In today's Finshots we see why Joshua Angrist and Guido Imbens were awarded the Nobel Prize in economics


The Story

Before we get to the story, a recap of some of the big ideas presented in the article we published yesterday.

Economists and policymakers often spend decades trying to study the causal relationship between variables — for instance, the impact of education on lifetime earnings, or the effect of minimum wage on unemployment. The only problem — Such analysis can be fraught with inconsistencies if you don’t do it right.

In other disciplines, researchers often adopt randomized controlled trials in an attempt to remove bias and inconsistency. As we outlined yesterday — In the field of medicine, you could study the effects of a pill by taking one set of participants and administering the dose while offering another group a placebo — saltwater for instance. If at the end of the experiment, the group that received the pill showed significant improvements compared to the group that received the saline solution, you could safely determine that the pill did its job. Unfortunately designing such experiments in real life can be particularly cumbersome. You can’t decide who gets to have an education and who doesn’t.

But sometimes, nature can throw up situations that mimic these controlled experiments.

Consider for instance Angrist’s PhD thesis. The young researcher was trying to study how veteran status affected an individual’s future earnings. More specifically, he was trying to see if serving in the army negatively impacted future earning potential. Now if you were new to this kind of thing, you would simply compare the wages of people who served in the army with those who didn’t and see if there’s a telling difference.

However, this doesn’t tell you the full story because certain types of men are more likely to serve in the armed forces compared to others. For instance, men with fewer opportunities in their teens are more likely to enlist. These people would have gone to earn less anyway, even if they didn’t join the army. So we can’t say for sure it’s the army that did the damage. What we need here is a source of randomization or a natural experiment that can mimic controlled settings. And back in the 70s, such an eventuality transpired when the American government declared war on Vietnam.

The government ran televised lotteries to decide who would be inducted into the army. Most of these men were between the ages of 19 and 20 and so the lotteries split a large part of this population into two groups — a treatment group who were drafted to participate in the war. And a control group — that wasn’t drafted. This provided the ideal setting for Angrist to study the two groups and see how their income patterns diverged over the years.

But alas, there was one other problem. Most of the individuals who served in Vietnam were volunteers who would have served no matter their lottery number. So these individuals differ from those who were picked randomly. And as the Nobel Committee writes, this can make it difficult for researchers to interpret the results —

Natural experiments differ from clinical trials in one important way — in a clinical trial, the researcher has complete control over who is offered a treatment and eventually receives it (the treatment group) and who is not offered the treatment and therefore does not receive it (the control group). In a natural experiment, the researcher also has access to data from treatment and control groups but, unlike a clinical trial, the individuals may themselves have chosen whether they want to participate in the intervention being offered.

But once Angrist and Imbens came along, they designed frameworks and methods to analyse such data and still derive meaningful insights. Their seminal contributions to the field help researchers use natural experiments to better understand and answer central questions for society and that’s why they were awarded the Nobel Prize alongside, David Card.

Until next time…

Also, don't forget to share this article on WhatsApp, LinkedIn and Twitter