I'm not certain how to interpret the entropy output--though I have used the Gini criterion before and interpreted it as the probability of reaching 100% on any given leaf the tree splits on.Though after reviewing things on the internet--I think I've been interpreting results really wrong for the decision tree altogether.

If I have a regression model, I would interpret a coefficient as saying the coefficient of coffee increases the probability that a person will be ready for work in the morning by 42%, if 0.42 were the coefficient on my summary out put.

But if it's on my Decision Tree and Entropy = 0.42--is that still associated with the probability of a binary dependant variable, with a sample = 500 and value [200, 300]

All of this is made up because I can't give you my actual data


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.