bootmlx: Bootstrapping - case resampling
In MarcLavielle/Rsmlx: R Speaks 'Monolix'

bootmlx

R Documentation

Bootstrapping - case resampling

Description

Generate replicates of the original data using random sampling with replacement. Population parameters are then estimated from each replicate.

Usage

bootmlx(
  project,
  nboot = 100,
  dataFolder = NULL,
  parametric = FALSE,
  tasks = c(populationParameterEstimation = TRUE),
  settings = NULL
)

Arguments

`project`	Monolix project
`nboot`	[optional] number of bootstrap replicates (default=100)
`dataFolder`	[optional] folder where already generated datasets are stored, e.g dataFolder="./dummy_project/boot/" (default: data set are generated by bootmlx)
`parametric`	[optional] boolean to define if parametric bootstrap is performed (new data is drawn from the model), (default: false)
`tasks`	[optional] vector of booleans defining the list of tasks to perform (default: estimation of the population parameters) available tasks: populationParameterEstimation, conditionalDistributionSampling, conditionalModeEstimation, standardErrorEstimation, logLikelihoodEstimation, plots
`settings`	[optional] a list of settings for the resampling and the results: `N` the number of individuals in each bootstrap data set (default value is the number of individuals in the original data set). `newResampling` boolean to generate the data sets again if they already exist (default=FALSE). `covStrat` a categorical covariate of the project. The original distribution of this covariate is maintained in each resampled data set if covStrat is defined (default=NULL). Notice that if the categorical covariate is varying within the subject (in case of IOV), it will not be taken into account. `plot` boolean to choose if the distribution of the bootstraped esimates is displayed (default = FALSE) `level` level of the bootstrap confidence intervals of the population parameters (default = 0.90) `seed` a positive integer < 2147483647, seed for the generation of the data sets (default = NA) `deleteData` delete created data set files after estimation (default = FALSE) `deleteProjects` delete created Monolix projects after estimation (default = FALSE)

Details

Bootstrap functionality is now available directly in the lixoftConnectors package using the function runBootstrap. Please migrate, as this function will be deprecated in the future.

Value

a data frame with the bootstrap estimates

Examples

## Not run: 
# RsmlxDemo1.mlxtran is a Monolix project for modelling the PK of warfarin using a PK model 
# with parameters ka, V, Cl.

# In this example, bootmlx will generate 100 random replicates of the original data and will
# use Monolix to estimate the population parameters from each of these 100 replicates:
r1 <- bootmlx(project="RsmlxDemo1.mlxtran")
  
# 5 replicates will now be generated, with 50 individuals in each replicate:
r2 <- bootmlx(project="RsmlxDemo1.mlxtran",  nboot = 5, settings = list(N = 50))

# Proportions of males and females in the original dataset will be preserved   
# in each replicate:
r3 <- bootmlx(project="RsmlxDemo1.mlxtran",  settings = list(covStrat = "sex"))

## End(Not run)

# See http://monolix.lixoft.com/rsmlx/bootmlx/ for detailed examples of use of bootmlx
# Download the demo examples here: http://monolix.lixoft.com/rsmlx/installation

MarcLavielle/Rsmlx documentation built on March 1, 2024, 2:01 a.m.