Macro, short samples, scatterplots

Here's an interesting post at Freakonomics by Justin Wolfers in which he concludes "Be wary of economists wielding short samples."

I like the post for its scatter plots. Here is my favorite plot from his post:



It reminds me of the Phillips curve plots from the 1960s and 1970s (but in reverse).

An Economics Haiku. Can You?

Haikus of econ
Ha! Some would call it crazy.
I wrote one. Can you?

If so, post in the comments below. Xan has four other "Haikunomics." Here's my favorite.

Some background on the title of my haiku. Derek Neal taught me econometrics in the first year of the UChicago PhD program. The one thing he taught me that stuck in my head was a warning about thinking while doing econometric analysis. According to him, some people get ahold of an econometric tool that is nice in some settings. Because it is so nice, they try to use it for a whole bunch of purposes, many of which are not an ideal application of the tool. The lesson: Think about what you are doing when you use regression analysis (no matter how complicated the analysis is)

The way that Neal put it is, "You give some people a hammer and the whole world looks like a nail."

Odd Odometer Readings?

This blog post by Jeff Ely reports on some interesting research on attentiveness. Ely finishes the post with this parenthetical statement:

The next time you see zeros roll over on your odometer you will understand why that always feels like a watershed event. Your car is only a mile older but it just took a discrete drop in value.

Click through to the post to see why he concludes this.

Civil War Econopondering

I found this blog post to be especially interesting. Here is an excerpt:

And the way modern America won was characteristic. Southerners were better warriors — man for man, they almost always outperformed Union armies, although the gap narrowed over time. But the North excelled at the arts of peace — that is, in industry and ability to get things done. The North couldn’t stop Bedford Forrest from raiding supply lines; but it could repair track incredibly fast. And it was that Northern superiority in logistics, in production, that eventually proved decisive.

The many comments on the post are also interesting reading (if not for their analysis, for their variety of impressions).

Seat Allocation, Price Discrimination and Loyalty

On my recent spring break getaway, Shanna and I flew Southwest. As this was the first time we had traveled on Southwest Airlines, I was exposed to a new way to allocate seats on a plane: open boarding with seat priorities.

If you are unfamiliar with how it works, each Southwest passenger receives a ticket with a boarding priority number. Just prior to boarding, passengers are encouraged to line up according to boarding priority (in groups of 30). The airline even went through the trouble to install markers to assist passengers in lining up efficiently.


Upon entering the aircraft, passenger A1 gets to pick his/her most preferred seat. A2 gets to pick from what is left, and so on. This continues until A60, starts over at B1 through B60 and starts over again at C1 until the flight is full. In the study of mechanism design, this type of mechanism is called a serial dictatorship, which are known to produce quite unequal outcomes.

Why would Southwest choose to produce unequal outcomes among its customers? After all, Southwest must know what it is doing. There must be some way to profit from this.

A partial answer is that Southwest can exploit the inequality and uncertainty of open boarding to charge for access to special clubs that get better boarding numbers, effectively using the boarding strategy as a method of price discrimination. Passengers who care enough about boarding priority pay extra to join the club. Those who don't care that much about seat selection get boarding priority C1.

In actuality, the program is (disguised as) a loyalty program. Book 25 one-way tickets in a calendar year or earn 75,000 Tier Qualifying Points and you get priority. You could earn (cash) rewards from using some other credit card, but you forgo those rewards for priority on your Southwest flights.

This cost and the 25-flight requirement is enough to screen the different types of customers. Priority types go through the hassle and forgo other credit-card rewards while low-cost types do not. And, the priority types' hassle earns Southwest some profit because they will be less price sensitive when it comes to the 22nd, 23rd, 24th and 25th fare. With this knowledge, Southwest can obtain a higher average price. After all, the boarding priority is worth something.

Here's one passenger on the A-List program (from back in 2009):

Now since I joined the A-List program, I’ve typically gotten boarding numbers in the A20s-A30 range. I’ve also been higher or lower than that. It’s worked well. I’ve never had a middle seat. I’ve usually gotten the exact seat I want, even.

But yesterday, I was taken aback. I checked in and got a B1 boarding spot. While I know the A-List program doesn’t guarantee an A spot, I still wondered how this could happen.

This was our first time on Southwest and we booked the flight because it was cheapest among all of our options. Guess what our boarding priority was. That's right. We were C1 and C2.

On Cheating

I have been working on getting a course ready for the new quarter so I haven't devoted much time to posting. Nevertheless, I decided to come out of hiding to direct your attention to this post on cheating at Economonomics:

Maybe if I was in the bottom decile in high school, competing with the people around me to not be the one who fails, and everyone else in my decile was cheating, and the risk of getting caught wasn't too high...well it could easily be not just selfishly optimal, but in fact even socially optimal for me to cheat. Is academic honesty about fairness? What could possibly feel less fair than me failing because everyone around me cheated?

I generally like the post as a push-back against the immorality of cheating. As Xan points out in the post, cheating can be morally ambiguous. This also has me wonder. Why do we punish cheating in the first place? What role does it serve? In classrooms and political arenas, cheating/corruption is frowned upon and punished when it is exposed. It also seems to me that this is a persistent fact that this is how cheating is treated. Why is this so?

Let's stick with the classroom example. Punishing cheating is like standing up for the classroom rules. To the extent that these rules are reasonable in promoting good class objectives, it's good to preserve a stable rule of law within the classroom. Thus, the moral ambiguity of cheating arises from the fact that (A) The class objectives may be objectionable, (B) the rules may not point the students in the direction of the objectives, and/or (C) The rules enforcement may be inadequate.

These are problems with the instructor or classroom environment, not necessarily the student. In this model of the world, students are just trying to do the best they can, given the environment they face. If the pressures are too great, the communication and enforcement of the rules too weak, the long-term objectives too muddled and the motivation for the subject is too little, who can blame the student for cheating?

Of course, cheating is the student's decision so the student should bear the responsibility for it. After all, the student violated the rules. Setting this fact aside, there is a lesson for teachers. Given that a student chose to violate one of your rules, you have to wonder why. Maybe it is fully the student's fault, but teachers set up most of the learning environment. It is possible that the student was responding to perverse incentives.

Avoidability and Public Goods Provision

Here's an interesting post from Jeff Ely at Cheap Talk about the role of avoidability in the provision of public goods.

Here’s the point. If the public good is avoidable, you can increase the user tax (by bundling ads) and trust that those who don’t value the public good very much will stop using it. Given the level of the tax it would be inefficient for them to use it. Knowing that this inefficiency can be avoided you have more flexibility to raise the tax, effectively price discriminating high-value users.

YouTube videos are a nice example of avoidable public goods. You don't have to watch them, but you can and I'll have a hard time preventing you from pirating the video if I try to charge you for access. Consistent with Ely's theory, YouTube videos are also largely ad-sponsored.

Educational Attainment and Simpson's Paradox

Here's Paul Krugman on the educational performance of Texas schools:

But here’s the thing: While low spending may sound good in the abstract, what it amounts to in practice is low spending on children, who account directly or indirectly for a large part of government outlays at the state and local level.

And in low-tax, low-spending Texas, the kids are not all right. The high school graduation rate, at just 61.3 percent, puts Texas 43rd out of 50 in state rankings. Nationally, the state ranks fifth in child poverty; it leads in the percentage of children without health insurance. And only 78 percent of Texas children are in excellent or very good health, significantly below the national average.

I came to this post from a link from Cafe Hayek to a thorough post by someone named iowahawk, who had an interesting response to Krugman:

Perhaps because a state's "average ACT/SAT" is, for all intents and purposes, a proxy for the percent of white people who live there. In fact, the lion's share of state-to-state variance in test scores is accounted for by differences in ethnic composition. Minority students - regardless of state residence - tend to score lower than white students on standardized test, and the higher the proportion of minority students in a state the lower its overall test scores tend to be.

Please note: this has nothing to do with innate ability or aptitude. Quite to the contrary, I believe the test gap between minority students and white students can be attributed to differences in socioeconomic status. And poverty. And yes, racism. And yes, family structure. Whatever combination of reasons, the gap exists, and it's mathematical sophistry to compare the combined average test scores in a state like Wisconsin (4% black, 4% Hispanic) with a state like Texas (12% black, 30% Hispanic).

The post by iowahawk goes on to compare tests scores by race between Wisconsin and Texas for a whole suite of comparisons of educational performance between the two states (broken down by race). Of the 18 comparisons (race-grade-specific test score by state), 17 of them favor Texas.

This reversal of trend is a phenomenon known as Simpson's paradox:

In probability and statistics, Simpson's paradox (or the Yule-Simpson effect) is a paradox in which a correlation (trend) present in different groups is reversed when the groups are combined. This result is often encountered in social-science and medical-science statistics, and it occurs when frequency data are hastily given causal interpretations. Simpson's Paradox disappears when causal relations are brought into consideration (see Implications to decision making).

The picture from Wikipedia is nice too:

To draw the analogy to the picture, Krugman was reporting along the downward-sloping dotted black line; iowabuck was reporting along the colored (red and blue) upward-sloping lines.