Tuesday, August 26, 2014

Learning about what observed variables you need for selection on observed variables to be a reasonable assumption

I like this paper a lot, both in the narrow sense that it presents interesting and useful results that I have already been citing, but also more generally because it follows the path that I think the literature should follow but rarely does. That path takes claims about the important of selection on unobserved variables in particular contexts and puts them to an empirical test.
-----------------------------------------------------

Marco Caliendo, Robert Mahlstedt, Oscar A. Mitnik:

Unobservable, but Unimportant? The Influence of Personality Traits (and Other Usually Unobserved Variables) for the Evaluation of Labor Market Policies

Abstract:
Many commonly used treatment effects estimators rely on the unconfoundedness assumption ("selection on observables") which is fundamentally non-testable. When evaluating the effects of labor market policies, researchers need to observe variables that affect both treatment participation and labor market outcomes. Even though in many countries it is possible to access (very) informative administrative data, concerns about the validity of the unconfoundedness assumption remain. The main concern is that the observed characteristics of the individuals may not be enough to properly address potential selection bias. This is especially relevant in light of the research on the influence of personality traits and attitudes on economic outcomes. We exploit a unique dataset that contains a rich set of administrative information on individuals entering unemployment in Germany, as well as several usually unobserved characteristics like personality traits, attitudes, expectations, and job search behavior. This allows us to empirically assess how estimators based on the unconfoundedness assumption perform when alternatively including or not these usually unobserved variables. Our findings indicate that these variables play a significant role for selection into treatment and labor market outcomes, but do not make for the most part a significant difference in the estimation of treatment effects, compared to specifications that include detailed labor market histories. This suggests that rich administrative data may be good enough to draw policy conclusions on the effectiveness of active labor market policies.

http://ftp.iza.org/dp8337.pdf

Monday, August 25, 2014

The neighborhood lawsuit

The lawsuit described in this astounding Ann Arbor Observer article took place over access to a path in my neighborhood.

Wow. All those lawyer fees could have made for some block party. Or maybe some big notation to a more deserving group?

Full disclosure: we don't know any of the parties to the suit very well, but know the folks who shut down the trail better.

Friday, August 22, 2014

Michigan to play Washington in college football

This will be fun! Stories from a Michigan blog and from the Seattle Times.

The Michigan blogger neglects to note that Washington would have won the last match in the big house had Slick Rick not blown the clock management.

Hat tip: Jeremy Fox

Monday, August 18, 2014

Humans need not apply



An over-the-top but still interesting and entertaining video about capital-labor substitution.

The video does overstate the case: in recent decades the labor market managed to absorb all the folks who used to farm as well as large numbers of assembly-line workers, keypunch operators and the like. I think the takeaway is more about the value of general skills (e.g. how not to be a jerk, how to show up on time, how to manage) than about a future with no work.

Hat tip: Dan Black

Saturday, August 16, 2014

Killewald and Gough

Two sociology students from Michigan foolish and/or bold enough to have me on their committees (and now on to careers in academia) have won a best paper award of the American Sociological Association section on the family.

Congrats!

Friday, August 15, 2014

Ann Arbor history: streetcars

The Ann Arbor News on Ann Arbor's history of streetcars. I was surprised by the extensiveness of the streetcar network.

Thursday, August 14, 2014

An old mystery solved: My Sharona

I probably should have sorted this out a long time ago, but it turns out there actually is a person called Sharona behind the Knack hit song "My Sharona". Perhaps not overly surprisingly, she now sells real estate in Los Angeles. You can see the (SFW) single cover featuring Sharona here.

I saw the Knack in concert back when I was in high school. People thought (and wrote - I wish I still had the Seattle Times concert review) they were going to be the next Beatles. To encourage such thinking, they performed "Hard Days Night" as their encore. As it turned out, they fizzled after their second album.

Wednesday, August 13, 2014

In preparation for the upcoming academic year ...

... advice on how to look smart in meetings.

Some of these work in seminars too.

And, of course, as noted on instapundit, where I found the link, "to [actually] be smart, avoid meetings as much as possible. . . ."

Tuesday, August 12, 2014

Assorted links

1. Mocking the "50 Shades" movie trailer.

2. Sava's restaurant in Ann Arbor written up in the Toronto Star.

3. An update on Second Life.

4. The 400th anniversary of the logarithm.

5. Always wear your seat belt.

Hat tip on #2 to Christine Gribowski and on #5 to Charlie Brown.

Monday, August 11, 2014

NYT on treating addiction

I liked this NYT piece on alternatives to conventional abstinence-based programs for dealing with addition.

I've tried a few times to convince the students in my undergraduate program evaluation course that it would be interesting to read some papers from the related evaluation literature but they have not shown much interest.

My sense of the literature is that placebo effects and heterogeneous treatment effects both likely loom large in a way that makes forward progress on the scientific front difficult. It also seems to me that a treatment that requires you to, say, never have another drink has not really fully solved the problem.

Sunday, August 10, 2014

Another plagiarizing politician

Blue team candidate Frank Walsh drops out of the Montana senate race. The original NYT take-down is here.

Improving referee response times

What Policies Increase Prosocial Behavior? An Experiment with Referees at the Journal of Public Economics
Raj Chetty, Emmanuel Saez, László Sándor
NBER Working Paper No. 20290
Issued in July 2014

We evaluate policies to increase prosocial behavior using a field experiment with 1,500 referees at the Journal of Public Economics. We randomly assign referees to four groups: a control group with a six week deadline to submit a referee report, a group with a four week deadline, a cash incentive group rewarded with $100 for meeting the four week deadline, and a social incentive group in which referees were told that their turnaround times would be publicly posted. We obtain four sets of results. First, shorter deadlines reduce the time referees take to submit reports substantially. Second, cash incentives significantly improve speed, especially in the week before the deadline. Cash payments do not crowd out intrinsic motivation: after the cash treatment ends, referees who received cash incentives are no slower than those in the four-week deadline group. Third, social incentives have smaller but significant effects on review times and are especially effective among tenured professors, who are less sensitive to deadlines and cash incentives. Fourth, all the treatments have little or no effect on agreement rates, quality of reports, or review times at other journals. We conclude that small changes in journals’ policies could substantially expedite peer review at little cost. More generally, price incentives, nudges, and social pressure are effective and complementary methods of increasing prosocial behavior.

------------------------------------

So I took part in this experiment as a subject. I was in the group that received the offer of a cash incentive to complete their report within four weeks. A couple of days before the four-week deadline, I took the paper out of the "to review" stack and did my report out of order relative to my usual first-in, first-out rule. Apparently, given the summary of results in the abstract, there are not enough people like me for this equilibrium effect to show up in a statistical sense in the data.

Saturday, August 9, 2014

Movie: Lucy

What to say about Lucy? Scarlett's performance in the lead role is, to quote the NYT reviewer, "improbable but somehow perfect" and very much the strength of the movie. Beyond Scarlett, I am less enthused than the NYT. There is way too much explanation - the movie's approach is much too reminiscent of the "Dukes of Hazard" TV show with its omnipresent narrator for dullards. A less obvious approach would have made for a better movie. The dreamy graphics reminded me too much of the intro to ABC's movie of the week back in the 70s (or maybe an over-achieving PBS series) for something produced in 2014. Overall, this could have been a much, much better movie.

I was entertained that the bad guys were from Taiwan rather than mainland China, presumably to increase ticket sales in mainland China. Indeed, this is sort of the perfect movie (rather like the Bourne and Bond franchises) to maximize worldwide sales by including characters from North America, Europe and Asia.

Recommended, but just for Scarlett.

Friday, August 8, 2014

Thursday, August 7, 2014

Pre-season amazement

The "dry season" (my name for the part of the year without American football) came to an end last Sunday, and, more to the point, the first pre-season college football polls have been released.

Astoundingly, Washington makes the top 25 but Michigan does not.

Book: Half of a Yellow Sun

Chimamanda, Ngozi Adichie. 2006. Half of a Yellow Sun. Anchor Books

The title refers to the flag of the short-lived republic in Biafra in what is presently south-eastern Nigeria. The Biafrians fought a tribally-based civil war with the remainder of Nigeria starting in the late 1960s - I can vaguely remember mentions of it on the news when I was little. This novel covers the years leading up to the civil war, the war itself, and a brief period afterwards. As best I can tell, it gets the history right.

This is literary historical fiction, and the plot and characters are well done, but what I found most interesting was, first, the portrayal of social and intellectual life at an African university shortly after independence and, second, the serial displacement and gradual decline in living standard and mental state of the main characters as they are repeatedly displaced as Biafra slowly (spoiler, but you sort of know this already because there is no currently existing country called Biafra) loses the civil war.

Bottom line: recommended.

Bonus BBC article on Biafrans who still dream of independence.

Hat tip on the book: Jessica Goldberg

Wednesday, August 6, 2014

Best-selling books in China

Ozy provides a look at the on-line bestseller list in China.

I have been struck on all three of my visits to China at how few books (and bookstores) one sees. When I ask about it I get puzzled looks or the claim that people in China read relatively more ebooks than Americans.

Tuesday, August 5, 2014

Unemployment policy design: Australia creates some useful variation

Australia, it turns out, requires a giant (by US standards) number of applications each week by those on unemployment insurance, as well as making them perform community service!

What does that lead to? Fake applications of course, as discussed in this Guardian article. And fake applications waste the time and money of the firms that receive them.

The problem with using command and control, rather than prices, to influence behavior is that it is almost always impossible to control all the margins, which means you get strategic responses. Sometimes these are small enough to matter and sometimes they are not. I'd be curious to see a thoughtful and thorough cost-benefit analysis of the Australian application requirement.

Monday, August 4, 2014

Paul, behave!

Larry Kotlikoff tells Paul Krugman to stop calling people names. I would add that Paul's behavior is a public bad for the economics profession; even he would surely call for it to be taxed. Perhaps he should be required to pay large fines to the American Economic Association. Basically the idea is the same as the fines that pro athletes pay their leagues when they act off.

Via Greg Mankiw

Homophoneobia

The sad tale of man fired from a school (!) for promoting the understanding of homophones in Utah.

Hat tip: Adam Cole

Sunday, August 3, 2014

Saturday, August 2, 2014

Movie: Secretary

Secretary is a sort of lite SM story of love, acceptance and self-discovery. The acting by James Spader and (especially) Maggie Gyllenhaal is exceptional, and the movie does a surprisingly good job of combining dark comedy and sexual tension with heartfelt self-realization.

Said the New York Times reviewer back in 2002 when the movie was released:
I prefer to see ''Secretary'' as a wacky new-wave romantic comedy in which two lonely people locked inside their private fantasies discover a miraculous erotic harmony. In today's post-Freudian, do-your-own-thing era of free sexual expression, the movie stands to be a wholesome self-help fable about the unlocking of shame and its magical transformation into pleasure and personal liberation. So what if its vision is finally too good to be true? 
Yeah, that's about right.

Highly recommended. It's well worth the time on Netflix.