June 2017
Beginner to intermediate
576 pages
15h 22m
English
We can obtain survival curves for the Cox model in a similar fashion as we did for the KM models. To obtain the data points for the curve, use summary(survfit(CoxModel.1)), which will also display the confidence intervals, count of the number of members who churned (n.event), and the number of members at risk (n.risk):
> summary(survfit(CoxModel.1))Call: survfit(formula = CoxModel.1) time n.risk n.event survival std.err lower 95% CI upper 95% CI 1 1488 15 0.993 0.00185 0.989 0.996 2 1455 52 0.967 0.00404 0.960 0.975 3 1393 34 0.950 0.00505 0.940 0.960 4 1342 20 0.940 0.00559 0.929 0.951 5 1315 39 0.919 0.00655 0.906 0.932 6 1245 42 0.896 0.00752 0.881 0.911 7 1156 60 0.861 0.00884 0.844 0.879 8 1020 68 0.818 ...