If the survival curves corresponding to the categories of a single covariate in a Kaplan-Meier survival plot are parallel then this confirms the assumption of proportional hazards in a Cox survival analysis
The assumption of proportional hazards in a Cox survival analysis may be confirmed by incorporating an interaction between the covariate and ln (time) in the model and ensuring that it is not statistically significant
A survival analysis assumes that the probability that an individual’s follow-up is censored is unrelated to the probability that the individual will develop the outcome of interest. If this is the case, we say that we have informative censoring.
Administrative censoring is generally informative.
If the development of one or more outcomes of interest precludes the development or measurement of any of the others in a survival analysis, the outcomes are termed competing risks.