there is a small difference in the output of the summary tables when I run it with the current version of the package, and the one given in the "solution" script (which, I guess, was run with a previous version). The latter has AIC and BIC, while the former hasn´t. Why is this so? Was it deemed useless to report those measures? Thanks, O^G

Hey Omar, Thank you for your question! To be honest, I don't know the exact reason why these measures are no longer present in the summary tables. Possibly, they are not used as often. Nevertheless, if needed, one can always retrieve them using the sm.tools.eval_measures.aic and sm.tools.eval_measures.bic commands. Here is an example: Kind regards, 365 Hristina

Follow this topic

Omar R. Valencia García

Last answered:

15 Nov 2021

Posted on:

12 Nov 2021

Doubt about the AIC and BIC

in Machine Learning in Python / Calculating the accuracy of the model

1 answers ( 0 marked as helpful)

Hristina Hristova

Instructor

Posted on:

15 Nov 2021

Doubt about the AIC and BIC

Submit an answer

related questions