I recently just finished two great books, Mastering 'Metrics, and Mastering the Grain Markets.
Mastering the Grain Markets
While I have a background in agricultural and applied economics, my interest was always related to the public choice and the environmental implications of biotechnology, as well as econometrics (hence this blog). So, I didn't really have much formal background related to commodity markets, other than a little exposure to options through a couple of finance classes. I have certainly read some really good extension publications related to futures, options, and hedging but Mastering the Grain markets by Elaine Kub really brings these issues to life. She brought me back to my crop scouting days in her many discussions of corn production and the agronomics of our major commodities. She also tackles some major issues and controversies associated with modern agriculture, everything from speculation, to biotech to sustainability issues, gluten fad diets and more. Prepare for a trip from gate to plate in this book that teaches like a textbook but reads like a novel!
Even if you think all you are interested in are the specifics around how futures and options work, you'll end up being convinced that the holistic approach is essential. To borrow one quote:
"..any participation in the grain markets is a form of participation in agriculture, and it should be regarded as one piece of a beautiful, challenging, miraculous whole."
A couple areas that struck me as particularly interesting were her discussions of counterparty risk and over the counter contracts. I'll probably have a separate post on this blog or my ag econ blog regarding counterparty risk.
So, why share a review about a grain markets book on an applied econometrics blog? Well, all the discussion about OTCs and risk management rekindled my interest in copulas, which I have blogged about before, and also made me a little more curious about index based crop insurance. Risk modeling in commodities go hand in hand with econometrics. Oh, and she even hits on precision agriculture and alludes to big data in agriculture:
"At the end of the growing season, he has every data point he could possibly need (seed population, seed depth, input rates, final yield, soil moisture, etc.) to fine tune his production practices on each GPS mapped square foot of his farm."
Before reading MM, I had previously read Angrist and Pischke's Mostly Harmless Econometrics. It was my first rigorous introduction to the potential outcomes framework and causal inference. It took me a while to work through and I still reference it often. Even though Mastering 'Metrics was supposed to be a 'lite' version or maybe an undergraduate version of MHE, reading in 'reverse' order worked out well. What I really liked was their intro to regression, and the presentation of regression as a matching estimator becomes even more crystal clear to me than it did in MHE. To borrow a quote:
"Specifically, regression estimates are weighted averages of multiple matched comparisons"
I really think a lot of people I encounter have a hard time thinking about that. I also got better insight and clarification on a number of issues related to instrumental variables, regression discontinuity, and difference-in-differences. Within the IV discussion, I really like the causal-chain of effects presentation and discussion of 'intent to treat', and better understand all the things related to compliers and noncompliers etc. They also really got me up to speed with regard to the differences in parametric vs. non-parametric RD and an important distinction between fuzzy and sharp RD:
"....with fuzzy, applicants who cross a threshold are exposed to a more intense treatment, while with a sharp design, treatment switches cleanly on or off at the cutoff."
Another thing that stood out with me, in their DD chapter they made some clarifications about weighted regression and clustered standard errors that seemed very helpful. Other things in general, I really liked their treatment of the regression anatomy formula and understood it much better in this reading. Their basic review and treatment of inference, standard errors, and t-statistics is really great and a good way to segway an undergraduate student from an introductory statistics class into the more advanced topics they present later in the text. I could also see certain graduate programs, even outside of economics making use of this text.
Both Mastering the Grain Markets and Mastering Metrics end with a final chapter tying everything together.
I highly recommend both books.
So above I mentioned that risk modeling and econometrics go hand in hand, but have been thinking, were any of the techniques covered in MM useful for work related to the commodities markets? In terms of informing marketing and risk management strategies, I'm not sure. Maybe some readers have some idea. But, in terms of policy analysis as it relates to commodity markets, perhaps. There are some that advocate that we should restrict speculation in commodity markets. Scott Irwin looked at the impact of index funds on commodity markets, using granger causality (although granger causality was not discussed in MHE or MM). Other work has relied on panel methods. A quick google search reveals some related work using instrumental variables discussed in MM. For now I'll just say to be continued.....
Irwin, S. H. and D. R. Sanders (2010), “The Impact of
Index and Swap Funds on Commodity Futures Markets:
Preliminary Results”, OECD Food, Agriculture and
Fisheries Working Papers, No. 27, OECD Publishing.