inst/doc/sequence-inference-and-randomization.R

In gp3sequences: Transparent Analysis of Ordered Categorical Sequences

## ----setup, include=FALSE-----------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
library(gp3sequences)

## ----data---------------------------------------------------------------------
paths <- replicate(20, sample(c("A", "B", "C"), 6L, replace = TRUE), simplify = FALSE)
data <- do.call(rbind, lapply(seq_along(paths), function(i) {
  data.frame(
    participant_id = paste0("p", i),
    sequence_id = paste0("s", i),
    sequence_order = seq_along(paths[[i]]),
    state = paths[[i]],
    group = if (i <= 10L) "control" else "treatment",
    stringsAsFactors = FALSE
  )
}))

## ----test---------------------------------------------------------------------
design <- declare_sequence_comparison_design(
  group_col = "group",
  unit_col = "participant_id",
  design = "randomized"
)

result <- test_sequence_group_difference(
  data,
  design,
  metric = "state_prevalence",
  target_state = "A",
  n_permutations = 999L,
  seed = 10L
)
result$estimate

## ----bootstrap----------------------------------------------------------------
result <- bootstrap_sequence_group_difference(
  result,
  n_boot = 999L,
  level = 0.95,
  seed = 11L
)
summarise_sequence_group_inference(result)

## ----plots, fig.width=7, fig.height=4-----------------------------------------
plot_sequence_group_inference(result, type = "permutation")
plot_sequence_group_inference(result, type = "group_means")