"get_prior() shows only one group random intercept prior when using gr(by = ...), shouldn't there be two as this model assumes groups being drawn from separate distributions?"

Interfaces brms
,
1

Short summary of the problem

brm.formula.1 <- bf(
  y ~ 0 + group+ 
    # Group-specific independent random intercepts
    (1 | gr(ID, by = group)), 
  sigma ~ 0 + group
)


prior_1 <- 
  # coefficients
  prior(normal(log(250), 50), class = "b", coef = "groupA") +
  prior(normal(log(250), 50), class = "b", coef = "groupB") +
  # intercepts
  prior(student_t(3, 0, 1), class = "sd", group = "ID:groupA", coef = "Intercept") +
  prior(student_t(3, 0, 1), class = "sd", group = "ID:groupB", coef = "Intercept") +
  # sigma
  prior(student_t(3, 0, 2), class = "b", dpar = "sigma", coef = "groupA") +
  prior(student_t(3, 0, 2), class = "b", dpar = "sigma", coef = "groupB")

The above code doesnt work for me. brms tells me that it couldnt find the names for the random intercept priors.

When using get_prior(), only a single prior is shown for the random-intercept distribution.

Following this I checked the the priors using prior_summary and it seems like only one sd intercept prior is can be set and this is applied to each group of by = group.

Is this the correct understanding @paul.buerkner