Skip to contents

Process: Simulating Fake Data

Source: R/process_simulate_list.R
simulate_list.Rd

This function generates random input parameters for a model based on user-specified distributions. For example, if the first parameter, eta, is set to follow a uniform distribution from 0 to 1, its values will be randomly sampled from U(0, 1).

You can also specify parameters to be drawn from a normal distribution. For example, eta = function() { stats::rnorm(n = 1, mean = 0.5, sd = 0.1) } . Make sure the last parameter, which typically represents the inverse temperature parameter in the soft-max function, is sampled from an exponential distribution.

Usage

simulate_list(
  data,
  id = 1,
  n_params,
  n_trials,
  obj_func,
  rfun,
  iteration = 10,
  seed = 123
)

Arguments

data

[data.frame]

This data should include the following mandatory columns:

  • "sub"

  • "time_line" (e.g., "Block", "Trial")

  • "L_choice"

  • "R_choice"

  • "L_reward"

  • "R_reward"

  • "sub_choose"

id

[vector]

Specifies which subject's data to use. In parameter and model recovery analyses, the specific subject ID is often irrelevant. Although the experimental trial order might have some randomness for each subject, the sequence of reward feedback is typically pseudo-random.

The default value for this argument is NULL. When id = NULL, the program automatically detects existing subject IDs within the dataset. It then randomly selects one subject as a sample, and the parameter and model recovery procedures are performed based on this selected subject's data.

default: id = NULL

n_params

[integer]

The number of free parameters in your model.

n_trials

[integer]

The total number of trials in your experiment.

obj_func

[function]

The objective function that the optimization algorithm package accepts. This function must strictly take only one argument, params (a vector of model parameters). Its output must be a single numeric value representing the loss function to be minimized. For more detailed requirements and examples, please refer to the relevant documentation ( TD, RSTD, Utility ).

rfun

[List]

A nested list of functions used to generate random parameter values for simulation. The top-level elements of the list should be named according to the models. Each of these elements must be a named list of functions, where each name corresponds to a model parameter and its value is the random number generation function.

e.g., stats::runif, stats::rexp

iteration

[integer]

This parameter determines how many simulated datasets are created for subsequent model and parameter recovery analyses.

default: iteration_s = 10

seed

[integer]

Random seed. This ensures that the results are reproducible and remain the same each time the function is run.

default: seed = 123

Value

a list with fake data generated by random free parameters

Examples

if (FALSE) { # \dontrun{
list_simulated <- binaryRL::simulate_list(
  data = binaryRL::Mason_2024_G2,
  obj_func = binaryRL::RSTD,
  n_params = 3,
  n_trials = 360,
  rfun = list(
    etan = function() { stats::runif(n = 1, min = 0, max = 1) },
    etap = function() { stats::runif(n = 1, min = 0, max = 1) },
    tau = function() { stats::rexp(n = 1, rate = 1) }
  ),
  iteration = 10
)
} # }