My current model is of the form $$\log(\frac{y_i}{1-y_i}) = \beta_0 + \beta_1 x_1+\beta_2 x_2.$$ Is it okay if I consider the model $$\log(\frac{y_i}{1-y_i}) = \beta_0 + \beta_1 x_1+\beta_2 \log(x_2+1),$$ where $x_2$ is continuous?

$x_2$ can take the value 0 hence why I am adding the constant 1. I am also applying the log transformation due to interpretability.


marked as duplicate by whuber Feb 6 at 21:49

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.