«

»

Mar 04

Print this Post

An Example of “Useless” Research that Isn’t

Over the years, Federal funding for the social sciences has come under fire from critics of all sorts, including the House of Representatives, which passed an amendment in 2012 to completely cut the National Science Foundation (NSF) funding for political science in particular. The argument in favor of these cuts usually sounds something like what blogger Steven Hayward recently wrote:

“But much of the time, social science is proving the trivial or the obvious, and offering little in the way of genuine advancement of our general understanding of how the world works.”

Mr. Hayward offers his “favorite” example: a nine-year Finnish study of 55,000 subjects that concludes that people who live close to bars tend to drink more heavily. I don’t deny that the social sciences, like other fields (even the hard sciences), occasionally produce research that seems to hold little value. However, in this particular instance, this frivolous-sounding study is actually useful.

It’s true that most of us wouldn’t be surprised to learn that people who live near bars tend to drink more. However, we wouldn’t be sure whether this association occurs because (i) heavy-drinkers choose to live near bars (“Selection Effects”), or (ii) bar proximity induces people who wouldn’t otherwise be heavy-drinkers to consume more alcohol (“Treatment Effects”). The distinction itself might sound trivial, but it isn’t if the policy goal is to curb heavy drinking. If bar proximity itself doesn’t induce greater drinking (i.e. Selection Effects), than policies designed to reduce drinking by limiting the number of bars in which alcohol is served are useless and fundamentally misguided. In this scenario, heavy-drinkers would find alternate methods to consume alcohol. Alternatively, in a world where Treatment Effects explain most of the association between bar proximity and drinking behavior, policies limiting the availability of bars would likely to be more successful.

The value in the “useless” Finnish study is that it’s able to sort out the effects of Selection versus Treatment. It does this by focusing on those subjects who previously didn’t live near bars but had bars move closer to their homes in later periods of the study. These residents didn’t choose to live near bars because of a desire to drink more, instead the bars chose to relocate for presumably independent reasons. The study found that once the bars were nearby, subjects began to drink more heavily. This conclusion supports the Treatment Effects explanation.

Granted, this research isn’t on a Nobel Prize-winning trajectory. However, this supposed paragon of useless research does in fact contribute our understanding of the environmental causes of heavy-drinking in a way that informs public policy choices.

About the author

Benjamin Bohr

Benjamin is a manager at Fulcrum Financial Inquiry. He specializes in statistics and data analysis for use in high-stakes litigation, business valuations, and other financial matters.

Permanent link to this article: http://betweenthenumbers.net/2013/03/an-example-of-useless-research-that-isnt/

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>


*