gravatar for dec986

3 hours ago by

United States

Hello,

I'm using survminer to try to create a survival formula for a phenotype data set.

library("survival", "survminer")
data <- read.csv(file = "Study.cleaned.csv", header = TRUE)
basic.cox <- coxph(formula = Surv(Observation_time, Event_Detected) ~ Patient_Age + Sex+BMI, data = data)
basic.assump <- cox.zph(basic.cox)
sink('/home/varieties/variables.tsv')
print(basic.assump)
sink()

This produces a file that looks like this:

     rho  chisq      p
A  0.00477 0.0987 0.7534
B -0.02352 2.5383 0.1111
C  0.02513 3.2104 0.0732
GLOBAL                             NA 5.6162 0.1319

I have tried about 2,000 different combinations of each factor A through L by summing them , e.g. A+B+C, A+B+D+E... etc. but the problem is that none of the summaries have all p-values being < 0.05, which is a requirement of the study.

Also, some times factors will split, and I don't know why. The output file will look like this:

C<100       0.207766 9.59e-09 0.999922
C<50        0.188145 2.07e-08 0.999885
C<69        0.124370 9.49e-09 0.999922
C>325       0.138520 1.05e-08 0.999918
C100        0.004437 9.01e-02 0.764040
C100.0      0.189391 1.14e-08 0.999915
C101       -0.012151 6.76e-01 0.410877...

and I don't know why it's splitting like this.

I have two questions:
1. How can I determine a formula that will have all p-values < 0.05?
2. Why do some factors split like C did in the example above?

link

written
3 hours ago
by

dec986210



Source link