Strip plot of p-values after each deletion

Each dot is one refit with one unit removed, on a p-value axis (linear by default, log on request), one strip per leave-one-out family; the diamond is the pre-specified analysis with nothing removed and the dashed line is alpha. Counts of deletions below alpha label each strip.

Usage

plot_pstrip(
  x,
  alpha = NULL,
  log_p = FALSE,
  xmax = NULL,
  label_family = TRUE,
  highlight = NULL,
  seed = 1L
)

Arguments

x

A stress_census, a stress_result, or a list of them (one strip each).

alpha

Significance level; defaults to the census's own.

log_p

Draw the p-value axis on a log scale (spreads out the small p-values; harder to read for most audiences).

xmax

Upper limit of the linear p-value axis; NULL fits the data.

label_family

Include the deletion family in each strip label; set FALSE when every census contributes one family (subjects only, say).

highlight

Optional labels of deletion rows (the removed unit, as in the census label column) to ring and label, for example the participant whose removal crosses alpha. Use mask_ids() first if identifiers must not appear.

seed

Seed of the vertical scatter within each strip, so the figure is the same every time it is drawn; the caller's random-number state is restored on exit.

Value

A ggplot object.

Examples

small <- mmrm::fev_data[mmrm::fev_data$USUBJID %in% paste0("PT", 1:60), ]
spec <- stress_spec(small, "FEV1", "USUBJID", "AVISIT", "ARMCD", "PBO", covariates = ~ FEV1_BL,
                    covariance = "cs", method = "Satterthwaite", vcov = "Asymptotic")
cen <- stress_census(spec, stress_loo(spec, by = "RACE"), stress_loo(spec, by = "SEX"))
if (requireNamespace("ggplot2", quietly = TRUE)) {
  plot_pstrip(cen)
  plot_pstrip(cen, highlight = "Asian")
}