BROADCASTS.com

https://slatestarcodex.com/2020/04/07/never-tell-me-the-odds-ratio/

[Epistemic status: low confidence, someone tell me if the math is off. Title was stolen from an old Less Wrong post that seems to have disappeared \u2013 let me know if it\u2019s yours and I\u2019ll give you credit]

I almost screwed up yesterday\u2019s journal club. The study reported an odds ratio of 2.9 for antidepressants. Even though I\xa0knew\xa0odds ratios are terrible\xa0and you should never trust your intuitive impression of them, I\xa0still\xa0mentally filed this away as \u201csounds like a really big effect\u201d.

This time I was saved by Chen\u2019s\xa0How Big is a Big Odds Ratio? Interpreting the Magnitudes of Odds Ratios in Epidemiological Studies, which explains how to convert ORs into effect sizes. Colored highlights are mine. I have followed the usual statistical practice of interpreting effect sizes of 0.2 as \u201csmall\u201d, of 0.5 as \u201cmoderate\u201d, and 0.8 as \u201clarge\u201d, but feeling guilty about it.

\xa0