News for hackers. Stuff that matters.
Re:Is Precognition Real? by araneae on Saturday November 06, 2010 @10:18PM (#1878419)
I went to Cornell and I'm one of the many students that participated in this guy's experiments (although not this particular one with the erotic pictures. I got regular pictures.)

I can tell you that every semester that I was there he was running a version of the "Are you psychic?" experiment. I'm sure he's been doing it every semester for a very long time. Undoubtedly there have been loads of experiments where it didn't pan out. (If you're curious about my results, I got 54% and a cheerful grad student greeted me after the fact by saying "congrats! you're psychic!")

The fact is, if you run an experiment like this enough times you are going to get a significant result eventually. That's why you have alpha values. If it's at .05, that means that 5% of the time you're going to get a false positive. I think that's what this is.

Re:Is Precognition Real? by SoftwareMaven on Sunday November 07, 2010 @05:49PM (#1880587)
The only way this kind of experiment can have meaning is if 1) somebody can hit a very high percentage correct a high percentage of the time or 2) over all, there is a trend that is unexpected.

I would be very surprised if said grad student actually believed you were psychic. A result in the significant region is NOT significant. A set of results in the significant region is.

Re:Is Precognition Real? by carbocation on Saturday November 06, 2010 @10:25PM (#1878437)
54% correct out of how many, if you remember? Figuring out the degree to which this deviates from a null expectation should be pretty straightforward.
Re:Is Precognition Real? by araneae on Saturday November 06, 2010 @10:29PM (#1878446)
I'm sure he gives the size in the paper somewhere. I expect it was probably similar to what I did. It was 5 years ago and the pictures weren't numbered so I really have no idea.
Re:Is Precognition Real? by carbocation on Saturday November 06, 2010 @10:42PM (#1878472)
The paper says it's 36 trials. 30% of experiments with 36 dichotomous decisions where the answers are chosen randomly would be expected to have 20/36 correct (= 56% correct) or better.