Quarter of birth is not a good instrument! Hallo?

Arrrgh! After 15 years, it’s hard to believe that John Bound’s and my critique of Angrist and Krueger’s quarter of birth instrument (and the whole weak instrument literature that followed, plus a bunch of papers that specifically adress the AK 1991 QJE paper) has yet to make a dent. How can the Economist claim that

In an influential early example of this sort of study, Joshua Angrist of the Massachusetts Institute of Technology (MIT) and Alan Krueger of Princeton University used America’s education laws to create an instrumental variable based on years of schooling. These laws mean that children born earlier in the year are older when they start school than those born later in the year, which means they have received less schooling by the time they reach the legal leaving-age. Since a child’s birth date is unrelated to intrinsic ability, it is a good instrument for teasing out schooling’s true effect on wages.

WRONG!!! Quarter of birth meets neither the relevance (at least in AK’s preferred specification) nor the exclusion restriction assumption required for IV. See Kasey Buckle’s and Dan Hungerman’s excellent paper that, one hopes, is the death knell for any paper that claims quarter of birth is unrelated to outcomes except through the compulsory schooling/school age starting law mechanism. There’s also a very good paper by Rashmi Barua and Kevin Lang that shows that the compulsory schooling/school age starting law mechanism doesn’t meet the monotonicity requirements for a LATE interpretation of the IV estimate of the effects of school entry on outcomes.

Despite all this, Angrist and Pischke in their otherwise excellent Mostly Harmless Econometrics once again belabor the AK results and present them as if they are sensible estimates of the returns to education.

Why is this? How can a result which has for many reasons and by many authors been shown to have problems persist in being held up as a shining example of the usefulness of the IV technique? Part of the answer is that more than any other IV story (and every good IV paper has a story), AK’s story is really good. Incredibly clever. Easy to see in graphs. Believable. So, we (even I) want to think that AK’s instrument is sensible and good. Because if the AK story doesn’t hold, then lots of other IV stories are probably invalid. And with them goes the whole natural experiment movement.

Update:
(I posted a slightly different version of this to The Economist website.)

The Value of an M.A. Degree

There’s an interesting “Room for Debate” in today’s New York Times.

And here’s my comment on it.

Universities and Immigrants…

Thomas Friedman lost me completely when he endorsed the invasion of Iraq, and most of the time the things he says are pretty vapid. But today’s column is actually pretty good, if, as usual, lacking in a full appraisal of the situation. In particular:

I still believe that America, with its unrivaled freedoms, venture capital industry, research universities and openness to new immigrants has the best assets to be taking advantage of this moment — to out-innovate our competition. But we should be pressing these advantages to the max right now.

That’s probably true, especially the bit about research universities (being totally objective). American’s higher education system is the best on the planet.

This is also on-target, I think:

China is also courting trouble. Recently — in the name of censoring pornography — China blocked access to Google and demanded that computers sold in China come supplied with an Internet nanny filter called Green Dam Youth Escort, starting July 1. Green Dam can also be used to block politics, not just Playboy. Once you start censoring the Web, you restrict the ability to imagine and innovate. You are telling young Chinese that if they really want to explore, they need to go abroad.

We should be taking advantage. Now is when we should be stapling a green card to the diploma of any foreign student who earns an advanced degree at any U.S. university, and we should be ending all H-1B visa restrictions on knowledge workers who want to come here. They would invent many more jobs than they would supplant. The world’s best brains are on sale. Let’s buy more!

The current problem is that even the richest research universities (like Harvard) are cutting back. How long this will last remains to be seen, but the downturn in the stock market (and thus in the endowments of those rich universities) is causing problems in hiring. I am sure this also has had an effect on graduate student funding.

So, Friedman gets it right, but misses the broader effects of the crisis on higher education.

QJPS Style Guide — Required Reading!

I received today the best style guide for a journal that I have ever received… from politcal scientists, no less.

Here are a few excerpts (and my comments) from the style guide of the Quarterly Journal of Political Science:

Acknowledgments. Please be brief. Avoid hyperbole and effusive expressions of debts of gratitude to family, friends, pets, etc.

HA! I wish they’d also added that one shouldn’t include that craven caveat “All remaining errors are the responsibility of the author,” or somesuch stupid thing. Even worse, in my opinion, is the cryptic “The usual caveats apply.” Duh! Of course the errors are the responsibility of the author. If I give someone comments, they can take them or not… but it’s their name that’s on the byline, not mine.

Put another way — If you’re an economist (or political scientist), I’ll be happy to share authorship on any paper if you’re willing to let me take part of the blame if you’re found to have screwed up. Unless you’re Steve Levitt.

Reporting of Data

• Please use three significant digits in tables and text.

I agree. This is usually sufficient.

• We prefer the reporting of standard errors, because QJPS readers can divide. We
  frown upon stars and daggers not only because they are unsightly but also because
  QJPS readers have inalienable rights to choose their own critical values.

YES! I’ve been saying this for years (something I got from Gary Solon in grad school, I think). Ironically, the paper I submitted to the QJPS actually had asterisks in it… but only because we thought political scientists liked them. Now I know that the opposite is true, at least among the serious empirical political scientists.

• Because the alternative hypothesis β ≠ 0 is not as interesting as β ≥ 0, p-values should be one-tailed in most instances.

Here I disagree. It depends on what’s appropriate to the underlying theory being tested. A priori, I’m not sure you can say that one is more interesting than the other.

One correction, though. If the null is β = 0, then the strong inequality should be used in the alternative, not the weak inequality. What if the coefficient were identically zero, would you reject or not reject the null?

• In text and tables, avoid abbreviations in the names of variables. Modern typesetters can accommodate upper and lower case fonts and words longer than eight characters, so full descriptive words or phrases are preferred.

  •  Opaque: The coefficient for DINVTSHR is positive.

  •  Clear: The coefficient for Democratic incumbent’s vote share is positive

Again, YES! I hate it when people use variable names in their tables and in the text of their papers. You have to spend all your time reading the paper flipping back between the table that defines the variables (if there even is one) and the table you’re interested in. In my experience, the Industrial and Labor Relations Review is especially egregious in this regard.

So, hats off to Keith Krehbiel and Nolan McCarty, the chief editors of the QJPS. Everyone doing empirical work should adopt these guidelines, whether they’re in political science, economics, demography, public policy, or other fields.

“Toy Models” and “Stylized Facts”

I’ve been at a couple of different conferences over the last two weeks, both very different in content (immigration vs. law/econ) and style (20 papers vs. 7 papers over two days). This has given me a little time to ruminate over fad phrases in economics.

The one that seems to be running around these days is “toy model”. I’m not sure where this started, but I think it’s dumb. What do people mean when they say this? That’s is a partial equilibrium model? Then why not say that? It seems to me to be a way for empirical folks to say that they wrote down a model, but they don’t think it’s got much relation to reality or the empirical work that follows. If you write down a model, you should be willing to defend it. If you think it’s not very complete, then why do it? Just refer to it as “the model” and be done with it.

A phrase I hadn’t heard in a while, but which showed up at one of the conferences was “stylized fact”. I also don’t know where this got started, although I seem to remember hearing it a lot from Harvard and MIT grad students on the market when I was a grad student at Michigan. I have always wondered exactly what is a “stylized” fact. Does that me that it is somehow not true? Or that it’s a simplified version of reality? I am glad that this fad phrase seems to have goneout of fashion, because like “toy model,” I think it’s just dumb — one of those phrases that economists utter to show that they’re “in the club” that generally have little or no content.

Thankfully, I have never heard anyone say that they were going to employ a “toy model” to try to explain the “stylized facts”!

Why not inflation?

Paul Krugman writes in today’s NYT about inflation. In particular, he voices a sentiment that I’ve been thinking for awhile now:

So is there any reason to think that inflation is coming? Some economists have argued for moderate inflation as a deliberate policy, as a way to encourage lending and reduce private debt burdens. I’m sympathetic to these arguments and made a similar case for Japan in the 1990s. But the case for inflation never made headway with Japanese policy makers then, and there’s no sign it’s getting traction with U.S. policy makers now

.

The question is why not? Surely some degree of inflation would be good for the housing market, as well as the consumer credit markets.

Andy Kroll: Six Ways the Financial Bailout Scams Taxpayers

Andy Kroll: Six Ways the Financial Bailout Scams Taxpayers

Posted using ShareThis

This is why Timothy Geithner was a lousy choice for Treasury Secretary. I hope now that he’s got some help from Alan Krueger and others that there will be more transparency and less cronyism.

Debt as income substitute?

I don’t have any statistics at hand, but an enterprising graduate student could do this. I have been wondering lately, whether overall inequality in the US would have increased or decreased if you include borrowing from housing and credit cards over the last 10 years. To what extent did borrowing substitute for real wage growth, which we know has been pretty stagnant over much of the distribution.

This seems like the kind of thing the folks at Center for American Progress or the Economic Policy Institute would be interested in doing…

Without some sustained and across the board real wage growth, it’s hard to see how things will improve for most people, even once the housing market eventually picks up.

What’s wrong with single payer?

David Sirota hits the nail on the head with this piece in Salon:

In saying they can voluntarily slash $200 billion a year off the country’s medical bills over the next decade and still preserve their profits, healthcare companies implicitly acknowledged they were plotting to fleece consumers and have been fleecing them for years. With that acknowledgment came the tacit admission that the industry’s business is based not on respectable returns, but on grotesque profiteering and waste — the kind that can give up $2 trillion and still guarantee huge margins.

And…

That’s why the White House’s current posture is so puzzling. As the Associated Press reports, Obama aides are trying to squelch any single-payer discussion, deploying their healthcare point-person, Sen. Max Baucus, D-Mont., to announce that “everything is on the table with the single exception of single-payer.”

So it’s back to why — why Obama’s insurance-industry-coddling inconsistency? Is it a pol’s payback for campaign cash? Is it an overly cautious lawmaker’s paralysis? Is it a conciliator’s desire to appease powerful interests? Or is it something else?

So, Obama, which is it?

The immigration debate: is it possible to be objective and nativist at the same time?

A few weeks ago George Borjas talked about how the Center for Immigration Studies has come under attack from the Southern Poverty Law Center for its anti-immigration stances.

George cites a well-known labor economist who thinks that CIS’s output will be more accurate than refereed journals because of all the folks gunning to discredit CIS. I’m not sure I buy that arguement. Besides, a very well-known immigration economist that I know is just as skeptical about CIS’s work because of their very obvious nativist position.

That said, I think Steve Camarota, the poli-sci Ph.D. who produces most of CIS’s Backgrounders, is a smart guy, and affable, too (I had the good fortune to debate with Steve awhile back at a function for William and Mary’s Christopher Wren Society).

This all points to the question as to whether we stop believing research when its producer starts to take political stands, or when it is produced by a “think tank” with an obvious perspective. I think places like Brookings do a better job of this than, say, CIS, but that may be because I am more likely to see the world from the same perspective that Brookings does.

For me, I guess it comes down to whether I can predict a priori what someone is going to say about a particular topic. If the Cato Institute suddenly came out endorsing universal health coverage, it would be news (and I make take what they say more seriously, because would run counter to my expectations).

I once had some of my research used as talking points by the Republican National Committee (back when Pat Buchanan was running for president) because it showed that immigration had an impact on the wage structure in the US. Despite the fact that I hated being a poster child for the RNC, the data said what they said. I couldn’t (and wouldn’t) change that just because it ran counter to my (usually) liberal attitudes. Maybe the numbers that CIS produces are accurate, but you have to wonder whether they always tell the whole story, even if it doesn’t suit their agenda.