Run likelihood profile for a FIMS model

This function runs a likelihood profile for a FIMS model by fixing a specified parameter at a range of values spanning the initial value.

Usage

run_fims_likelihood(
  model,
  parameters,
  data,
  module_name = NULL,
  parameter_name = "log_rzero",
  n_cores = NULL,
  min = -2,
  max = 2,
  length = 5
)

Arguments

model

Output from estimate_fims(), currently only used to get the estimated value for log_rzero.

parameters

A FIMS parameters object containing the model parameters.

data

A dataframe or tibble containing the model data, or a FIMSFrame object.

parameter_name

A string specifying the parameter to profile over, e.g., "log_rzero".

n_cores

The number of cores to use to run likelihood profile in parallel. Default is parallel::detectCores() - 1.

min

The minimum value for the parameter profile relative to the initial value.

max

The maximum value for the parameter profile relative to the initial value.

length

The number of values to generate between min and max. An odd number is recommended to include the initial value.

Value

A list containing the vector of parameter values and a dataframe with the estimates for each model.

Examples

if (FALSE) { # \dontrun{
 library(FIMS)
# Use built-in dataset from FIMS
 data("data1")
 data_4_model <- FIMSFrame(data1)
# Create a parameters object
 parameters <- data_4_model |>
   create_default_configurations() |>
   create_default_parameters(data = data_4_model)
# Run the  model with optimization
 base_model <- parameters |>
   initialize_fims(data = data_4_model) |>
   fit_fims(optimize = TRUE)
 like_fit <- run_fims_likelihood(
   model = base_model,
   parameters = parameters,
   parameter_name = "log_rzero",
   data = data1,
   n_cores = 3,
   min = -1,
   max = 1,
   length = 3
  )

} # }