Saturday, November 7, 2009

Used Barf Bags and Statistical Literacy

NYTimes Magazine Via Joshua Gans. Find the logical (statistical?) mistake:

As a last ditch effort, I grab an air sickness bag from out of the wall pocket. Using one of the rejected crayons I scrawl a face on the bottom of the bag. I reach inside, turn it into a hand-puppet and say the funniest thing I can think of: “Ooga booga.” The child stops crying. Then smiles. Then giggles.

“You like the puppet?” I ask. “MO PUPPA!” she says.
...
Then think to myself, “sure, one puppet is fine, but two puppets — now that’s a show!” I reach into the wall-pocket in front of my husband and take out his air sickness bag. I draw another face, this time taking a little more time and care with my creation. I give it curly hair, long eyelashes and glasses so that it looks a little bit like me. Nice touch.

I stick my hand inside. And then my world contracts.

Seems this air sickness bag has been used before, but not for a puppet show. No, it’s been used for the purpose that god intended.
....
Roughly two million people fly the friendly American skies every single day. How many of those travelers feel nauseated enough to reach for, and then use, an air-sickness bag? (I travel often and can count on one clean hand the number of times I’ve seen it happen.) And of those phantom pukers, how many would choose to tuck the vomit-filled vessel back into the wall-pocket? And then, what’s the likelihood that a cleaning crew would overlook the sack o’ sick? And finally, what are the odds that all of this would become the perfect set-up for one arrogant idiot who tries to make a hand-puppet out of a barf bag?!
...
Anyway, it’s possible that the occurrence of this mathematical improbability has created a statistical vortex by which we are virtually guaranteed that this plane will land safely.



Best Jobs

Mathematician #1, Statistician, #3, Economist, #11. Have no clue how historians and sociologists beat us out, but at least we beat "philosopher," or "stand-up philosopher" aka "bullshitter" (gotta love Mel Brooks).

College Selectivity and Student Mobility

Via TC @ MR: A recent study by Caroline Hoxby
shows that although the top ten percent of colleges are substantially more selective now than they were 5 decades ago, most colleges are not more selective. Moreover, at least 50 percent of colleges are substantially less selective now than they were then. ... [S]tudents used to attend a local college regardless of their abilities and its characteristics. Now, their choices are driven far less by distance and far more by a college's resources and student body. It is the consequent re-sorting of students among colleges that has, at once, caused selectivity to rise in a small number of colleges while simultaneously causing it to fall in other colleges.
I'm a bit puzzled. Though the results almost certainly document an overall decline in student quality for a large number of more remote colleges and universities, I'm not sure this proves that there has been a decline in "selectivity" on the part of those universities. Schools may not be lowering their standards; they may just be getting a more average applicant pool with fewer top-talent students. I would invoke the principle that people will find your results more believable if you interpret them conservatively.

Wednesday, November 4, 2009

Socialist Highways and When to Shut up and Pay your Taxes

I was just wondering what the average share of the highway budget most Americans would pay if it were divided according to the "benefits received" principle (i.e. how much you use it). Turns out, on average, if you mostly commute on federal roads (not a horrible assumption, but we could easily just assume that the per-mile cost is the same for federal roads as state and municipal roads and be OK) then it would be about $110, just for your daily commute to work.
According to the Department of Transportation there was about 43.5 billion allocated to federally-maintained highways in 2008. The total vehicle-miles traveled was about 3.03 trillion for the same year. The average commute (according to an ABCNews survey) is about 16 miles each way. So if you work 5 days a week about 48 weeks out of the year, and have an average commute, you'll travel about 7680 miles per year just to get to and from work, or 0.0000002535% of the total highway vehicle miles traveled. So if you paid that "share" of the transportation budget, that would come to about $110 per worker.
So you might say, "GREAT, PRIVATIZE THE ROADS OVER TO THE MARKET!" Not so fast! If we ran things according to the market, many of you suburban republicans would have a higher than average commute, especially you folks in big urban-sprawl areas like St. Louis or Dallas or Chicago. Plus, some people may not use roadways at all, or they may "use" them much more lightly. I travel 3 miles and ride a bike. Why the hell should my tax dollars subsidize some jerk with a full-size pickem up truck that does more road damage??? Some folks would call that downright un-Amuhrrican! Clearly some folks should pay more. Plus, whoever owned the roads would have a monopoly, so they'd be able to price-discriminate and charge double from 7-9am and 4:30-6:30pm, and make a tidy economic profit off the deal. So you'd probably pay at least 2 or 3 hundred a year to the private company. So, on average by privatizing certain things (or not having regulation) we probably end up saving 100 so that we can pay twice or thrice that, i.e. bending over a dollar to pick up a dime.

Political lobbying explained through the example of all-pay auctions

Tuesday, November 3, 2009

Sampling Bias and "Enthusiasm Gaps"

This is an interesting twist on sampling bias. Since robopolls are less able to coax you into staying on the line, they only grab the more enthusiastic likely voters. In New Jersey, human polls and robopolls are indicating leads to opposite candidates. Human polls favor Corzine, and robopolls favor Christie.

The Productive Nature of Whining

Don't let a VMI cadet see this.

More Rationale for Overoptimism

There is a simple way to get overoptimism (and hence bubbles): suggest that the agent's payoff is correlated with his guess. Here's another:
The observer’s beliefs are different from agent A’s.  They are drawn from the same distribution G but there is no reason that the observer’s beliefs are the same as agent A’s.  In fact, the action agent A took will only be the best one from the observer’s perspective by accident.  Actually, the observer’s beliefs will be the average of the distribution G which is lower than the belief of  agent A since agent A deliberately took the action which he thought was the best.  This implies that the agent A who took the action is “overoptimistic” relative to an arbitrary observer.


Sunday, November 1, 2009

Economists Category on Jeopardy

They zip through world history and Shakespearian quotes, but a question about Adam Smith elicits blank stares. Priceless.



Brain Drain or Brain Gain?

This article in Foreign Policy confirms what economists have said about skilled migration for the last decade or so: It helps both the recipient and the source country. One of the ways they acknowledge emigration to help is through remittances.  However, the last point, "Just as fears about possible negative effects of brain drain are typically overblown, so is the hype over the ability of countries to tap their diaspora to set up trade and investment," is not consistent with recent research. There are a few papers out showing a strong positive link between skilled emigration and FDI flows in the other direction, including one that a couple of guys named Bang and MacDermott are trying to get published.

Tax Water?

Urban economists might think taxing land is the ideal way to manage urban growth; PK thinks it wouldn't raise enough $$. Should we tax water? Like a tax on land (not a tax on property, which would include the development of land), it would likely not distort investment. I'm concerned about the distributional consequences of a tax on a necessity that many people consume inelastically.

Rich people with civic responsibility

Rich Germans petition in protest of government tax rates!!! That's right, they think they're paying too little and they should be paying MORE!