A previous study had participants make a dichotomous decision, and it was analyzed with logistic regression.

A follow-up study is measuring the same construct, but having participants make a continuous decision (i.e., Likert scale from 1-7).

I've had success using the simr package in R to simulate data and figure out the power with N participants if I were to run another study using logistic regression.

However, is there a sensible way to use the effect size from the study using logistic regression, to determine power and sample size for the study with a continuous DV, analyzed with linear regression?

In case it's relevant, all of these studies are analyzed with mixed effects models, including random subject intercepts, and analyzed at the trial level.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.