Question: Is it appropriate to calculate Cohen's $d$ (effect size) from the regression coefficient of an independent categorical variable?

Background: My regression coefficient represents participation in an intervention (treatment group = 1; comparison group = 0).

My inclination is to simply divide the coefficient by the standard deviation of the dependent variable.

This approach makes conceptual sense to me since this coefficient represents the average predicted difference in the dependent variable between subjects in the treatment and comparison groups (while all other independent variables are held constant).

Does the application of Cohen's $d$ extend to multiple regression?

  • $\begingroup$ I think you should divide by RMSE instead of the SD. Also, this would give you Hedges g rather than Cohen's d. $\endgroup$
    – David Lane
    Commented Mar 19, 2017 at 21:06


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.