Popular Science

So there is this article which has been making ripples on the Internet today. Supposedly it's trying to put some science behind the argument that democracy in the US doesn't work. The punchline is convenient:

But the picture changes markedly when all three independent variables are included in the multivariate Model 4 and tested against each other. The estimated impact of average citizens’ preferences drops precipitously, to a non-significant, near-zero level. Clearly the median citizen or “median voter” at the heart of theories of Majoritarian Electoral Democracy does not do well when put up against economic elites and organized interest groups.

Except the problem is, the conclusion isn't really accurate. A quick look at the article shows the authors conclude that two of their independent variables are strongly correlated (average citizen preferences and economic elite preferences, see Table 3), and then proceed to ignore the ensuing multicollinearity issues in their modelling approach. It's worth reminding that multicollinearity makes individual variable coefficients unreliable. Moreover, all three independent variables are demonstrably positively correlated with the outcome variable (Table 2), suggesting the conclusion should be exactly the opposite of the one pitched . What's "beyond alarming" here are not the findings or the Internet buzz. It's the fact that analysis like this actually passed peer review this way.

A V, 2 Us, and an L

A V, 2 Us, and an L:

click on graphic to enlarge

This is taken from Greg Mankiw''s blog. Interestingly, exactly the same type of graph is used in Intro to Stats texts to illustrate misleading use of graphs. Not that the data is incorrect or anything, but it takes a minute to figure out why it looks like employment percentage dropped down to close to zero in 1983...

BPEA is open access

From Greg Mankiw's blog:

BPEA is open access: "Here is some interesting news.  The Brookings Papers on Economic Activity, one of the best applied macro journals around, is making all journal issues available to the public without charge.  Click here for the recent conference papers and here for back issues."

Dawn of The Living Dead, Nerd-Style

Wondered about the mechanics of a zombie infestation? Ask Canada.

New Version of the Nigerian 419 Scam

Most of you have probably received a version of this in your e-mail. The attempts are painfully transparent: a desperate widow/orphan is fleeing from a coup somewhere in Africa, and is willing to pour millions of dollars in your bank account.

Today, I received a curious new permutation in my e-mail: an invitation to register for a legitimate conference, with a contact e-mail @live.com, and sent by a @gmail.com account. Inventive, no?

On a related note, here is an entertaining site dedicated to the said scam scheme.

Causality

Drivers who switched ... saved an average of [X dollars] a year

This popular insurance commercial carries a clear subtext: if you change your insurance provider, you will save money. But is this really the same as "changing insurance saves you money?".

Causality is an import concept, which is often critical in understanding economic analysis. To give an anecdotal example, the sun rises 1 hour after I wake up, but this doesn't mean me waking up makes the sun rise. Sure, there is a correlation between two events, but that doesn't necessarily have any strong inferences about their causality.

But back to the insurance example: those who switch insurance surely save money. If they weren't about to save, they wouldn't have switch to boot. So this is more or less stating the obvious. But drivers are different, and so are the policy packages offered. Therefore picking a a number of drivers at random, and switch their insurance might provide surprising average results.

And, of course, the above slogan would be different even if the sample size of drivers who switched is just two, but then again -- advertising is often designed to be catchy and not necessarily informative.

Run for the blonde!

If you have seen the movie A Beautiful Mind, then you probably remember the bar scene where John Nash muses aloud about what happens when everyone goes for the blonde.

This episode was supposed to illustrate Nash Equilibrium, a concept named after Nash, who received the Nobel prize in Economics in 1994 for his work in the field of game theory.

Of course, it takes about 5 lines to explain why the example is faulty, and every undergraduate who has taken a basic game theory course should be able to do it. The surprising part is the massive reaction this little scene has caused on the Internet: the comments vary from tongue-in-cheek George Clooney references to a 12-page scientific paper. Panic!