survival tip

A recent paper* turns the modern spotlight of statistics onto that pressing issue of how best to survive a big cat attack. The authors analysed data from 185 puma attacks on humans in North America over more than 100 years. The response was severity of injury, ranging from no injury to death. The predictors were age, group composition and behaviour. I am not sure about age but I am guessing that you shouldn’t go walking by yourself in puma country for a start. The modern data crunch used to reveal the elusive truth was multinomial regression.

Chris Lloyd on Core Economics, the rest here.

the story behind the election

Andrew Gelman and John Sides have an article in the Boston Review analyzing Obama's victory, here.

radical thought

Probably the most noble thing a publisher can possibly do is provide cheap paperback editions of important texts. All the first editions and Folio press embossed hardbacks in the world are, culturally if not financially, worth less than a single bundle of 1960s Penguin Classics, and the line of low-budget purveyors of enlightenment is a worthy and laudable one. From the Everyman’s Library editions of the 1900s-40s, with their arts & crafts aesthetic, aimed clearly at autodidacts rather than scholars, to the more famous and, recently, highly fetishised Pelicans and Penguins of the 40s-70s, this is a story of profit, no doubt, but also of human emancipation through mass production. ...

Owen Hatherley on Verso's Radical Thinkers: Series 4 in 3:AM Magazine, here.

that clinking clanking sound again

Greg Butler has drawn my attention to an article in the NYT on Kickstarter, a new method for raising funds for the arts, here.

Why didn't they ask Gelman?

Reformers like Cerf, Klein, Weisberg, and even Secretary Duncan often use the term “value-added scores” to refer to how they would quantify the teacher evaluation process. It is a phrase that sends chills down the spine of most teachers’-union officials. If, say, a student started the school year rated in the fortieth percentile in reading and the fiftieth percentile in math, and ended the year in the sixtieth percentile in both, then the teacher has “added value” that can be reduced to a number. “You take that, along with observation reports and other measures, and you really can rate a teacher,” Weisberg says.


Steven Brill, The Rubber Room, in the New Yorker.

A student. Well, no, Mr Weisberg, you really can't.

One can't help feeling that Mr Weisberg, Mr Brill and the New Yorker would all benefit from the services of a statistician. (Not that they actually need someone like AG for this kind of thing, but it would be infra dig, presumably, to call on someone who had merely mastered the material in an introductory course for undergraduates.)

disparition

He tried to show what it was like to read a book and what the thinking mind looked like in the act of writing.

He wrote compellingly about effort, about difficulty, about struggle, about failure, about incoherency, about instability, tension, waste, self-consciousness, incompleteness, process . . .


Mithridates on the critic Richard Poirier, who has just died.

codes of the underworld

The signaling problems faced by criminals are unusual in the following regard. On one hand they wish to signal a certain untrustworthiness, namely that they are criminals in the first place. This is useful for both meeting other criminals and also for intimidating potential victims. On the other hand, the criminals wish to signal that they are potentially cooperative, for the purpose of working with other criminals. Sending these dual signals isn't easy and Gambetta well understands the complexity of the task at hand.

Tyler Cowen of MR, on Diego Gambetta's Codes of the Underworld: How Criminals Communicate.