Friday, August 28, 2015

Scientists Replicated 100 Psychology Studies, and Fewer Than Half Got the Same Results | Science | Smithsonian

This is troubling in many ways.  I would expect the numbers to be better in finance (especially the mathematical studies and modeling studies), but I have no doubt that the timing of studies matters and that the replication is often impossible (possibly in part since the original study influences the subjects/markets).



Scientists Replicated 100 Psychology Studies, and Fewer Than Half Got the Same Results | Science | Smithsonian:

"Across the sciences, research is considered reproducible when an independent team can conduct a published experiment, following the original methods as closely as possible, and get the same results. It's one key part of the process for building evidence to support theories. Even today, 100 years after Albert Einstein presented his general theory of relativity, scientists regularly repeat tests of its predictions and look for cases where his famous description of gravity does not apply. "


Here is another story on this:
http://www.vox.com/2015/8/27/9216383/irreproducibility-research

A simple finance example: CAPM worked well in the era it was developed but could not be replicated in out of sample (more recent) tests).  (and before I get complaints, I realize that CAPM is not a perfect example but it was first one that came to my head).

'via Blog this'

No comments: