Simulate skewed RT data for the factorial design — simulate_rt

This function simulates response time data for the factorial design of the experiment. It was used for power analyses by simulation.

Inspired by Chris Jungerius.

Usage

simulate_rt_data(
  n_subj_per_group,
  meanlog = 2.1,
  sdlog = 0.55,
  shift = 5,
  tau_0 = 0.9,
  tau_vis = 0.75,
  tau_spa = 0,
  beta_aph = 0,
  beta_vis = 0,
  beta_spa = 0,
  beta_aph_vis = 0,
  beta_aph_spa = 0,
  seed = NULL,
  ...
)

Arguments

n_subj_per_group: Number of subjects per group. The total number of subjects will be n_subj_per_group * 2.
meanlog: Mean of the log-normal distribution for the base RT values.
sdlog: Standard deviation of the log-normal distribution for the base RT values.
shift: Non-decision time, i.e., the minimum value of the RTs.
tau_0: By-subject random intercept standard deviation.
tau_vis: By-subject random slope standard deviation for the visual category.
tau_spa: By-subject random slope standard deviation for the spatial category.
beta_aph: Effect of the aphantasia group on the RTs.
beta_vis: Effect of the visual category on the RTs.
beta_spa: Effect of the spatial category on the RTs.
beta_aph_vis: Effect of the interaction between the aphantasia group and the visual category on the RTs.
beta_aph_spa: Effect of the interaction between the aphantasia group and the spatial category on the RTs.
seed: Random seed for reproducibility. If NULL, no seed is set.
...: Additional arguments passed to the function. Unused.

Value

A dataframe with the simulated RT data.

Examples

# No main effects
df <- simulate_rt_data(100)
head(df)
#> # A tibble: 6 × 12
#>   id    group    category rt_total trial tau_0 tau_vis tau_spa beta_0 aphantasia
#>   <chr> <fct>    <fct>       <dbl> <int> <dbl>   <dbl>   <dbl>  <dbl>      <dbl>
#> 1 id001 Aphanta… Visual       36.5     1 0.919   0.898       0  34.7           1
#> 2 id001 Aphanta… Visual       11.6     2 0.919   0.898       0   9.77          1
#> 3 id001 Aphanta… Visual       20.2     3 0.919   0.898       0  18.4           1
#> 4 id001 Aphanta… Visual       14.6     4 0.919   0.898       0  12.8           1
#> 5 id001 Aphanta… Visual       13.7     5 0.919   0.898       0  11.9           1
#> 6 id001 Aphanta… Visual       10.6     6 0.919   0.898       0   8.78          1
#> # ℹ 2 more variables: visual <dbl>, spatial <dbl>

df |>
  dplyr::group_by(group, category) |>
  dplyr::reframe(
    mean_rt = mean(rt_total),
    median_rt = median(rt_total),
    sd_rt = sd(rt_total),
    min_rt = min(rt_total),
    max_rt = max(rt_total)
  )
#> # A tibble: 6 × 7
#>   group      category mean_rt median_rt sd_rt min_rt max_rt
#>   <fct>      <fct>      <dbl>     <dbl> <dbl>  <dbl>  <dbl>
#> 1 Aphantasia Control     14.2      13.1  5.68   5.78   64.3
#> 2 Aphantasia Spatial     14.9      13.5  5.91   5.70   57.3
#> 3 Aphantasia Visual      14.5      13.0  5.97   4.90   41.0
#> 4 Typical    Control     14.5      13.2  5.47   4.94   45.0
#> 5 Typical    Spatial     14.4      13.2  5.28   5.96   45.7
#> 6 Typical    Visual      14.1      13.0  5.47   5.39   46.9

# Visual category effect around 2.5s
df <- simulate_rt_data(100, beta_vis = 2.5)
df |>
  dplyr::group_by(group, category) |>
  dplyr::reframe(
    mean_rt = mean(rt_total),
    median_rt = median(rt_total),
    sd_rt = sd(rt_total),
    min_rt = min(rt_total),
    max_rt = max(rt_total)
  )
#> # A tibble: 6 × 7
#>   group      category mean_rt median_rt sd_rt min_rt max_rt
#>   <fct>      <fct>      <dbl>     <dbl> <dbl>  <dbl>  <dbl>
#> 1 Aphantasia Control     14.2      12.7  5.28   5.76   45.3
#> 2 Aphantasia Spatial     14.5      13.3  5.79   4.65   67.7
#> 3 Aphantasia Visual      17.0      15.6  5.87   7.42   65.6
#> 4 Typical    Control     14.4      13.0  5.76   5.19   52.5
#> 5 Typical    Spatial     14.2      13.0  5.54   5.93   60.1
#> 6 Typical    Visual      16.8      15.6  5.41   8.55   52.1