy discussion.

CHASING THE SUN by Richard Cohen

Update, February 16, 2011: Here's a link to a new photograph of a black hole without a galaxy - perhaps the remains of a disintegrated galaxy? The black hole has a mass 20,000 times that of our sun.

I'm trying to blog about books that are relevant to my consulting but really want to mention Chasing the Sun by Richard Cohen (Random House 2010, 511 pages). It's subtitle is "The Epic Story of the Star that Gives Us Life" and it's an astonishingly broad survey, moving from Stonehenge to the Pyramids to Antarctica to India, about the sun in different cultures, and the sun as metaphor, myth, and the (literal) support of all life.

We take the sun for granted, except during eclipses, but it's the basis of a lot of human culture: calendars, navigation, astronomy, astrology, religion. Painting, music and literature. But Cohen doesn't stop there. He explains why the sun burns. What will happen, to it and to us, when it burns out. And the history of how we figured out as much as we have.

If I have one quibble with this book, it's with Cohen's conclusion that the jury may still be out on global warming, because not enough climate scientists have engaged with recent research suggesting the sun's activities are also contributing to climate change. Fair enough, but he does not address the possibility that human activities might be exacerbating the effects of a sun cycle. As I said, it's only a quibble.

Cohen is deeply engaged in every aspect of the sun, from art to solar physics, but wears his erudition lightly -- this is the only book I've read that includes cartoons among the end notes. And the book is supremely well-organized, a particular feat given its range, with generous illustrations.

Critical thinking and mathematical literacy

Mathematics, and statistics in particular, offer us powerful tools to understand and explain the world. Unfortunately, they also offer us equally powerful ways to conflate information, confuse us, and confound us as well.

In Proofiness, a book geared to non-mathematicians, journalism professor Charles Seife offers some simple measures to make sure we keep our critical facilities intact:

• Pay attention to the context -- a number alone can suggest a certainty that might not exist. (Even counting can be prone to errors.)
• Remember that correlation and causation are not the same thing, and that a correlation may not have meaning. We are wired to look for patterns, and sometimes our brains fool us into finding a pattern that is not there.
• We don't know how to calculate risk so we often base decisions on the information in front of us and how it's presented.
• Polling is not a perfect science, and knowing the margin of error does not correct all the possible errors.

And so on. He calls succumbing to these errors and others "proofiness." Along with that term, he uses additional, equally memorable coinages: randumbness, causuistry, and regression to the moon. But it's in the examples that this book is most useful. Drawing from recent events--the 2000 Presidential election, the 2008 Minnesota senatorial election, the OJ Simpson trial, various death penalty trials--he shows us all too many places where numbers have been used to trump logic, common sense, and, well truth. And Seife shows us how lawyers, journalists, and we ourselves as consumers, are party to continuing these errors. Proofiness,  (Viking, 2010, 260 pages) is well worth reading and even more worth absorbing.

"The Mathematics of Narcissism" in Slate.com

Anyone who has tried to compile statistics for a large group of humans has been confronted with the issue of which of a large collection of measurements are the most important. It's useful to remember that how we choose the key data is worth revisiting occasionally. Jordan Ellsberg discusses this issue, and how it was resolved in two very different contexts, in a Slate post called, "The Mathematics of Narcissism," available here.

The two contexts are the decision of the committee writing DSM V to exclude "narcissistic and paranoid personality disorder" from the list of psychiatric diagnoses, and the decision of the authors of the National Research Council's committee ranking graduate schools essentially to throw up their hands instead of agreeing on a single ranking system.

I can think of lots of contexts -- New York City's ranking of its schools with a letter grade comes to mind -- in which this issue could use revisiting. Sometimes the contentious discussion just tells you more than the single grade or ranking does.