I have a question regarding KM analysis. I have ExpressionSet like this of the first 10 cases:
eset()
ExpressionSet (storageMode: lockedEnvironment)
assayData: 6 features, 6 samples
element names: exprs
protocolData: none
phenoData
sampleNames: 1 2 ... 6 (6 total)
varLabels: age_at_diagnosis last_follow_up_status ... lymph_nodes_removed (9 total)
varMetadata: labelDescription
featureData: none
experimentData: use 'experimentData(object)'
Annotation:
This is my expression of eset:
1 2 3 4 5 6
a 8.676978 9.653589 9.033589 8.814855 8.736406 9.274265
b 5.298711 5.378801 5.606122 5.316155 5.303613 5.449802
c 5.430877 5.199253 5.449121 5.309371 5.438538 5.347851
d 6.075331 6.687887 5.910885 5.628740 6.392422 5.908698
e 5.595625 6.010127 5.683969 5.479983 6.013500 5.939949
f 5.453928 5.454185 5.501577 5.471941 5.525027 5.531743
and here is the pData:
age Status MEN group grade size stage LNP LNR time mn doc
1 52.79 d post 4 2 18 2 1 12 3.865753 pos 0
2 32.61 d pre 3 3 16 2 5 23 1.679452 neg 1
3 66.83 a post 4 3 15 3 8 17 5.616438 pos 0
4 71.21 a post 4 3 21 2 1 12 1.169863 pos 1
5 76.84 d-d.s. post 4 3 50 2 3 24 3.602740 pos 1
6 60.77 a post 4 2 23 2 0 2 1.367123 pos 0
I know how to generate a KM curves for the whole dataset here is my code; I only give you a data of the first 10 cases as it's a limitation of space in stack website:
library(survival)
c <- Surv(as.numeric(ab$time), ab$doc)
plot(survfit( c ~ as.factor(ab$mn)))
So, my question is how can I modify this code to just for cases that are ab$mn == 'neg'
Thanks in advance,
I would follow the advice of Terry Therneau regarding how to use the Surv function, which is not to build Surv-objects outside the coxph function. This will also let you use the subset-parameter that is a handy feature of coxph:
plot(survfit( Surv(as.numeric(time), doc) ~ as.factor(mn), data=ab, subset = mn == 'neg' ))