In many medical studies it could be interesting to ascertain whether groups of survival curves can be carried out, especially when confronted with a considerable number of curves. Though the aforementioned methods like Log-rank, Peto & Peto, etc. can be used to compare multiple survival curves, to the best of our knowledge, there are none available method that can be used to determine groups among a series of survival curves. When the log-rank test (or its analogous) is used to compare three or more survival curves at once, the test reports a single p-value testing the null hypothesis that all the samples come from populations with identical survival. If the null hypothesis of equality of curves is rejected, then, this leads to the clear conclusion that at least one curve is different. However, these methods cannot be used to ascertain whether groups of curves can be performed or if all these curves are different from each other.
clustcurv proposes an approach that allows determining survival groups with an automatic selection of their number.