search

autonlab / auton-survival

Auton Survival - an open source package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Events
http://autonlab.github.io/auton-survival
MIT License
315 stars 74 forks source link

Calculate log partial likelihood for the DCM #114

Open tommyvcc opened 1 year ago

tommyvcc commented 1 year ago

Dear all

After running the deep cox mixtures, how can I calculate or know the log partial likelihood? Is there a code for that?

The reason I am asking for it is to calculate the Akaiki Information criterion and compare it with other models

Would you kindly be able to help me with that point?

chiragnagpal commented 1 year ago

the akaike information criterion is not well defined with the cox partial likelihood.

AIC is defined in terms of the full likelihood, the partial likelihood is different from that

tommyvcc commented 1 year ago

Thank you so much for your support and prompt response.

Is there anyway to calculate the Akiki information criterion or the full likelihood for the deep cox mixtures model?