library(survival) 
##############################################################
n<-200
y<-rweibull(n,shape=2,scale=10)
cy<-runif(n,0,100)
stat<-as.numeric(y<cy)
test.data<-data.frame(y=y,z=stat)

plot(survfit(Surv(y,z)~1,data=test.data))
xv<-seq(0,25,by=0.05)
Sv<-1-pweibull(xv,shape=2,scale=10)
lines(xv,Sv,col="red")

#############################################################
aml
?aml

Surv(aml$time, aml$status)

?Surv

survfit(Surv(aml$time,aml$status)~1)

fit1 <- survfit(Surv(aml$time,aml$status)~1)
plot(fit1)

fit2 <- survfit(Surv(time,status)~x,data=aml)
plot.survfit(fit2,lty=1:2)

leukemia.surv <- survfit(Surv(time, status) ~ x, data = aml) 
plot(leukemia.surv, lty = 2:3) 
legend(100, .9, c("Maintenance", "No Maintenance"), lty = 2:3) 
title("Kaplan-Meier Curves\nfor AML Maintenance Study") 
lsurv2 <- survfit(Surv(time, status) ~ x, aml, type='fleming') 
plot(lsurv2, lty=2:3, fun="cumhaz", 
	xlab="Months", ylab="Cumulative Hazard") 

survdiff(Surv(time, status)~x, data=aml)

##############################################################

survreg(Surv(time, status)~x, dist="exponential", data=aml)

fit1 <- survreg( Surv(time, status)~x, data=aml, dist="exponential")
predict(fit1, type="quantile", p=c(0.1, 0.5, 0.9) )

amlnew <- data.frame(aml, x1=c(rep(0,11), rep(1,12)) )
survreg(Surv(time, status)~offset(0.3*x1), data=amlnew, dist="weibull")

data(cancer)
summary( survreg(Surv(time, status) ~ age+sex, data=cancer, dist="weibull") )
betas <- 1:95/100
llik <- rep(0, 95)
for(i in 1:95) {
	llik[i] <- survreg(Surv(time, status) ~ age+offset(betas[i]*sex),
					data=cancer, dist="weibull")$loglik[2]
}
plot( betas, llik, type="l" )
abline( h = max(llik) - 3.84/2 )

##############################################################

coxfit1 <- coxph(Surv(time, status)~x, data=aml)
summary(coxfit1)