Overview

Cox–Snell residuals


Show Summary Details

Quick Reference

Residuals introduced in 1968 by Sir David Cox and E. Joyce Snell, for assessing the validity of a survivor function that has been proposed for a set of survival data. The value of the survivor function depends on the time, t, and on one or more parameters estimated by the vector θ̂. The Cox–Snell residual rj, corresponding to time tj, is given by

rj=-ln{S(tj ; θ̂)},

where S(tj ; θ̂) is the value of the estimated survivor function at time tj. If the model is correct, then the residuals should have an exponential distribution with mean 1.

Subjects: Probability and Statistics.


Reference entries

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.