Prediction: The Replication Crisis will be Solved by Market Forces, not Academics

Social science is in an interesting place, especially my home discipline of social psychology.  Traditionally, it has been practiced by scholars at academic institutions who are relatively unaffected by market forces, which meant that it didn’t really matter to people’s careers if what was discovered in social science was actually used, but rather that those discoveries were published in the right journals.  A few enterprising scholars used this fact to build lucrative careers by simply inventing discoveries that nobody was going to check.  Still others do things that are not fraud, but certainly increase the chances of finding positive results, that may or may not be generally true.  Indeed, I think every scholar engages in some form of this, including things that aren’t currently seen as biased like trying different stimuli/materials when your initial stimuli doesn’t work (I’ve done this).

There is no top-down cure for this.  We could (and perhaps should) strive for ways to make research more perfect, and worthy organizations are working on that.  But social science research is never perfect, always requiring a sample that is biased in some way and some compromise as far as control, ecological validity, and measurement, and perhaps this is where the metaphor of trying to emulate “hard” sciences like physics fails.  It doesn’t fail because the researchers are less intelligent or careful…indeed working with human subjects requires more ingenuity.  But rather it fails because while an experiment done on one rock most likely replicates on the next rock, human beings vary to much greater degrees.  We don’t all react the same to profound stimuli like the end of Romeo and Juliet, the election of a black President, or the sight of violence, so should we expect us all to react so predictably to subconscious primes or invented tasks?

I work as a data/social scientist because I believe in the utility and power of working using data on human behavior, but it is fundamentally different than experimenting on rocks or chemicals, in that findings are always probabilistic.   You can make a lot of money and do a lot of good things based on probability…but it is not the same kind of knowledge as the knowledge that allows my car to start in the morning, my refrigerator to run on electricity, and your computer to translate my words into pixels on your screen, where near-absolute predictability allows those items to function.

Probabilistic knowledge is better dealt with in markets, as compared to the current peer review journal system.  Social scientists actually study this.  The journal system is not well equipped to deal with things that are not black and white as all it’s constituent parts (what gets published, who gets authorship, who gets hired) are black and white.  Markets let people make bets, hedge their bets, and come to some probabilistic version of truth.

Social science, whether social scientists are a part of it or not, is moving toward being a market, as far more data on human thought, communication, and behavior is captured by the tech industry than is captured by academics, and the tech industry is fully responsive to market forces.  Statisticians and data scientists now publish far more knowledge than is available in scholarly journals.  Most tech companies do thousands of experiments each year and bet real money on the outcomes.

There is absolutely a place for the well designed academic study in this world, as there certainly are gaps in what is understood by industry processes.  But the insertion of market forces into social science is bound to change academics away from publication for publication sake and toward creating knowledge that is useful, as there will be real money at stake.  Publishing a paper will no longer be the end accomplishment, but rather the productive use of the knowledge gained by one’s research.  In that world, it won’t really matter what you think of the methods, statistics or claims of another researcher.  If you really don’t believe in a particular phenomenon, you can bet against it, or if you believe in a particular fact about human nature, you can bet on it.  And if there is no market for that bet, then maybe the question wasn’t that important to begin with.

- Ravi Iyer



Also read...