May

22

 I was reading this: “Our main finding is that economic data do not appear informative enough to uniquely identify the relevant predictors when a large pool of variables is available to the researcher. Put differently, predictive model uncertainty seems too pervasive to be treated as statistically negligible. The right approach to scientific reporting is thus to assess and fully convey this uncertainty, rather than understating it through the use of dogmatic (prior) assumptions favoring sparse models.”

And Karl Popper’s “Science as Falsification” came to mind. 

Peter Grieve writes: 

I’m sorry to say that there is a movement in physics to abandon Popper’s ideas about falsifiability. This seems to be motivated by the fact that string theory and the multiverse theory are at best extremely difficult to test.

Those still supporting Popper are called Popperazzi. Some of them call string theory “mathematical theology”.

Kim Zussman adds: 

Is an untestable theory that fits observations necessary to discard?

Stefan Jovanovich replies:

A theory that “fits” - i.e. usefully works with - observations cannot be discarded until those observations challenge the theory’s ability to predict events. The theory may simply be lucky enough to fit what people and their instruments can “see” and be better than chance at estimating what will happen in the future; but that “luck” will still be sufficient know-how until repeated observation reduces its foresight to no better odds than chance.

Observation is the test. Until Eddington’s observations of the eclipse in 1919, there had been no observations of the spacial interaction of matter and light that contradicted Newton’s theory. Eddington’s observations did not “prove” Einstein’s theory was “settled science” as the warmists like to say; they proved that Newton’s theory was not as useful an approximation of reality as general relativity.

The point that Eugene Fama keeps making is that economics, as a general theory of behavior, has yet to be even lucky over any extended period of time. Its interpretations of information theory seem to work fairly well in the limited domain of financial transactions but only to prove that risk’s rewards are only verifiable after the fact.

Meanwhile, we enjoy the game and keep blowing on the dice when it is our turn to roll.


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search