Marc F. Bellemare Posts

That’s the title of a wonderful new book by Anna Josephson and Jeff Michler of the University of Arizona who cover the ethics related to the entirety of the research process, from early research ideas to the dissemination of research findings on social media and interacting with policy makers, and everything in between.

When I was asked by Anna and Jeff to blurb the book, I wrote after I finished reading an advance copy that “[i]n a book that is as broad as it is deep, [the authors] set the standard for what constitutes ethical research in applied economics.”

I finished reading it, and I stand by that assessment. A lot of academic writing is excessively narrow, often out of a desire by authors to establish themselves as experts. Conversely, when academics try to make broader statements, they tend to not delve too deeply about the issues involved. Anna and Jeff have managed to cover a wide range of topics, and they cover nearly each and every one of those topics at depth. This is a book which I wish I would have been able to read when I was a first-year PhD student thinking about research topics in-between problem sets and exams.

That is the title of a new working paper by Bernhard Dalheimer (currently a postdoc in our department, but headed to Purdue, where he will start in the fall as an assistant professor), Sunghun Lim (Louisiana State), and me.

We ask a simple question: How does the extent of a country’s participation in global agri-food value chains (GAVCs, or “GA-vicks”) translate in terms of food price levels and food price volatility?

That is the title of a new working paper by Dan Millimet and me. If memory serves, the genesis of this paper was an exchange Dan and I had on Twitter where we both remarked that, with panel data, adding more rounds of data is not necessarily better if the goal is to identify a causal relationship, because the amount of stuff, both observed and unobserved, that remains constant over time (in other words, what is controlled for by unit fixed effects) decreases as the data grows to cover a longer time period.

Given that, it is surprising that the fixed effects (FE) estimator has emerged as the default estimator to use when trying to identify a causal relationship with longitudinal data. Even Yair Mundlak, who developed the FE estimator to control for management bias when estimating agricultural production functions, recognized that stuff is only time-invariant when looking at short periods when he wrote, in his original 1961 then-Journal of Farm Economics, now-American Journal of Agricultural Economics article, that (emphasis added)