1
$\begingroup$

Consider the line of code below for implementing Cox model in R and finding the hazard ratio:

 fitcox <- coxph(Surv(Survival,Death) ~ clusters, data = data)

Here "clusters" is a vector with 30 values as 1, 30 values as 2 ,30 values a 3 and 30 values as 4. The Kaplan-Meier graph consists of 4 plots ; one for each cluster. When I run the above command, the hazard ratio comes out to be 1.3154 (i.e. exp(coef) in R). What does that mean? I mean I have 4 groups but hazard ratio is supposed to be between 2 groups only. What does R mean by 1.3154?

Further Information:

head(data)

Survival Death clusters

" 345"   "0"   "1" 

"  85"   "0"   "1"

"1058"   "0"   "1" 

" 964"   "1"   "1" 

"1315"   "0"   "2" 

" 669"   "0"   "2"

 summary(fitcox)

enter image description here

https://i.stack.imgur.com/96DMh.png

Improve this question
$\endgroup$
8
  • 2
    $\begingroup$ Can you plot the raw output and a sample of the data? Something like the output of head(data) $\endgroup$
    – Demetri Pananos
    Apr 5, 2019 at 17:33
  • $\begingroup$ Please consider it now. $\endgroup$
    – Omar Rafique
    Apr 5, 2019 at 18:54
  • $\begingroup$ Yea. This is what I was looking for. Thanks with $as.factor$ it is giving me 3 hazard ratios for clusters1, cluster2, cluster3. Does it mean that cluster1 is the reference? $\endgroup$
    – Omar Rafique
    Apr 5, 2019 at 19:05
  • 1
    $\begingroup$ Since this is what it was i post it as the answer.. $\endgroup$
    – user213325
    Apr 5, 2019 at 19:08
  • 2
    $\begingroup$ Yes, this is normal behavior. You can read about dummy coding, here for example statisticssolutions.com/dummy-coding-the-how-and-why $\endgroup$
    – user213325
    Apr 5, 2019 at 19:21

1 Answer 1

Reset to default
2
$\begingroup$

I guess your predictor has the class "numeric" and thus R thinks it is one continuous variable and determines the hazard ratio for this one variable. If this is the case all you need to do is 

data$clusters <- as.factor(data$clusters)

After that R will provide three hazard ratios, each showing the hazard ratio of a given group versus the reference. You can change the refernce group with.

data$clusters <- relevel(data$clusters, "name_of_group")
Improve this answer
$\endgroup$
0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.