Posterior decision summary for fixed-effect coefficients

For each fixed-effect coefficient (b_*) in the model, returns posterior mean, SD, credible interval, probability of direction (pd), and optional probability of meaningful change and ROPE-probability. Posteriors are on the link scale (Stan parameterization).

Usage

summarize_fixed_effect_decisions(
  model,
  threshold = NULL,
  rope = NULL,
  intervention_goal = c("increase", "decrease"),
  ci_level = 0.95
)

Arguments

model

A fitted brmsfit.

threshold

Numeric. A positive magnitude expressed on the improvement-oriented scale (i.e., after any decrease reflection). If supplied, the posterior probability that the effect meets or exceeds this magnitude in the goal direction is reported as prob_meaningful_change.

rope

Numeric length-2. ROPE bounds on the link scale, expressed on the native coefficient scale. For intervention_goal = "decrease" the bounds are reflected together with the draws, so an asymmetric ROPE stays attached to the same parameter region. If supplied, posterior probability inside the ROPE is reported as rope_prob.

intervention_goal

"increase" (default) or "decrease". For "decrease", every reported coefficient is sign-flipped so that a positive value denotes improvement (full reflection onto an improvement-oriented scale); pd is unchanged and the ROPE is reflected with the draws. Intercept and ordinal threshold terms (b_Intercept) are excluded from the table, so only treatment, trend, and moderator slopes are reported.

ci_level

Credible interval width (default 0.95).

Value

A data frame with one row per fixed-effect term and columns term, mean, sd, lower, upper, pd, prob_meaningful_change, rope_prob. For a log link, the response-scale incidence-rate ratio columns irr, irr_lower, irr_upper are attached; for a logit link, the odds-ratio columns or, or_lower, or_upper. These ratios are exp() of the native (unreflected) coefficient, so they carry the conventional definition regardless of intervention_goal; only the mean/lower/upper columns are reflected for direction. An identity link attaches nothing, since link scale equals response scale.

Examples

if (interactive()) {
  dat <- simulate_scd_data()
  fit <- brms::brm(outcome ~ phase + (1 | case), data = dat, refresh = 0)
  summarize_fixed_effect_decisions(fit, threshold = 0.5,
                                   rope = c(-0.1, 0.1))
}