View Post

[sundin13]

Torillian said:

Here's where I'm at dude. You are quoting at me the guy who talks about science for Nerdist.com (a nice guy but someone with a bachelor's in civil and environmental engineering and a masters in science communication) to disprove the conclusions made by a professor of psychology at University of Washington who's published 50 publications within the last ten years, been cited more than 4000 times, and has a plethora of awards including a genius grant. Take this from a scientist, this lady is a rising star in her field and I would need quite a bit of evidence before I believe she's just a dipshit who doesn't know how to analyze her own data.
I mean just look at this shit: https://scholar.google.com/citations?hl=en&user=4hwc6fwAAAAJ
This is a person that lives and breathes this kind of analysis every second of every day. To think you or I can come into her field and assume we know better than her and the peers in her field that reviewed her manuscript and approved it for a reputable journal is just nuts.

I'll just chime in real quick to say that you are in fact, very right about all of this.

P value is not "margin of error" it is a statistical test of a hypothesis. When the p value is greater than 0.05, that indicates that the results found would not be unsurprising if the null hypothesis were true. That fact is the very fact that the paper that I posted is highlighting: That there is no statistically significant difference between transgender (with social transitioning) and non-transgender populations in relation to certain highlighted factors. A confirmation of a null hypothesis is just a scientifically important as a confirmation of a hypothesis.