simulate,DualResponsesDesign-method {crmPack}

This is a methods to simulate dose escalation procedure using both DLE and efficacy responses. This is a method based on the DualResponsesDesign where DLEmodel used are of ModelTox class object and efficacy model used are of ModelEff class object. In addition, no DLE and efficacy samples are involved or generated in the simulation process

Description

This is a methods to simulate dose escalation procedure using both DLE and efficacy responses. This is a method based on the DualResponsesDesign where DLEmodel used are of ModelTox class object and efficacy model used are of ModelEff class object. In addition, no DLE and efficacy samples are involved or generated in the simulation process

Usage

## S4 method for signature 'DualResponsesDesign'
simulate(
  object,
  nsim = 1L,
  seed = NULL,
  trueDLE,
  trueEff,
  trueNu,
  args = NULL,
  firstSeparate = FALSE,
  parallel = FALSE,
  nCores = min(parallel::detectCores(), 5),
  ...
)

Arguments

object

the DualResponsesDesign object we want to simulate the data from

nsim

the number of simulations (default :1)

seed

see setSeed

trueDLE

a function which takes as input a dose (vector) and returns the true probability (vector) of the occurrence of a DLE. Additional arguments can be supplied in args.

trueEff

a function which takes as input a dose (vector) and returns the expected efficacy responses (vector). Additional arguments can be supplied in args.

trueNu

the precision, the inverse of the variance of the efficacy responses

args

data frame with arguments for the trueDLE and trueEff function. The column names correspond to the argument names, the rows to the values of the arguments. The rows are appropriately recycled in the nsim simulations.

firstSeparate

enroll the first patient separately from the rest of the cohort? (not default) If yes, the cohort will be closed if a DLT occurs in this patient.

parallel

should the simulation runs be parallelized across the clusters of the computer? (not default)

nCores

how many cores should be used for parallel computing? Defaults to the number of cores on the machine, maximum 5.

...

not used

Value

an object of class PseudoDualSimulations

Examples

##Simulate dose-escalation procedure based on DLE and efficacy responses where no DLE 
## and efficacy samples are used
## we need a data object with doses >= 1:
data <- DataDual(doseGrid=seq(25,300,25),placebo=FALSE)
##First for the DLE model 
##The DLE model must be of 'ModelTox' (e.g 'LogisticIndepBeta') class 
DLEmodel <- LogisticIndepBeta(binDLE=c(1.05,1.8),
                              DLEweights=c(3,3),
                              DLEdose=c(25,300),
                              data=data)

##The efficacy model of 'ModelEff' (e.g 'Effloglog') class 
Effmodel<-Effloglog(Eff=c(1.223,2.513),Effdose=c(25,300),
                    nu=c(a=1,b=0.025),data=data,c=0)

##The escalation rule using the 'NextBestMaxGain' class
mynextbest<-NextBestMaxGain(DLEDuringTrialtarget=0.35,
                            DLEEndOfTrialtarget=0.3)


##The increments (see Increments class examples) 
## 200% allowable increase for dose below 300 and 200% increase for dose above 300
myIncrements<-IncrementsRelative(intervals=c(25,300),
                                 increments=c(2,2))
##cohort size of 3
mySize<-CohortSizeConst(size=3)
##Stop only when 36 subjects are treated
myStopping <- StoppingMinPatients(nPatients=36)
##Now specified the design with all the above information and starting with a dose of 25

##Specified the design(for details please refer to the 'DualResponsesDesign' example)
design <- DualResponsesDesign(nextBest=mynextbest,
                              model=DLEmodel,
                              Effmodel=Effmodel,
                              stopping=myStopping,
                              increments=myIncrements,
                              cohortSize=mySize,
                              data=data,startingDose=25)
##Specify the true DLE and efficacy curves
myTruthDLE<- function(dose)
{ DLEmodel@prob(dose, phi1=-53.66584, phi2=10.50499)
}

myTruthEff<- function(dose)
{Effmodel@ExpEff(dose,theta1=-4.818429,theta2=3.653058)
}

##The true gain curve can also be seen
myTruthGain <- function(dose)
{return((myTruthEff(dose))/(1+(myTruthDLE(dose)/(1-myTruthDLE(dose)))))}


## Then specified the simulations and generate the trial 
##For illustration purpose only 1 simulation is produced (nsim=1). 
options<-McmcOptions(burnin=100,step=2,samples=200)
mySim <-simulate(object=design,
                 args=NULL,
                 trueDLE=myTruthDLE,
                 trueEff=myTruthEff,
                 trueNu=1/0.025,
                 nsim=1,
                 seed=819,
                 parallel=FALSE)