Yeah, if you look at the actual numbers, this study is kind of ludicrous. About half the cis people had the gene, but almost half the trans women didn't have the gene. Since cis people outnumber trans people by quite a bit, that means that more than 99% of people who have the gene are not trans. Maybe more than 99.9%.
Also worth noting is that "significant" in statistics doesn't mean in science what it means in plain English. In this case, it means that, given the sample size, there's just barely enough of a correlation for them to believe that there is any link at all, no matter how weak; if they'd had one less trans woman with the gene then the correlation would have been indistinguishable from random experimental noise.
![[community profile]](https://www.dreamwidth.org/img/silk/identity/community.png){kind=small}
(no subject)
Date: 2009-05-22 04:38 am (UTC)Also worth noting is that "significant" in statistics doesn't mean in science what it means in plain English. In this case, it means that, given the sample size, there's just barely enough of a correlation for them to believe that there is any link at all, no matter how weak; if they'd had one less trans woman with the gene then the correlation would have been indistinguishable from random experimental noise.