Skip to main content
Skip table of contents

runModelBuilding

Run model building for automatic covariate model building or automatic statistical model building. The current settings for running model building can been seen by calling getModelBuildingSettings and the returned settings can be modified and used for the settings argument. See example.

Usage

R
runModelBuilding(...)

Arguments

...

[optional] Settings to initialize the model building algorithm. See getModelBuildingSettings for a description of settings. Settings can be passed individually as name-value pairs or together in a single list.

See also

getModelBuildingSettings for a description of settings
getModelBuildingResults to get results

Examples

R
initializeLixoftConnectors("monolix")
project_file <- file.path(getDemoPath(), "1.creating_and_using_models", "1.1.libraries_of_models", "theophylline_project.mlxtran")
loadProject(project_file)

if (FALSE) {
# these two lines are equivalent
runModelBuilding()
runModelBuilding(settings = getModelBuildingSettings())
}

# settings can be set individually as name-value pairs
runModelBuilding(useLin = FALSE, covariates = "SEX", strategy = "cossac")

# or settings can be modified in the list returned from getModelBuildingSettings, then passed to runModelBuilding
mbSettings <- getModelBuildingSettings()

# for example, to force including the covariate SEX on parameter ka, 
# and to exclude the covaraite WEIGHT from parameter V
mbSettings$covariates <- c("SEX", "WEIGHT")
mbSettings$relationships[1,] = c("ka", "SEX", TRUE)
mbSettings$relationships[2,] = c("V", "WEIGHT", FALSE)
mbSettings$relationships
#>   parameters covariates locked
#> 1         ka        SEX   TRUE
#> 2          V     WEIGHT  FALSE

runModelBuilding(settings = mbSettings)
getModelBuildingResults()
#> [[1]]
#> [[1]]$BICc
#> [1] 373.2566
#> 
#> [[1]]$LL
#> [1] 339.3795
#> 
#> [[1]]$tested
#> [1] "" ""
#> 
#> [[1]]$individualModels
#>      SEX WEIGHT
#> Cl FALSE  FALSE
#> V  FALSE  FALSE
#> ka  TRUE  FALSE
#> 
#> [[1]]$bestModel
#> [1] TRUE
#> 
#> 
JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.