[extropy-chat] aargh

[Damien Broderick]

At 01:16 PM 12/18/2004 -0500, Eliezer wrote:

>Damien, I see where he says that results under control are statistically 
>significantly less good than results obtained at home.  (What a 
>surprise!)  I don't see where it says 70% hits (20% expected) effect size.

I cover my head with shame. I was hastily conflating several sources and 
percentages, and managed to screw it up not once but twice. Ertel's results 
will be published in

Ertel, S. (2004). The ball drawing test.  Psi from untrodden ground. In M.
A. Thalbourne & L. Storm (Eds.), Parapsychology in the 21st Century: The
Future of Psychical Research: McFarland.


>If this guy is getting an effect size of 70% hits on a 20% target, I like 
>that.  That's a nice, clear claim.

Of course, and he'd be waltzing away with Randi's dough. But hey, 40% more 
hits than MCE, under controlled conditions, is surely interesting.

 > Needless to say, it will also turn out to be totally bogus.

Eliezer's `What a surprise!' is *why* nobody uses the at-home results as 
*evidence*. It is a screening procedure, which also captures some Ss who 
have got high scores simply by chance, and who will fall away to chance in 
subsequent trials. The worst that can be said about it is that it might 
also screen for cheats and liars, who may be more likely to find loopholes 
in the experimental controlled runs. Maybe so, and hence the need for 
relentless scrutiny.

Damien Broderick