A portrait of the Nobel Masters of ‘Matrix’

Every year on the second Monday of October, the Sveriges Riksbank Prize in Economic Sciences is announced in memory of Alfred Nobel aka the Nobel Prize in Economics. This year on October 11 Three economists – David Card, Joshua D. Angrist and Guido W Imbens – were given this distinguished honor. Interestingly, half the prize was awarded to the David card, while the remaining half was divided equally between Angrist and Imbans. Coincidentally, every year the actual prize is presented on 10 December in a grand ceremony that coincides with the death anniversary of Alfred Nobel.

a connecting thread

The Nobel citation states that the prize was given for “methodological contributions to empirical labor economics and the analysis of causal relationships”. All three have many things in common apart from their interest in this aspect of econometrics. Not surprisingly, he teaches at some of the best universities in the world – Card teaches at UC Berkeley, Angrist at MIT, and Imbanes at Stanford. Card and Angrist both received their PhDs from Princeton, and their doctoral supervisor was the great labor economist, Orle Aschenfelter. Imbens earned doctorates from Brown University, and all three are Fellows of the Econometric Society, a rare honor among economists. The list of his accolades is extensive, but it is worth mentioning that the unique honor of Guido Imbense’s ‘best man’ goes to Joshua Angrist.

an important discovery

To me this year’s Nobel Prize in Economics is particularly valuable because it is awarded to those who have made a methodological contribution to the establishment of causation. Economics has always been interested in causal relationships, which is already clear from Adam Smith’s book titled, An inquiry into the nature and causes of the wealth of nations. This is particularly important in matters of human behavior as casual relationships are important for policy making. Suppose you see that whenever my sister buys shoes, it rains in Bhubaneswar. If it was a coincidence or a spurious correlation, we have nothing to worry about. But if this was the reason, then a flood prevention policy for Bhubaneswar would be to put an end to my sister’s shoe shopping spree! Exploring causality is doubly important in this age of big data, where analysts only look for patterns in the data, not the behaviors that can lead to the process of generating the data.

When we see two events, A and B, being correlated, in general we cannot conclude that A causes B, as a set of confounding factors may or may not be present. that the opposite may also be causation. One way is to consider an experimental framework where we treat event A as a treatment and see what events it generates.

However, this is also problematic. Once we offer treatment to a person, it is not possible to study the same person without treatment. Therefore, we need to resort to statistical techniques. A type of statistical technique in this vein that was introduced and popularized in economics by the winners of the 2019 Nobel Prize in Economics Abhijit Banerjee, Esther Duflo (incidentally Angrist was one of Duflo’s PhD supervisors) and Michael Kremer in the Randomized Controlled Trial (RCT) is called. . In this approach we compare outcomes in treatment and no treatment (control) groups in the same way as drug testing to establish causality while protecting against things like contamination in the two groups.

a different technology

This year’s Nobel laureates use a different technique called the natural experiment. To quote Peter Frederickson, chairman of the awards committee, “sometimes nature or policy changes provide conditions that resemble random experiments,” and the genius of those scholars is to recognize and identify those situations. lies in their ability to establish causal links. Using these naturally occurring events.

Take for example the work of David Card (with the late Alan Krueger, whom many believed he may have shared the Nobel with). Generally, economists believed that raising the minimum wage would increase unemployment because firms would hire fewer workers. In 1992, New Jersey increased its minimum wage, while neighboring Pennsylvania did not. Card and Kruger surveyed a large number of fast food workers on both sides of the New Jersey-Pennsylvania border in this natural experiment and established that higher wages had no effect on employment! This study has helped to change how economists view the minimum wage; Today it is widely believed that the minimum wage cannot affect employment because firms can pass on the costs to consumers.

statistical techniques

One drawback of natural experiments is that we cannot control who participates in them. It is here that the work of Angrist and Imbens has been of great importance for economics and other related fields. Angrist and Imbens developed a framework and demonstrated how statistical techniques could be used to draw accurate conclusions about causal relationships from natural experiments.

Finally, if you want to use some of these scholarly works, you can find a lot of papers on google scholar. Angrist is one of the authors of two excellent introductory books: Mostly harmless econometrics And mastering metrics Which is perhaps the most accessible of all his works. The author of an all-encompassing book called Imbens is Causal findings for statistics, social and biomedical sciences. David Card is one of the editors of several editions of the encyclopedia, handbook of labor economics.

Sudipta Sarangi is Professor of Economics at Virginia Tech, US, and author of the recent book, Teaeconomics of small things