Marc F. Bellemare Posts

I will be teaching the last quarter (i.e., half-semester) of our first-year graduate econometrics sequence this year. This of course means that I will be teaching causal inference.

To do so, I am using the second edition of Morgan and Winship’s wonderful Counterfactuals and Causal Inference, which features a wonderful discussion of the stable unit treatment value assumption (SUTVA).

Many people who were trained in econometrics prior to the Credibility Revolution are not familiar with the acronym SUTVA, and even the full name “stable unit treatment value assumption” can sound more confusing than not. In economics, people sometimes refer to it as the “no-macro-effect” or “partial equilibrium” assumption.

What SUTVA says, basically, is that for a treatment D and and outcome Y, the value of D for individual i in time period t should should not have any effect on the value of Y for individuals who are not i in any time period t or for individual i in any time period that is not t.

Put more simply: That individual i gets treated in period t should have no effect on any other individual’s outcome at any given time, nor should it have any effect on that individual’s outcome in other time periods.

Put yet more simply: There should not be any spillovers.

The SUTVA can be extremely difficult to satisfy, and as with many other assumptions, though it might be feasible to rule out certain types of SUTVA violations, it may be difficult if not impossible to rule them all out.

In Bellemare and Nguyen (2018), for instance, we were interested in the relationship between farmers markets and food-borne illness in a given state in a given year. In an attempt to rule out contemporaneous spillovers from neighboring states, we controlled for the average number of farmers markets in neighboring states, but this did not help with any potential spillovers from year to year, or across states from year to year, no matter how unlikely they are.

In preparing my other graduate class–microeconomics of agricultural development–this semester I read an article which does a wonderful job of testing for SUTVA violations. In their 2019 article investigating the puzzle of “sell-low, buy-high” behavior (i.e., the phenomenon whereby smallholders sell their crops at low prices around harvest time, only to buy the same commodities later in the year at high prices), Burke et al. test for SUTVA violations by randomly varying the intensity of a randomly assigned treatment.

This double randomization allows first to estimate the impact of their treatment, which consists of a loan at harvest time, and then to estimate the impact of treatment spillovers. The idea behind the latter is that if SUTVA holds, the estimate of the treatment effect should be invariant to how many people receive a loan within a given community.

Burke et al.’s findings are telling: When few people are treated in a given community, receiving a loan at harvest reduces the extent of “sell-low, buy-high” behavior and increases the welfare of smallholders via an increased use of storage. But when many people are treated in a given community, smallholders are not significantly better off, since the use of storage is not more profitable.

As I said above, testing whether SUTVA holds can be extremely difficult, if not impossible. Burke et al. randomly varied treatment intensity to get at whether the SUTVA held, but not everyone can do so. Testing whether SUTVA holds can be particularly difficult with observational data. But this need not doom one’s findings. One way out of this is to admit that one cannot test for SUTVA, and that one’s treatment effect estimate should hold for “similar situations,” which ultimately limits external validity.

In Burke et al.’s case, had they not varied treatment intensity and only offered loans to small proportions of smallholders in each community, this would have meant saying that the treatment effect should hold in other situations where only a small proportion of smallholders are treated in each community.

I will be co-teaching a course titled Advanced Econometrics: Recent Methods and Issues at the University of Copenhagen from June 22 to 26, 2020 with my colleague Arne Henningsen. Though the link lists Arne as the instructor, I will be teaching the lecture part of the course, and Arne will be teaching the lab part of the course.

If you are interested in taking the course, enrollment is open to students outside of the University of Copenhagen, and as of writing, registration is about $145, which is a bargain (though if you do register, you are obviously responsible for your travel and accommodation costs, but Copenhagen is lovely in June).

The course is not identical to the course Arne and I co-taught in May 2018 at Copenhagen, though it will certainly share some similarities. For starters, because I am teaching the entirety of Morgan and Winship (2015) to our first-year PhD students this semester, there will be a lot of emphasis on the nuts and bolts (i.e., potential outcomes model and directed acyclic graphs) of causal inference. Second, we will also update the material by covering recent papers which have been published since we last taught the course. Third, I will be holding office hours every day, and I will be happy to discuss your research project in detail with you.

Here is the course description:

Since 2015, I have served as co-editor of leading field journals in agricultural economics almost continuously, first at Food Policy (2015-2019), and now at the American Journal of Agricultural Economics (officially since January 1, but I started handling manuscripts at the end of July), where I am slated to serve until the end of 2023.

Both those experiences have been hugely rewarding.

Both those experiences, however, also come with their fair share of frustrations.

Perhaps the worst aspect of editing a journal is dealing with would-be reviewers who are at once always-takers and never-givers (ATNGs)–that is, those academics who just love to submit to a journal but never have time to review for it.

The behavior of ATNGs is all the more annoying when I see bright young academics ask #EconTwitter how many reviews is too many for an assistant professor, because they have done one per week since the start of the calendar year and they feel like they aren’t really in a position to say “No” to journal editors–who may eventually get asked to write external review letters for those same young academics.

The behavior of ATNGs imposes a huge externality on those who (feel like they) cannot say no. Speaking with colleagues who also serve as editors at the AJAE and elsewhere, this behavior is much more common than most people suspect. And lest you think that there is some kind of editor fixed effect at play, the same ATNGs keep coming up when comparing notes with other editors in my area of research.

Recently, I discussed this with one of my mentors, who has extensive experience editing journals. His solution has been to directly tell ATNGs that for the peer-review system to work, people have to review in addition to submit, and that he will not be sending out any of their papers for review until they start reviewing for him. After all, for the system to work, for every paper of yours that gets sent out for review at a journal, you should be prepared to do two or three reviews for that journal.

As such, and because I believe in an equitable division of labor when it comes to peer review, I am seriously thinking of adopting the same policy for those manuscript I handle at the AJAE.

One concern that arose when discussing that policy with others was “Doesn’t it unfairly penalize the coauthors of ATNGs?” There is no doubt it does, but the hope here is that those same coauthors will put pressure on their ATNG coauthors so that those ATNGs become better citizens of the profession.*

All of my time away from home is spent in an academic department or in volunteer organizations, so I am painfully aware of the fact that in the absence of incentives, it’s always the same people who show up to do the work. But as an economist, I also know that when they are available, incentives work: Going back to my mentor, he told me that after he’d initially adopted the aforementioned policy toward the two ATNGs he had to deploy it with, one of them stopped submitting to the journal he edited altogether, and the other started reviewing ipso facto. From a social-welfare perspective, either outcome is better than having to deal with ATNGs.

* Alternatively, “Won’t we be missing out on good manuscripts if we do that?” Again, no doubt, but there is a considerable supply of excellent manuscripts–there are way many more of them than we can ever hope to publish–and I am happy accepting those manuscripts that are sitting right at the margin.