Which theory is borne out by data?
Robert Murphy's new column over at the Mises Institute reviews the data on macroeconomic performance over the past two years in response to the ARRA stimulus package and casts this ex post facto data against Keynesian and free-market theories to determine which theory was right. His column is worth a read, although I consider this line to embody the central lesson:
As Jim Manzi has been repeatedly arguing - echoing the writings of Mises - it is impossible to conduct a truly controlled experiment in the social sciences. Often without realizing it, economists interpret the data as confirming their preferred theories, even when those same data give stronger support to their ideological opponents.
