Posterior-predictive line draws for a spaghetti overlay

Returns the observed single-case series alongside a small number of posterior-predictive replicate series, shaped for a line-graph overlay colored by baseline vs intervention condition.

Usage

ppc_overlay_draws(
  model,
  data = NULL,
  n_lines = 20L,
  mode = c("same", "new"),
  design = NULL
)

Arguments

model

A fitted brmsfit.

data

Data holding the outcome, case, phase and (optional) time columns; defaults to the model's data. Rows with a missing outcome are allowed: replicate values are set to NA there.

n_lines

Number of replicate series to return.

mode

"same" replicates for the observed cases; "new" draws new case effects from the population posterior (allow_new_levels = TRUE) to assess generalization. In both modes an observation-level random effect (one level per fitted row) is redrawn rather than conditioned on, and replicate values are set to NA wherever the observed outcome is missing so both sides use the same rows.

design

Design the model was fit with, as returned by detect_design_type. Only "alternating" changes the phase structure: conditions are pooled instead of being split into numbered runs. NULL (default) re-derives it from data, which can disagree with the design the model was fit with.

Value

A list with observed and replicates data frames (columns case (tier label), time, condition, phase (phase occurrence such as "A1"), outcome, and draw for replicates); NULL if the case, phase, or outcome column is missing, and an error if brms cannot produce posterior draws.

Examples

if (interactive()) {
  fit <- run_scd_analysis(simulate_scd_data())$model
  str(ppc_overlay_draws(fit, n_lines = 5))
}