I have a question regarding the interpretation of coefficient magnitude (not coefficient) in linear regression when the dependent variable is log-transformed.
When the y is not log-transformed the interpretation is like the following an increase of x (independent variable) by one standard deviation is associated with the increase of y (dependent variable) by 2.63% of its standard deviation.
But I do not know if this is also true when y is log-transformed.In other words, How should I consider percent standard deviation changes? (because the model is of percent changes in )
A continuation of this question
Thank you
