I'm building a survival analysis model using the survival package in R, with a Weibull distribution to suit the skewed nature of my dataset, which is time-to-event data for devices on a network. I understand that the hazard function provides a conditional estimate, given that an individual has survived until time t, of the event rate at the current point in time (if the time interval is close to 0), or the next time interval.

Is it possible to calculate the hazard function at time interval t + some positive value? Ie. the probability, given that a device has survived 3 days, that it will have an event 2 days later? How do I define the time interval when calculating the hazard function? Can it be varied, or is it fixed?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.