A non-parametric test for comparing two survival curves, which results from the work of Sir David Cox and Nathan Mantel. Denote the total number of deaths in the second group by D2, and let the ordered survival times of the combined group be t(1)<t(2)<…<t(k). The test statistic, C, is given by C = U / √I, where , , and m(j) is the number of survival times equal to t(j), d(j) is the total number of individuals who died (or were censored) at time t(j), and p(j) is the proportion of these who were in the second group. If the differences between the survival curves are attributable to random variation then C has a standard normal distribution.
Subjects: Probability and Statistics.