Confidence interval choice in Kaplan Meier

[claudiocc1]

Would it be possible to add a switch in the KM fitter to allow for returning the confidence intervals according to equation 1.2a and 1.2b of
https://www.math.wustl.edu/~sawyer/handouts/greenwood.pdf
instead of using the exponential formula?

Actually, to be honest, what I am after is just the expression in equation 1.2b (maybe you have a better suggestion on how to easily extract it?).
The reason is that this quantity is necessary to construct the Greenwood-Nam-D'Agostino statistics, see Section 4 of
https://onlinelibrary.wiley.com/doi/full/10.1002/sim.6428

Thank you so much.
Claudio

[CamDavidsonPilon]

Hi @claudiocc1, all the information is available on the KaplanMeierFitter object: kmf.survival_function_ gives you the SF at times (and kmf.predict for interpolating, if needed), and kmf.event_table gives you the counts. Actually, the kmf._cumulative_sq_ is the second part of that term exactly.