R语言问题：cox回归分析报错，Loglik converged before variable 1 ； coefficient may be infinite.

最新推荐文章于 2024-08-08 14:59:55 发布

？！27

最新推荐文章于 2024-08-08 14:59:55 发布

阅读量1.6k

点赞数 8

文章标签： r语言回归

本文链接：https://blog.csdn.net/qq_59360476/article/details/136669285

版权

代码：

library(survival)
library(survminer)

coxPfilter=0.05
inputFile="TCGA.expTime.txt"
setwd("D:/01/16.uniCox")

rt=read.table(inputFile, header=T, sep="\t", check.names=F, row.names=1)
rt$futime=rt$futime/365

outTab=data.frame()
sigGenes=c("futime","fustat")
for(i in colnames(rt[,3:ncol(rt)])){
cox <- coxph(Surv(futime, fustat) ~ rt[,i], data = rt)
coxSummary = summary(cox)
coxp=coxSummary$coefficients[,"Pr(>|z|)"]
if(coxP<coxPfilter){
sigGenes=c(sigGenes,i)
outTab=rbind(outTab,
cbind(id=i,
HR=coxSummary$conf.int[,"exp(coef)"],
HR.95L=coxSummary$conf.int[,"lower .95"],
HR.95H=coxSummary$conf.int[,"upper .95"],
pvalue=coxSummary$coefficients[,"Pr(>|z|)"])
)
}
}

报错：

Warning messages:
1: In coxph.fit(X, Y, istrat, offset, init, control, weights = weights,  :
  Loglik converged before variable  1 ; coefficient may be infinite. 
2: In coxph.fit(X, Y, istrat, offset, init, control, weights = weights,  :
  Loglik converged before variable  1 ; coefficient may be infinite. 
3: In coxph.fit(X, Y, istrat, offset, init, control, weights = weights,  :
  Loglik converged before variable  1 ; coefficient may be infinite. 
...

即：在 coxph.fit（X， Y， istrat， offset， init， control， weights = weights，：
Loglik 收敛于变量 1 之前;系数可以是无限的。

数据不大，数据处理时已标准化，且没有空缺值，但是不知道怎么改，求大佬指点。