Subgroups

August 20, 2008
Posted by Jay Livingston

Yesterday, Jeremy Freese had a post at Scatterplot on interaction effects:

There are so many ways of dividing a sample into subgroups, and there are so many variables in a typical dataset that have low correlation with an outcome, that it is inevitable that there will be all kinds of little pockets for high correlation for some subgroup just by chance.
Today, the Onion News Network had this example, probably inspired more by Mark Penn than by Jeremy, but instructive nevertheless.



Hat tip to Ezra Klein at The American Prospect.

Head Start for Stats

August 21, 2008
Posted by Jay Livingston

If you want students to master quantitative methods, I guess you have to start while they're young.



As you have no doubt guessed, this has nothing to do with statistics. The products – backpacks, wristbands, etc. – are like medical alert bracelets for kids, to alert adults to the child’s food allergies or other medical conditions.


The Problem of Evil

August 19, 2008
Posted by Jay Livingston

Does evil exist and if it does, do we ignore it, do we negotiate with it, do we contain it or do we defeat it?
That was the question Pastor Rick Warren put to Obama and McCain in the televised interviews at the Saddleback Church.

The problem of evil and what to do about it. It’s a potentially daunting and complicated topic, one that theologians and philosophers have written about at length over the centuries. It’s also potentially very simple – evil is bad, and we’re against it. It’s us versus them.

Obama’s answer wasn’t exactly a long theological discourse, but it did acknowledge some complexity. His examples suggested that evil lies not in individuals but in actions, and the examples he gave were not people that we have declared war on. (“We see evil in Darfur.”) One of those examples was something about us: “ We see evil, sadly, on the streets of our cities.” Obama even cautioned against the good-vs-evil mentality, implying that we, the good guys, might wind up doing evil. “A lot of evil has been perpetrated based on the claim that we were trying to confront evil… In the name of good.”

McCain saw no such ambiguity. “Defeat it,” he said, and the audience applauded loudly. McCain also saw evil as residing in individuals, and he named names, names of those we are already fighting: Bin Laden, radical Islamic extremists, Al Qaeda. For McCain, it’s simple. We’re the good guys, they’re the bad guys, and we will defeat them. [Applause.]

The Manichaean view seems to play well politically – hauling out images of Bin Laden and Al Qaeda for the Two Minutes Hate – at least for domestic consumption. As a basis for foreign policy in the real world, it may have its limitations. For one thing, it only works if you are powerful enough to enforce your definitions of evil on the entire world, for it turns out that not everyone in the world shares the same idea of what or who is evil.

Are we Americans the good guys fighting the forces of evil? A recent poll commissioned by the Telegraph (UK) asked people in five countries, “Do you think that the United States is overall a force for good or force for evil in today's world?”

Here are the results (I’ve omitted the “Don’t Know” percentage).


The poll was carried out online between May 23 and 29 by YouGov plc. The total sample was 6,256: Britain 2,241; France 1,005; Russia 1,001; Italy 1,004; Germany 1,005. To get the full results, go here.

I Majored in Sociology and All I Got . . .

August 15, 2008
Posted by Jay Livingston

. . . was this t-shirt.


I saw this in Strawberry Fields last week. I guess the sociology department at his school decided to try a little viral marketing.