5

As social scientists become more concerned with causal inference, a good thesis these days needs some sort of quasi-experimental strategy. For example, an economist wants to know the effect of military service on income but faces the problem that people who enlist are different from those who don't. So he uses the random Vietnam War lottery as a quasi-experiment with a valid control (who won the lottery and did not serve) and treatment (who lost and did serve). (More examples of these natural experiments).

As a PhD student sitting in my cubicle, I'm lost on how to identify these opportunities. Reading published work does not really help since these experimental opportunities are quite idiosyncratic. I'm not averse to going out there to find my own opportunity, but unsure about how to do this effectively. Do I read history book? Or talk to policy makers?

Since experimental opportunities are not available to all (or most) topics, I'm already paralyzed at the stage of choosing a topic (and thus can't start reading history book / talking to policy makers).

The standard advice I've got is not to pick question based on method. However, I find this quite a double standard given the concurrent push for quasi-experimental design.

  • Suggestion: Look at examples of past natural experiment based papers to see what kinds of patterns they looked for, then think about whether your field has anything similar. (My canonical example of a natural experiment was the epidemiological study of cats falling from high-rise windows -- not an experiment you can deliberately try, but one which happens frequently enough that there was enough data to draw statistically valid insights from, telling us more about exactly how and in what order the typical cat responds to that emergency.) – keshlam Dec 17 '14 at 19:20
  • @CapeCode My apology since my question is quite specific to social sciences. I included an example of what's a natural experiment I have in mind. Hopefully with that example, it's clear why I'm having difficulties coming up with similar design on my own. – Heisenberg Dec 18 '14 at 0:24
  • What makes you believe such a strategy exists? – Superbest Dec 20 '14 at 0:37
  • 2
    @Superbest Because there are scholars who specialize on using these quasi experiments in their research (eg Economist Angrist, Political Scientist Thad Dunning). I suppose there is a certain momentum factor involved since when an opportunity is spotted it's brought to these well known authors for collaboration. Of course I'm not attributing everything to fame (these guys need to get famous with independent work first) - hence I ask for things that a PhD student can do to spot these things by himself. – Heisenberg Dec 20 '14 at 1:57
2

Don't sit in your cubicle!

Go to the library (a physical one assuming you have one still). Read the newspapers (physical ones are easier to browse but you can do this on line). Look at the controversies, the scandals, that are emerging daily on the news: political lies, child abuse, discriminative policies, public funding, privatization, quantitative easing, bank bail outs. Look at states with different parties in control. Get hold of the latest and previous census data. Get hold of the Enron emails. Get access to the data that companies are building up through loyalty cards and credit cards. Talk to you med school or a disability charity about mining their data. Have a look at the data mining literature - talk to the people at your university who do this and what contacts they have...

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.