I am using Stata and trying to find out if there is a correlation between categorical variables (e.g., states) and continuous variables (e.g., weight).
With a minimum knowledge of statistics, I think in this case, I should calculate η^2 (correlation ratio) instead of r (Pearson). Does anybody know how to do this in Stata? Or is there any suggestion for the alternative method?
With a minimum knowledge of statistics, I think in this case, I should calculate η^2 (correlation ratio) instead of r (Pearson). Does anybody know how to do this in Stata? Or is there any suggestion for the alternative method?
