Question: survival analysis with a continuos variable
gravatar for igor
3.8 years ago by
United States
igor11k wrote:

I am trying to correlate survival with a continuous variable (for example, gene expression). I've been using the survival package in R to deal with survival data and it seems to be very comprehensive, but there does not seem to be a way to do correlation. Is there a proper method for that?

I am concerned it's not appropriate or not possible for survival data. Maybe that is why variables are binned by group in all the survival data that I have seen.

However, there is a Cox proportional hazards regression model test that is implemented in the coxph() function. That sounds like the most appropriate alternative. Is it?

survival R • 5.2k views
ADD COMMENTlink modified 3.8 years ago by sviatoslav.kendall770 • written 3.8 years ago by igor11k
gravatar for sviatoslav.kendall
3.8 years ago by
United States
sviatoslav.kendall770 wrote:

When I do survival analysis with a continuous variable as the predictor, I use the coxph() function something like this:

coxph_obj = coxph(Surv(my_Data$Survival_Time, my_Data$Survival_Event) ~ my_Data$Continous_Variable)

But here's an older post that you might find helpful: R survival analysis

ADD COMMENTlink written 3.8 years ago by sviatoslav.kendall770

I saw that post and found it very helpful. I mainly wanted to check if coxph is the best approach or if there better methods.

ADD REPLYlink written 3.8 years ago by igor11k
Please log in to add an answer.


Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.3.0
Traffic: 1715 users visited in the last hour