when i was an escort, there was a slight (r=0.2) negative correlation (p=0.1) between the likelihood that I had an orgasm and the physical attractiveness of my client.
27
12
205
Conversation
Replying to
Was r=0.2 or r=-0.2? The sign of r determines directionality. The p-value has nothing* to do with the strength or direction of the result, just the likelihood it’s a true result.
1
15
Replying to
It was -.2, I forgot to include negative sign.
I also know how r and p values work, I'm starting to get offended when ppl try to explain them to me for the millionth time. Like do you think I just threw those numbers in there for fun?
4
1
46
Replying to
Research scientists throw those numbers in for fun and then misinterpret them—I only blindly trust statisticians. I commented on it because the inclusion of the p-value didn’t apply to the context.
1
4
Replying to
I wasn't sure where to put the p value in that sentence, and figured it didn't matter too much cause ppl who know what p value means wouldn't misinterpret it.
Replying to
I would have left it out and relegated it to a table somewhere. It’s most meaningful alongside the parameter values or effect sizes it tests the significance of.
What was your model here? Linear probability, logistic regression, or something else?
1
2
No matter how smart you are, there’s always a man who thinks he’s smarter. How long before you do the numbers on mansplaining?
1
Fuck p values. Leave em out. Rampant p hacking has ruined what was not a very good method for analyzing the fit of a statistical model. See amstat.org/asa/files/pdfs
1