26: Interpreting effect sizes
Everything Hertz
00:00
Is the Cohen's Rule of Thumb Correct?
Dean Obeidallah says he is a fan of Cohen's seminal work. He disagrees with its centrality to the work that people do, but thinks it was useful practical research who offered practical advice. But when you're running power analysis, now you can either do a post hoc power analysis or an a priori one and figure out what kind of sample size you need for your study. So if you're expecting a small effect size, so, um, going with 20 5th percentile effect size. If you're going to use Cohen's recommendations for HRV for HIV, you need a three hundred and ninety-three participants per group.
Play episode from 13:56
Transcript
