A Simulation Study On Kaplan Meier Non-Parametric Survival Methods
Abstract
Exploring a time to event data, especially time to failure (Death) assuming some data are censored and no tied observations. This article discusses the use of Kaplan Meier nonparametric approach on mortality data simulated over some period specifically 15-weeks follow up. Series of simulations were carried out and survival and hazards probabilities and Kaplan Meier graphs were obtained for different simulations. Law of large numbers as well as demographic stochasticity in the model were observed. The findings suggested that as the number of subjects at risk increases, the expected survival µbwhich is approximately 6 weeks and unconditional probability of survival S(t) are almost decreasing at the same rate indicating more mortality on daily basis while the hazards h(t) are tending towards being constant.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.