I have used the cube root $(1/3)$ transformation on both my dependent and one of my independent variables. I would have preferred a log-transformation but my data has both negative values and zeroes.

I have read (and reread) the following posts: How to interpret regression coefficients when response was transformed by the 4th root? and Interpreting cubed root transformation. However, these posts only pertain to the transformation of either an independent or the dependent variable.

At this stage it is still not clear to me how to interpret the coefficients when both variables are transformed with the cube root.

lm(formula = tax_rate^(1/3) ~ financialization_ratio^(1/3) + zNumber_of_employees, 
    data = data)

(Intercept)               0.55  
financialization_ratio    0.08  
zNumber_of_employees      0.01  

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.