Recent content by Rets

  1. R

    How to deal with non-proportional hazard Cox models?

    Hi hlsmith, Thank you for this !! So the statistical results you obtained in the table suggest that no significant interaction occured and that only the antibiotics had an effect on survival ? Not sure how to interpret the graphs for proportional hazard checks... but maybe with so few...
  2. R

    How to deal with non-proportional hazard Cox models?

    dataset + Rcode: > library(survival) > library(ggplot2) > library(ggpubr) > library(survminer) > > a<-read.delim("surv.txt") > > survobj <- Surv(time = a$time, event = a$survival, type='right') # Important about the "survival" variable: 2= dead, 1=alive in the notation, which is different from...
  3. R

    How to deal with non-proportional hazard Cox models?

    It is an interaction because one group is treatment A, the other is treatment B and the other is treatment A+B (plus controls for which none treatment was done). The two variables "antihypertensive" and "antibiotics" are categorical variables with two modalities "presence/absence" (ie, yes/no)...
  4. R

    How to deal with non-proportional hazard Cox models?

    Yes, group assignment was randomized. The interaction is "antibiotics:antihypertensive"
  5. R

    How to deal with non-proportional hazard Cox models?

    Any advice or suggestion? I would be so happy to hear from you
  6. R

    How to deal with non-proportional hazard Cox models?

    Dear all, I want to run a Cox model to see if there is an interaction between two treatments. However, the test to see if proportional hazard is respected suggests that it is actually not respected. So I don't know what other statistical survival analysis to do because it means I cannot rely on...
  7. R

    R: Survival and censored data: how structure my input datasheet?

    Dear all, I would like to know how to organize the datasheet to import in R for survival analysis (Surv object, logrank test and Coxph). Let's consider an experiment with small animals. A cohort of 600 individuals is being followed-up every two days for 6 days (so I have data at day=0, 2, 4...
  8. R

    Survival analysis at few dates: glms? logrank? cox ?

    Dear OBH, Thank you for your instructive reply. I have been trying to run your script. However, I got confused. In the first example with t-tests, the command "mean(pvalues < alpha)" gives me only: 0. So what is the power in that case ? I am not used to loops sorry. For the second example, I...
  9. R

    Survival analysis at few dates: glms? logrank? cox ?

    Hi Obh, Ok thank you so much for these explanations! I like the comparisons, this is very clear to me now, thanks! Regarding the power, it is indeed counter-intuitive that a higher number of follow-ups will not result in a higher statistical power! So we actually could reduce all the...
  10. R

    Survival analysis at few dates: glms? logrank? cox ?

    Hello, Thank you for your explanations ! 1: Ok, so if the number of individuals being followed is 100, and 50 died during the study which is lasting 365 days, then the sample size is 50. However, I suppose the logrank test will be much more powerful if we have a follow-up every day so 365...
  11. R

    Survival analysis at few dates: glms? logrank? cox ?

    Thank you very much for your explanations. So "Event" or "sample size" is the number of death x the number of follow-ups? If no one is dead, the sample size is 0? And if I want to assess the effect of a factor on the mortality at one time only, do you think anova on glm built under binomial...
  12. R

    Survival analysis at few dates: glms? logrank? cox ?

    Sorry, I was not clear in my post and misused the word "event". What I mean is a short follow-up. For 9 days, instead of having 10 follow-ups, so 10 times the information alive/death for every animal of the same sample size (same number of animal so same events per time of measurement= same...