PBRF (version 1.0.0)

pbf2: prob being in response function

Description

Calculate the probability of being in response function (PBRF) and the variances

Usage

pbf2(y1,y2,d1,d2,times=y2[order(y2)])

Arguments

y1

a numeric vector of event times denoting the minimum of event times \(T_1\), \(T_2\) and censoring time \(C\), where \(T_2\) corresponds to the event time, \(T_1\) corresponds to the response time.

y2

a numeric vector of event times denoting the minimum of event time \(T_2\) and censoring time \(C\). Clearly, y2 is not smaller than y1.

d1

a numeric vector of event indicators with 1 denoting the response is observed and 0 denoting otherwise.

d2

a numeric vector of event indicators with 1 denoting the event is observed and 0 denoting otherwise.

times

a numeric vector of timepoints at which we want to estimate the PBRF

Value

pbrf

The estimates at each timepoints (row) and by methods 1-5 (column)

vpbrf

The variance estimates at each timepoints (row) and by methods 1-5 (column)

Details

There three methods to estimate PBRF: the subtraction, the division and the Semi-Markov methods are presented in Tsai et al. (2017). There are two sub-methods for division and the Semi-Markov methods when the censoring distrbution is estimated in two different ways (looking at y1=min(\(T_1\),\(T_2\),\(C\)) and at y2=min(\(T_2\),\(C\))). So there are 5 methods in total reported. Method 1: division and based on y1; Method 2: division and based on y2; Method 3: Semi-Markov and based on y1; Method 4: Semi-Markov and based on y2; Method 5: subtraction. The methods based on y2 perform better than the corresponding ones based on y1.

References

Tsai W.Y., Luo X., Crowley J. (2017) The Probability of Being in Response Function and Its Applications. In: Matsui S., Crowley J. (eds) Frontiers of Biostatistical Methods and Applications in Clinical Oncology. Springer, Singapore. <doi: 10.1007/978-981-10-0126-0_10>.

Examples

# NOT RUN {
  n<-300
  rho<-0.5
  lambda10<-0.1;lambda20<-0.08;lambdac0<-0.09
  lam1<-rep(0,n);lam2<-rep(0,n);lamc<-rep(0,n)
  z<-rep(0,n)
  z[1:(n/2)]<-1
  lam1<-lambda10
  lam2<-lambda20
  lamc<-lambdac0
  tem<-matrix(0,ncol=3,nrow=n)
  
  y2y<-matrix(0,nrow=n,ncol=3)
  y2y[,1]<-rnorm(n);y2y[,3]<-rnorm(n)
  y2y[,2]<-rho*y2y[,1]+sqrt(1-rho^2)*y2y[,3]
  tem[,1]<--log(1-pnorm(y2y[,1]))/lam1
  tem[,2]<--log(1-pnorm(y2y[,2]))/lam2
  tem[,3]<--log(1-runif(n))/lamc
  
  y1<-apply(tem,1,min)
  y2<-apply(tem[,2:3],1,min)
  d1<-as.numeric(tem[,1]<=y1)
  d2<-as.numeric(tem[,2]<=y2)
  btemp<-pbf2(y1,y2,d1,d2,times=c(1,3,5))
  btemp
# }