1

I am going through survival analysis using Python's lifelines package.

https://lifelines.readthedocs.io/en/latest/Survival%20Regression.html

While reading ATF; Accelerated Failure time model and Cox Propositional Hazard method, I came to know AFT model is useful when relative failure of 2 population is given, but as I read further, in example AFT is used on single population only. How different it is from just CPHFitter( Cox Proportional Hazard Fitter) ?

I am not able to figure out how exactly acceleration is happening when relative accelerated failure rate is not given in example of AFT - (https://lifelines.readthedocs.io/en/latest/Survival%20Regression.html#the-weibull-aft-model)

Spiros
  • 2,231
  • 3
  • 15
  • 26
Arpit Sisodia
  • 570
  • 5
  • 18
  • 1
    I'm confused about your questions. It would help if you could expand your confusion / question. The Cox model and the Weibull model make different assumptions about the data, and this leads to different models. – Cam.Davidson.Pilon Oct 14 '19 at 17:51
  • i want to know who acceleration is happening given just one population. acceleration rate is relative so we need another population (https://lifelines.readthedocs.io/en/latest/Survival%20Regression.html#accelerated-failure-time-models) . In example given ( https://lifelines.readthedocs.io/en/latest/Survival%20Regression.html#the-weibull-aft-model) only one population is used. – Arpit Sisodia Oct 15 '19 at 08:50

0 Answers0