27 July 2011

Everyone hates adultery

John Sides and Matt Yglesias delve into the General Social Survey to see why people's attitudes toward adultery have changed.
Hester Prynne by Flickr user Billhd

The GSS is great; it may be my favorite dataset of all time. And I remember the first time I sat down and started playing with it I immediately gravitated to the variables about social behavior--extramarital sex, premarital sex, pornography, gay sex, and so on. Political scientists hardly ever get to play with these sorts of variables, and guys who do International Relations absolutely never have time to wonder what causes adultery. And Sides, like Douthat and Yglesias, is right to be shocked at the levels of support for extramarital sex--it is striking the first time you plop these into Stata to see that your parents' or grandparents' generation enjoyed a bit on the side.

Sides observes that more-educated Americans have gotten less accepting of adultery, and speculates that the availability of divorce has something to do with it. Yglesias notes that an alternative theory is that female empowerment has made women less reliant on breadwinners, and so the "marriage market" may have allowed them to find more suitable mates and enforce better behavior by holding out an exit option.

I think these are both plausible theories worth investigating. But I want to add some data and some thoughts to this debate. What follows uses only descriptive statistics (for now), so no interpretation is needed, just some careful thought. But I want to drive down one main point: Adultery used to be at least somewhat popular, but everyone hates adultery more than they used to, and this shift has affected practically all subgroups over the past forty years.

First, let's take a look at some additional data. The two charts below show shifts in opposition to adultery by sex and by race over the period 1972 to 2010.

First, a couple of notes. I follow Sides in defining opposition to adultery (and, yes,  I am using the shorter and judgmental term) by using the GSS question XMARSEX. (By the way, this is how we refer to GSS variables at my department--"XMARSEX," "PORNLAW", "HOMOSEX", etc. Way cooler than standard variable names like "V16".) In this case, I am conservative: Opposition to adultery includes only those who say adultery is always wrong.

Second, we should be aware that the GSS responses constrain our ability to answer these questions. What we want to know is under which circumstances people believe adultery is acceptable, but we merely know if they think it is "almost always" or "sometimes" wrong, or "not wrong at all." It is possible that the categories we're measuring have changed--that the person who thought in 1975 that extramarital sex was almost always wrong would believe that given today's divorce laws that it is now simply wrong to engage in affairs. There are strategies to cope with challenges such as these, but I'm not going to get into them now.

Third, we should always be aware that America has changed a lot in the past 40 years. In 1972, only 11 percent of respondents had a college degree; in 2010, 29 percent of respondents did. Similarly, in 1972, about 84 percent of respondents were white; in 2010, only about 76 percent of respondents were. (That's one reason why I just use "White" and "Black" as categories in the race chart--there aren't enough observations to support finer-grained categories across such a long time period.)

Getting back to the charts with these caveats in mind, though, we can see that the same picture that John held out is broadly true: even groups (like men) that used to be favorable to adultery are no longer supporters. The same pattern can be seen by looking at religious affiliation, which I present in two ways. The first looks at Protestant versus Catholic attitudes and the second at all respondents who view themselves as religious versus those who have no religious preference (e.g., atheists and agnostics). (Again, data limitations prevent me from displaying anything more fine-grained.)

Here we begin to see an interesting pattern. The shift in societal mores has affected even atheists and agnostics, contrary to what we might expect if we get all of our news from Glenn Beck. Secondly, although nonreligious respondents are more tolerant of deviations from marital fidelity, the gap is narrowing quickly; nonreligious respondents are now almost as willing to condemn adultery as Catholic respondents were in 1972.

Just for fun, I also looked at a partisan breakdown.

Although there is a widening split between the parties on this issue (and others), nevertheless Democrats and Republicans alike have grown less tolerant of adultery, at least at a mass level.

Given the relationship of adultery to marriage (long recognized by playwrights among others), we might want to investigate whether those who are married have different ideas than the population as a whole. A plot of opposition to adultery by marital status reveals a surprising pattern. In this case, we see that although married respondents have always been intolerant of adultery, divorced/separated respondents and never-married respondents have quickly caught up.

Note that fewer than half of single respondents in 1972 thought extramarital sex was "always wrong," which explains Mad Men. Very interestingly, in the early 1970s divorced respondents were fairly accepting of extramarital sex, but over the past few years their attitudes have converged on those of married respondents a generation ago. (One wonders if there isn't a natural ceiling to how strongly divorced respondents will condemn adultery, since some of them, at least, are presumably divorced because of an affair.)

Finally, I looked at whether levels of workforce participation by women have tracked with changes in perceptions on adultery. The first chart takes women who are working either full or part-time and compares their attitudes with women who are not (e.g., laid off, never working, retired, and so forth).

Here, we can see that there is support for a modified version of the Yglesias hypothesis. If the effect of women getting jobs is to make them more likely to demand marriage equality and fidelity, than that effect is recent. In the 1970s and 1980s, women who worked approved of adultery at nearly the same rate as men.

 However, there does seem to be some support for the idea that male attitudes have changed. The chart immediately above compares the attitudes of men whose wives work full- or part-time with those of men who are unmarried or whose wives do not work. Whereas there was practically no difference between those two groups throughout the 1970s or even the George H.W. Bush administration, a wide gap opened up during the Clinton-Bush administrations. (It remains to be seen whether the steep decline in 2010 is a blip.) This is consistent with Yglesias' (girlfriend's) hypothesis: male attitudes have shifted faster and more consistently than women's.

Finally, I want to point out that the GSS is sponsored by the National Science Foundation. This is what federal support of social science underwrites. It's critical to have these data in uninterrupted time-series, and it's essential that guys like Tom Coburn not be allowed to take away funding for such projects.

13 July 2011

Number One for 13 July 2011

There's only millions that lose their jobs and homes and sometimes accents / There's only millions that die in their bloody wars, it's all right
"Ping Pong," Stereolab

11 July 2011

What do professors do?

The question, from the Hon. Mr. (Matthew) Cameron [Yglesias blog understudy]: How can we raise the teaching productivity of the university?

The answer: The quickest route is to sacrifice research.

I think that there's a widespread misunderstanding of what professors actually do and what universities are actually for. Teaching is secondary. This is not true by biomass--the bulk of tertiary education institution are, indeed, devoted by teaching--but in terms of societal value research is the primary goal and justification of the academic enterprise.

Let's unpack the fallacy. Cameron argues a point that a lot of people find intuitively appealing: Universities are soooooo inefficient, because they use large in-person lecture courses to teach! We should just put those online and use the savings to drive down tuition costs to help the Struggling Middle Class and make college more accessible for the Honest Working Classes. (I think all of this is important, so I'm not mocking the SMC and the HWC themselves, but rather pundits'--often Ivy alumni who frankly don't know many authentic SMC and HWC members--invocation of these mythical creatures.)

Consider how Cameron phrases the difficulties:
Universities have little reason to cut costs because their reputations directly benefit from higher per student academic spending. So even if a school achieves cost savings without sacrificing quality – say, by replacing large, intro-level lectures with online courses – it will be regarded as less prestigious by many ranking methodologies. ... inally, university faculty view online technology as a threat to their role at the heart of the higher education system. This was evident during an exchange between George Mason University Prof. Tyler Cowen and Stanford University Prof. Tim Bresnahan at yesterday’s conference. When Cowen raised the possibility of universities employing fewer professors once online courses are widespread, Bresnahan responded defensively by asserting that he does more than just teach.
Cameron then lays out what he sees faculty as doing:
Obviously, Bresnahan has a point – the specialized expertise and personalized guidance that professors can convey to students in higher-level college courses truly is indispensible. For entry-level lectures with hundreds of students, however, faculty members often don’t do much more than teach. They don’t grade papers, they don’t meet their students and they aren’t able to delve into the finer details of the subjects they teach. These classes aren’t just a waste of students’ money, however; they’re also a drain on professors’ time. If they were freed from their obligation to teach such classes, professors would be able to devote more effort toward their niche in the higher education system – stimulating students’ intellectual curiosity through personal interactions and engaging learning experiences.
Here we see the thinking behind the critique of the large lecture course from the point of view of those whose only engagement with academia has been as a student:
  • Professors are primarily teachers;
  • teaching is best carried out in face-to-face interactions;
  • large lecture courses make it hard for professors to have face time with students;
  • ergo, large lecture courses are a waste of time.
There is a corollary argument for replacing these courses with online courses:
  • The Internet is cheap, and allows for on-demand scheduling;
  • Students from the HWCs and SMCs are motivated and disciplined;
  • Online courses suffer from all of the disadvantages of large lecture courses (no face time, no instructor engagement, etc) but at least they are cheaper to provide;
  • Universities will pass on all cost savings from eliminating large lecture courses to students;
  • Universities will be unharmed by losing those tuition dollars;
  • ergo, let's move large lecture courses online.
These arguments collapse at several points because their assumptions are valid. The argument for online courses is staggeringly weak. In the first place, the success of the University of Phoenix belies pundit optimism about distance education. Students in online courses have higher drop-out rates than their in-person equivalents, and universities have no reason to pass on cost savings to students. Indeed, if universities did have a reason to do so, then the adjunctification of higher ed would have been accompanied by plummeting tuition costs. But I am less interested in those reasons than in the wildly naive view about what it is professors do and how that conditions this debate. When my non-grad school friends and my family ask what I plan to do after finishing my doctorate, they invariably ask if I plan to teach. I invariably respond that I would, in fact, very much like to be a professor. But I never use the verb "teach" in describing that position.

I love teaching. I think I am good at it. I work very hard at doing well at it. But given a choice between being a mediocre teacher and a great researcher, or a great teacher and a mediocre researcher, I would take the former every time. Every time. Because if I just wanted to teach, there are many more lucrative and less demanding ways to do so--most of them involving majoring in education as an undergraduate and getting a better-paying job in a nice suburban school system or a good private school. (Yes, the BLS shows that political science "teachers" earn more than secondary school teachers, but that does not account for wages foregone--which can be substantial if you take five or six years to finish your degree--nor the survivor bias for university salaries: all of the washouts have already washed out of that pool, because for university instructors tenure is a privilege, not an entitlement.)

I don't think that the choice is that stark. And I think that, frankly, teaching is not really as hard as it seems. Yes, being the bestest teacher in the whole wide world is very tough, but that is to say that giving Steve Jobs-level presentations is incredibly more demanding than giving a very good presentation. Acquiring a relatively high level of competence seems to be more a matter of discipline and minimal training than of massive investment (certainly less than, say, learning game theory). (Veteran professors are welcome to disabuse me of my naivete.)

Yet that is almost irrelevant. Granted that universities--all of them, even Harvard--need some faculty to work hard at teaching, the real value-added from universities does not come from teaching. It can't, by definition. Both the best and the worst pedagogue in the world alike are limited by how good their subject matter is. There can be no calculus teachers without calculus, no physics teachers without physics, no political science teachers without political science research. Who cares how well we are teaching if what we are teaching is wrong?

And, by definition, only research can be progressive and expand our capabilities and understanding. But the value of humanity's understanding of a subject is bounded by the most perceptive, not the mean. When the British astrophysicist Arthur Eddington was asked how many people understood his theory of the expanding universe, he thought for a moment before replying, "Perhaps seven." Professors are often criticized or mocked because their research is so obscure, but it is precisely that obscurity which often leads to breakthroughs with startlingly practical applications.

This is at the heart of Professor Bresnahan's response to Cowen that he does more than just teach, and it is why Cameron has so badly misunderstood what the professoriate does. It is not a question of "the specialized expertise and personalized guidance that professors can convey to students in higher-level college courses." It is the fact that that expertise did not spring forth fully-formed from Zeus' head. Rather, it was hard-won, mostly by professors who were probably notoriously bad teachers.

And that is why weakening the edifice of the university by forcing its scholars to become pedagogues first and researchers second, if at all, is so frightening. Research will continue, with or without the university. But research outside of academia is proprietary and narrow, and whole disciplines--especially the social sciences--will vanish or become so transformed as to be unrecognizable. (Think of the niche field of "retail anthropology.") Universities exist to provide public goods, and piecemeal "reforms" such as blindly sacrificing large lecture courses and the cross-subsidization they provide both to research and to those much-ballyhooed higher level courses will profoundly alter the production and transmission of knowledge.

Number One for 11 July 2011

The less I say the more my work gets done:

Elton John, "Philadelphia Freedom," a song for which I have a totally inexplicable fondness:

08 July 2011

What is an academic poseur?

The question, from a backbencher: You've laid out the case for bringing back the insult poseur. Are there poseurs in academia?

The answer: Are there poseurs in academia? Are there animals in the zoo?

A poseur wants you to think that he's genuine when he's a fake, and knows it. Consequently, an academic poseur wants you to think he's a genuine scholar when he's just faking it.

Paul Ryan is a policy wonk poseur.

I think that it should be self-evident that this is a common type, not only among graduate students but faculty -- even quite senior faculty.

The distinction between knowingly faking something and just not being good at something is critical. It's the personality version of plagiarism: wanting the benefits of expertise without the hard work of developing it. Empirically, however, the poseur is even worse at his job than the plagiarist is at his. The plagiarist copies expertise, but the poseur may not quite know whose expertise to copy.

How can you tell the difference? The biggest difference is that the poseur wants you to think he understands, say, deconstructionism or maximum likelihood estimation. And he'll even know many of the keywords, and he'll do a lot of the low-cost things that you'd do if you were a serious student of the subject. (In the quant methods version, this would be signing up for the Gary King twitter feed; I don't know what it would be for the po-mo stuff, but let's say that it's wearing only black.) And he may even ask questions--"How are you handling endogeneity?", "Did you try robust standard errors?"--that are very similar to the ones that someone who really knows his stuff would ask.

But on close interrogation, you'll note that the questions are always the same, and that his discussions of the subject always hinge on lore, not logic. (All academic fields have rich traditions of lore, which is the oral culture of the discipline. Lore reflects the actual practice of the bulk of researchers working in a field. Typically, lore is to the discipline's formal methodology as the religion of the faithful is to the theology of the clergy.) And that lore itself may be outdated: anyone who claims to like methods but has a preoccupation with R-squared, for instance, probably doesn't understand what R-squared actually means, and certainly hasn't done the very basic reading on the subject of interpreting linear regression.

There will be other signs: interpreting logit regression results without understanding that MLE coefficients don't represent a constant marginal result is a trivial matter, but a common one. Another will be recommending the newest gee-whiz method in a case where it's not really appropriate--but it will impress the senior faculty around the table, who themselves have never heard of the new method and are sure to think that anyone who has is a frood who really knows where his towel is.

By now, you may be wondering if you are a poseur. It's possible. I have been a poseur; I have denied my poseurness; I have overcome it. And the secret to overcoming it is the essence of Socratic wisdom--admitting that you know nothing--leavened with a bit of Buddhist humility (that is, letting go of your attachments to impressing others). But if you believe that there is a royal road to understanding, then you should know that you are a poseur.

Number One for 8 July 2011

  • The best paragraph I read yesterday:
    This is why I got into the newspaper business, to be able to write like this and get paid for it. This is what newspapers used to do — some of them, anyway. We would publish pieces like this on a Sunday, and no one would ask, as they would in later years, “But what’s the utility here? Can we include a sidebar on the sperm bank’s hours and rates? This seems awfully long. Are we being self-indulgent here? I mean, really, who cares?”
    [Nancy Nall]
  • Courtesy of the Hon. ZW: Eric Mazur on how to teach without lecturing
  • How to respond to criticism [Duck of Minerva]
  • Is partisan polarization a consequence of U.S. relative economic decline? [Matthew Yglesias]
"Crepuscolo Sul Mare", Piero Umiliani

07 July 2011

Are reruns dead?

The question, from a backbencher: Netflix now has the distribution rights for all of the Star Trek television series--save Deep Space Nine, inexplicably. What does this say about the future?

The answer: It means that reruns are dead. It also means that the future will be nothing like Star Trek.

Over the past forty years, Star Trek reruns and marathons on cable channels and low-powered TV stations have been a staple of American life. They are so mainstream that even Transformers: Dark of the Moon (co-starring Leonard Nimoy, in his second appearance as an evil Transformer) features a joke about them. (The clip is about two seconds long; I identified the episode--"Amok Time"--halfway through it.)

But with Netflix, why bother showing reruns of Star Trek at all? Netflix Streaming is cheap--less for a year than for cable for a month--and easier to use than a DVR. For one thing, Netflix works over devices that are slightly more portable than a 48-inch screen. (After all, there's a reason why 80 percent of online streaming is over iOS devices.) The immediacy of the delivery, and the fact that Netflix remembers where you left off, is pretty much a killer app for me.

Immediately, of course, this is going to kill the TV DVD collection. Why bother? In an earlier age, I bought the first five seasons of Scrubs and the first four of The West Wing. These days, however, I'm pretty sure I wouldn't bother--without checking, I'm unsure if either show is on Netflix, but in either case I'd wait. I watched those DVDs pretty regularly when I had a Real Job, and that meant that I've watched the average disc in that collection twice. Maybe three times, in the case of the first seasons of both.

The same calculus must apply to cheap TV content. What is going to attract eyeballs to watching Patrick Stewart make it so in a bad episode--and Next Generation had a handful of those, as you may recall--when Netflix allows us to watch only the good ones and then recommend to us new shows that we never would have heard of without the recommendation engine?

What Netflix streaming is going to do, then, is accelerate the future of entertainment. And the future of entertainment will literally look a lot like the past. Whether it's Alyssa Rosenberg discovering Cheers or me reliving my own private 1980s with the remastered original series*, pop culture in the world of tomorrow will be forever competing with the past. That's good in many respects--the future The Wire will have to be that much better, since it will be competing not just with whatever else is on but with The Wire itself--but bad in many others, since the production of new cultural content will largely become either bad remixes or new dreck. In sum, whatever orgastic visions of the future of pop culture we may once have had, we will instead be borne back ceaselessly into the past.

* I'd like to say that I am astonished by how good the remastering and re-creation of the special effects are. The cheesiness is not entirely gone, but the vibrancy of the colors and the freshness of the score is really impressive.

Number One for 7 July 2011

You got a thing about you, I just can't live without you:
  • Good advice on handling journal submissions and budgeting your time [FPArena]
  • So far, the best book I've read this year [Springer]
  • Old but still reassuring: China's aircraft carrier sucks [Wired]
  • Kevin Drum sums up more of the Obama administration than he may have intended: "Obama isn't doing this because he has to. He's doing it because he wants to."
  • Let's take note of Georgetown Professor Hans Noel's recent fame. If the conceit of this blog is that I am the prime minister, then Hans was very recently its sovereign (viz., my boss). So, an extra-special Noel in July roundup:
    • Columbia Journalism Review
    • The Monkey Cage
    • Enik Rising
    • Matthew Yglesias
    • Three-Toed Sloth, notable also for this para:
      On the other and more positive side, we have it seems to me lots of examples of successfully pursuing scientific, causal knowledge in fields where experimentation is even harder than in sociology, such as astronomy and geology. Perhaps explaining the clustering of behavior in social networks is fundamentally harder than explaining the clustering of earthquakes, but we're even more at the mercy of observation in seismology than sociology.
      As cheerful as this prognosis is, it does seem to gloss over the problems inherent in studying the activities of self-aware and calculating (or norming) agents, especially agents who might also be reading our articles.
    One thing that I think that CKNZ should stress in their discussion--and Hans does get at this in his discussion of the "terrain" of horse races--is that many of the journalistic tropes about presidential campaigning do not apply to the general election (cf King and Gelman 1993) but they are in full force in the "invisible primary." I should also say that I love CKNZ because it does help bring back the kind of engagement with elite, backroom politics that I loved about, say, The Making of the President 1960 (as partial--in both senses of the word--as it was) and the grittiness of What It Takes.

The Turtles, "Elenore"

06 July 2011

Am I ready to teach?

The question, from a backbencher: The Rt. Hon. P.M. will begin teaching his first solo university course next week. Is he ready?

The answer: As much as can be hoped.

The logistics are pretty well done. I spent the Fourth of July indoors, revising my syllabus for the Introduction to International Relations course I'll be teaching in a few days. I ordered the textbooks for the course months ago, so my biggest questions were whether I had to add too many additional readings (not really) and which of the dozens of articles I'd read on nuclear war were suitable for freshmen and sophomores. (Not many.) In what may yet prove to be a triumph of whimsy over experience, I also made Dr. Strangelove an "optional" reading--or, rather, viewing--for that day, which means that I now have to reserve a screening room.

What I'm most nervous about, of course, are the basics--whether the course is paced well enough, whether I can actually recall some of the treacherous details (like the precise ordering of the payouts of Prisoner's Dilemma), whether I'll be able to connect with a remarkably diverse group of students. The operationalization of this nervousness has come down to worrying about trivial things, like what template to use for my Keynote presentations or whether I can trust the University to consistently have technology unlocked in my room.

Behind this is my desire to be the Ultimate Teacher, who gives the sort of presentations that a cyborg melding of Randy Pausch, Robin Williams in Dead Poets Society, and Steve Jobs unveiling a new iPad would only dream of. This is unlikely to happen, although I think that I am a competent lecturer, for two reasons:
  1. I am a competent lecturer, but not THAT great.
  2. Giving a course is not like giving a presentation.
The first reason is easy enough to understand. The second is, I think, something that people misunderstand for reasons of both left and right deviationism. The right-deviationist attitude is that a course is essentially a transmission of ideas from the sage on the stage to the groundlings below. The objections to this are easy to list, and the most important is that this is not, actually, how people learn.

But the left-deviationist approach has just as many, if not more, flaws. It draws from the idea that courses are supposed to be some sort of egalitarian, Montessori-like exercise in self-development and growth. This, I think, might well be true, but practicable only in courses of, say, five or six--roughly the same size as graduate seminars, and for much the same reason. The expectations that this approach holds out are simply unrealistic. I have 42 students. I can't get to know them all as individuals in any sort of holistic manner in the span of five weeks; there simply isn't enough time. And at least some of the students, as a statistical regularity, will not be interested in sharing a deep learning experience--they would just like to pass.

So, this is the dilemma of the large lecture course. It's impossible to do much more than lecture for the bulk of the instructional time, but we also know that real, in-depth learning does not come from engagement with learning. Rather, as Richard Mitchell once noted, "It is not as we read the page that education illuminates us; it is when we look up." But I can't do that in the large lecture course. How, then, to avoid this Scylla and Charybdis? Well, in the first place, I do intend to take Andrew Gelman's advice about conference presentations: "Don't try to blow them away, just do something solid."

Some of my lectures are, I think, going to be pretty good. But I want them all to be good and thorough expositions of the important arguments that help students go beyond the reading and help them analyze the questions that we are dealing with.

In fact, that may serve as a nice mission statement for university lecturers: Don't teach the reading, teach the questions. We don't get into this business to engage with "The Literature," and I suspect that I am not alone in finding much of "The Literature"--that mythical, corpulent, ancient, ever-rotting leviathan--to be deathly dull. Rather, we find the world itself to be exciting, and the puzzles we try to solve to be fascinating.

This post has been nothing more than an excuse to link to Robert Morrison's talk on "The Lecture System in Teaching Science", which says everything I've wanted to say much better. So you should probably read that. But if you don't read the whole thing, at least read this:
What makes a teacher stimulating? Is it really the elegant presentation of a beautifully organized lecture? The students may admire a performance like that, and enjoy it as a tour de force; the lectures may be enormously popular and play to packed houses — but are admiration and passive enjoyment really what is wanted? What we really want to do is strike a spark in the students' minds. We want to reveal to them the beauty of ideas and concepts and rationality. The teacher and his personality play the key role in this. But it is not the teacher's wit and polish and delivery that are important. It is the teacher's enthusiasm for the subject that is enormously contagious. It is the students' seeing how a mind better trained than theirs approaches an intellectual problem. It is the intense pleasure the students get when they are led, like Socrates' slave-boy, to use, really use, their own minds. Surely, this is the kind of stimulation that we are looking for.

Now, like a real professor would, I'm going to go do research.

Number One for 6 July 2011

  • This post is the most popular I've ever written, thanks to inadvertent SEO: Are tornadoes scary? [PMQT]
  • China is moving up the value chain. [Time]
  • More ideas on increasing classroom productivity in large-lecture situations. [The Chronicle]
  • Does absenteeism affect learning outcomes? Apparently by as much as a full letter grade. And larger and mathier courses mean more absenteeism. Consequently, this economist calls for strict regulation:
    A generation ago, both in principle and in practice, attendance at class was not optional. Today, often in principle and almost always i npractice, it is. Perhaps a return to the old system would make a large difference to learning. There is no way to find out but to try.
    [Journal of Economic Perspectives]
  • Of course, access to good teaching is like access to good healthcare: Money counts. [NYT]
  • Going on the bookshelf, someday:Berk on Regression:
    Presumes at least minimal familiarity with the math and practicalities of doing a multiple linear regression. The point of this book is to explain very clearly what regression can and cannot do, and especially to drive home the meaning and force of all the assumptions which are required to make the machinery of statistical inference for linear regression work. These assumptions are, or ought to be treated as, scientific hypotheses, which need to be not just taken for granted, or even listed mechanically and then ignored, but supported. (Many of them are hard to even assert with a straight face about important kinds of real data, never mind back up.) As he rightly says, the requirements for using regression for causal inference are even stronger, and the common practice of ignoring these issues, or hoping that they'll go away if you just use instrumental variables, has nothing to recommend it. (However, the discussion of Judea Pearl's work on causal inference in section 10.5 seems to me to be somewhat superficial, and even to misunderstand Pearl's book more than a little.) Of course, as descriptive summary of a data set, regression has much to recommend it; but not necessarily more than newer methods of data-mining, which he considers briefly in the conclusion.
    [Cosma Shalizi]

02 July 2011

Return to form

Lifestyle blogging has long struck me as boring, but the past month has left my intellect and my energy too drained to attempt even something so desiccated as talking about the books I've read or the neat political science tricks I've learned.

What was most draining, strangely, wasn't the travel per se or the concentration that I've been giving to other projects, even though I've worked pretty hard on several of them. Rather, it was the sheer strain of meeting lots and lots of new people. It turns out that there's only so many times that I can give my name, my university affiliation, and a précis of my dissertation topic.

I've now returned to my comfortable cave, however, and that means that it's time to write. A lot. Just as there is a difference between composing great symphonies and writing production music, so too there is a difference between crafting top-notch prose and creating drafts of articles that explain variables and measurement. The latter version, in both cases, requires a strong back. And that is why I blog: it is the equivalent of pumping iron for hack academic writers.

I do feel, however, that my workflow has gotten rather better in the past couple of months. And a nontrivial portion of that improvement derives from using the iPad more strategically. I took both my Macbook and my iPad to the undisclosed location (Syracuse University) I spent most of the past month. It turns out that, save for statistics, this is a belt-and-suspenders solution. I only use plain text and Pages anymore when I have a chance; the iPad is perfect for both. And the iPad also now offers me every TV show I've ever wanted to watch via the Netflix--and the Netflix app seems to run more smoothly on the iPad than on the MB.

So look forward to more prose ground out over the coming months. Inshallah, some of it will even end up in journals read by as many as several hundred people.