interaction term in brms

brm.R

library(brms)
library(tidyverse)

set.seed(123)  

# generate some subject-averaged data
n_subjects <- 100

data <- tibble(
  id = 1:n_subjects, 
  congruent_informative = rnorm(n_subjects, 500, 60), 
  incongruent_informative = rnorm(n_subjects, 500, 60),
  congruent_noninformative = rnorm(n_subjects, 500, 60),
  incongruent_noninformative = rnorm(n_subjects, 500, 60),
) |> 
  pivot_longer(cols = congruent_informative:incongruent_noninformative, 
               names_sep = "_", 
               names_to = c("congruency", "cue"), 
               values_to = "rt")

# fit the model
# of course, ex-G is bad choice for this subject-averaged simulated data
model <- brm(rt ~ congruency * cue + (1|id), 
             data = data, 
             family = exgaussian(), 
             cores = 4)

summary(model)

# Population-Level Effects: 
#                                         Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
# Intercept                                 505.59      5.79   494.38   517.35 1.00     3755     2505
# congruencyincongruent                     -12.24      8.33   -29.04     3.86 1.00     3511     2635
# cuenoninformative                           1.68      8.26   -14.45    17.67 1.00     3552     2613
# congruencyincongruent:cuenoninformative     2.53     11.57   -20.01    25.80 1.00     3098     2293
# 
# Family Specific Parameters: 
#   Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
# sigma    55.01      3.71    46.66    60.88 1.00     2638     2786
# beta     15.10      9.73     2.03    35.04 1.00     1975     2215