## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)
set.seed(2026)

## ----setup--------------------------------------------------------------------
library(aiEvalR)

## ----gstudy-data--------------------------------------------------------------
design <- expand.grid(case = 1:20, prompt = 1:3, model = 1:2, run = 1:2)

# plant variance: cases differ most, then prompts, then model, then run
case_eff   <- rnorm(20, sd = 1.0)
prompt_eff <- rnorm(3,  sd = 0.5)
model_eff  <- rnorm(2,  sd = 0.3)
run_eff    <- rnorm(2,  sd = 0.2)

design$score <- 5 +
  case_eff[design$case] + prompt_eff[design$prompt] +
  model_eff[design$model] + run_eff[design$run] +
  rnorm(nrow(design), sd = 0.5)

## ----gstudy-------------------------------------------------------------------
g <- ai_generalizability(
  design,
  score  = "score",
  case   = "case",
  facets = c("prompt", "model", "run")
)
g

## ----dstudy-------------------------------------------------------------------
# dependability using 3 prompts, 2 models, 2 runs (as observed)
ai_dstudy(g, n_prompt = 3, n_model = 2, n_run = 2)

## ----dstudy-compare-----------------------------------------------------------
full    <- ai_dstudy(g, n_prompt = 3, n_model = 2, n_run = 2)
minimal <- ai_dstudy(g, n_prompt = 1, n_model = 1, n_run = 1)

c(full_phi = full$phi, minimal_phi = minimal$phi)

## ----decision-consistency-----------------------------------------------------
# rows = prompts, cols = repeated occasions; some prompts sit near a cut
responses <- rbind(
  c(9, 9, 10),   # clearly above a cut of 5 every time
  c(1, 0, 1),    # clearly below
  c(4, 6, 5)     # right on the boundary -> inconsistent
)
ai_decision_consistency(responses, cutpoint = 5)