在尝试将 Weibull 比例风险模型拟合到gehanR 中的数据时，我注意到更改gehan数据的顺序会更改输出。
library(MASS)
library(survival)
attach(gehan)
survreg(Surv(time, cens) ~ treat, gehan, dist = "weibull")
产生以下输出：
Call:
survreg(formula = Surv(time, cens) ~ treat, data = gehan, dist = "weibull")
Coefficients:
(Intercept) treatcontrol
3.515687 -1.267335
Scale= 0.7321944
Loglik(model)= -106.6 Loglik(intercept only)= -116.4
Chisq= 19.65 on 1 degrees of freedom, p= 9.3e-06
n= 42
但是，当我手动将数据输入 R 时，
control <- c(1,1,2,2,3,4,4,5,5,8,8,8,8,11,11,12,12,15,17,22,23)
control.status <- c(rep(1,21))
treatment <- c(6,6,6,6,7,9,10,10,11,13,16,17,19,20,22,23,25,32,32,34,35)
treatment.status <- c(1,1,1,0,1,0,1,0,0,1,1,0,0,0,1,1,0,0,0,0,0)
new.time <- c(control,treatment)
new.status <- c(control.status,treatment.status)
group <- as.factor(c(rep("control",21),rep("treatment",21)))
parametrik.surv <- Surv(new.time, new.status)
parametrik.fit <- survreg( parametrik.surv ~ group, dist="w")
这是一个稍微不同的输出：
Call:
survreg(formula = parametrik.surv ~ group, dist = "w")
Coefficients:
(Intercept) grouptreatment
2.248352 1.267335
Scale= 0.7321944
Loglik(model)= -106.6 Loglik(intercept only)= -116.4
Chisq= 19.65 on 1 degrees of freedom, p= 9.3e-06
n= 42
此外，在一本书 beta_0 中，beta_1 和 scale 分别给出为 0.98 、 1.27 和 1.37 。知道是什么原因造成的吗？