mutoss (version 0.1-12)

simulation: Simulation studies

Description

This function generates data according to a specified function and parameters and then applies specified procedures to the generated data. The generated data is stored in $data and the results are stored in $results. In order to recognize which results and generated data belong together every result contains an element $data.set.number. The data generating function must return a list which contains a list $procInput. Every element in $procInput will be used as an input parameter for the procedures provided by listOfProcedures.

Usage

simulation(replications, DataGen, listOfProcedures, discardProcInput=FALSE)

Value

A list with 2 elements. $data contains the objects generated by DataGen. $results contains the objects generated by the procedures augmented by the data set number and the parameter constellation.

Author

MarselScheer

Arguments

replications

The number of replications. This means how many simulation runs will be performed.

DataGen

A list that contains the function and parameters for generating data which will be analyzed be the procedures in listOfProcedures. It must contain the elements $funName (character) $fun (function)

listOfProcedures

A list of lists which contains the procedures with their parameters for the simulation.

discardProcInput

A list of lists which contains the procedures with their parameters

Examples

# this function generates pValues 
myGen <- function(n, n0) {
  list(procInput=list(pValues = c(runif(n-n0, 0, 0.01), runif(n0))), 
  groundTruth = c(rep(FALSE, times=n-n0), rep(TRUE, times=n0)))
}

sim <- simulation(replications = 10, list(funName="myGen", fun=myGen, n=200, n0=c(50,100)), 
list(list(funName="BH", 
  fun=function(pValues, alpha) BH(pValues, alpha, silent=TRUE), alpha=c(0.25, 0.5)),
list(funName="holm", fun=holm, alpha=c(0.25, 0.5),silent=TRUE)))

# the following happend:
# Call myGen(200,50) and append result to sim$data
# Apply bonferroni and holm each with alpha 0.25 and 0.5 to this data set
# Append the results to sim$restults
# Repeat this 10 times.
# Call myGen(200, 100) and append restult to sim$data
# Apply bonferroni and holm each with alpha 0.25 and 0.5 to this data set
# Append the results to sim$restults
# Repeat this 10 times.

length(sim$data)
length(sim$results)

# we now reproduce the 6th item in results
print(sim$results[[6]]$data.set.number)
print(sim$results[[6]]$parameters)

all(BH(sim$data[[2]]$procInput$pValues, 0.5, silent=TRUE)$adjPValues == sim$results[[6]]$adjPValues)

#
# Just calculating some statistics and making some plots
NumberOfType1Error <- function(data, result) sum(data$groundTruth * result$rejected)
result.all <- gatherStatistics(sim, list(NumOfType1Err = NumberOfType1Error))
result <- gatherStatistics(sim, list(NumOfType1Err = NumberOfType1Error), 
  list(median=median, mean=mean, sd=sd))
print(result)
require(lattice)
histogram(~NumOfType1Err | method*alpha, data = result.all$statisticDF)
barchart(NumOfType1Err.median + NumOfType1Err.mean ~ method | alpha, data = result$statisticDF)