[OPE-L:4179] Who agrees with Popper? Well, not the Bayesians

From: P.J.Wells@open.ac.uk
Date: Fri Oct 20 2000 - 08:33:14 EDT


Steve

You might want to hold back on the thanks somewhat -- what I agree with in
falsificationism is its use as a test of bona fides: I certainly *don't*
think it's (usually) much use in assessing the truth of theories.

This is for a reason which you bring out in another post: empirical evidence
is rarely terribly conclusive, even if we leave the D-Q problem aside.

Moreover, I'm surprised to see you instancing statistical testing of
hypotheses, since falsification seems to be something that stat.s tests are
intrinsically incapable of producing.

Your account of your econometric work seemed to say that there have been
(many?) occasions when the evidence, when it has become available, has
lowered your degree of belief in your initial hypotheses.

This, of course, is Bayesianism, which has always seemed to me highly
effective as both description of and prescription for actual practice in
empirical testing.

Julian

> -----Original Message-----
> From:	Steve Keen [SMTP:s.keen@uws.edu.au]
> Sent:	Thursday, October 19, 2000 11:13 PM
> To:	ope-l@galaxy.csuchico.edu
> Subject:	[OPE-L:4171] Re: Who agrees with Popper?
> 
> Dear Julian,
> 
> Thank you thank you thank you! -:)
> Steve
> At 21:11 19/10/00 +0100, you wrote:
> >It's annoying to have to put in a good word for this vastly-over-rated
> (not
> >least by himself) thinker -- but falsifiability is *quite* a good idea as
> a
> >test of whether a set of notions is, so to speak, advanced in good faith.
> >(And his anecdote against Adler, which he uses to illustrate his
> >disillusionment with confirmationism, is certainly both funny and
> >well-directed).
> 



This archive was generated by hypermail 2b29 : Tue Oct 31 2000 - 00:00:10 EST