# Survival analysis: log rank or ANOVA to compare groups?

If I want to know whether there is a significant difference in age of onset between the 2 groups, should I use ANOVA? My data meet the requirements of an ANOVA test. Or should I use the log rank test, which is basically the survdiff function in R?

Also, are survival times and age of onset (my x-axis) the same concept? I read that to see if two or more groups differ in terms of survival times, I should use the log-rank test. But what exactly is survival times?

• Do you know the time point of death of each and every patient in the analysis? Then classic ANOVA could work if the assumptions are really met. The log-rank test would be similar to Kruskal-Wallis then. In other words, if you don't have censored observations, then your questions boils down to "Kruskal-Wallis or F-test". – Michael M Aug 10 '15 at 10:27
• I think it would help if you returned the survival plots to the question. (You may accidentally have deleted it when you removed some of the initial text.) Otherwise neither the question nor the answer make much sense. – EdM Oct 6 '15 at 16:23
• When you say "My data meet the requirements of an ANOVA test" ... which requirements do you refer to? e.g. if there's any censoring they certainly don't, and I see no reason whatever to think that the distribution of onset times would be particularly close to normal; they look rather skewed to me (and with small sample sizes, you're not necessarily going to have much robustness against skewness, nor much ability to detect it if you test for it) – Glen_b Oct 7 '15 at 1:03