Corrections to the blogosphere, the consensus, and the world

Wednesday, November 11, 2009

272,789,137,666,806,000,000 green bottles

Mmm. Looking at that SBC study, they found 0.05 associations in 27 out of the 68 genes they studied. The problem with that is that the perms and combs are backbreaking. If, let's say, you can end up having 16 of those genes tripped, there would be 272,789,137,666,806,000,000 different ways to do it.
Can any of the trained mathematicians out there (you know who you are) check that?

But SBC says
My colleagues and I recently published the first candidate gene study of Asperger syndrome, which identified 14 genes associated with the condition.
Eleven genes survived family wise error rate (FWER) correction using permutations across both experiments, which is greater than would be expected by chance.
So who knows...

No comments:

Blog Archive

Search This Blog


Follow by Email

There was an error in this gadget

Total Pageviews