Bias and calibration of each rater — sad

Combines fixed and random effects of a sad_fit() model into the bias of each rater at the centring severity and the slope of the rater's estimates on actual severity (1 = perfect calibration), per condition.

Usage

sad_raters(fit)

plot_sad_raters(x, ...)

Arguments

fit: An object returned by sad_fit() with family = "gaussian".
x: An object returned by sad_raters().
...: Not used.

Value

sad_raters() returns a tibble with rater, condition, method, bias_at_center (percentage points) and slope. plot_sad_raters() returns a ggplot object, with lines linking the same rater across conditions.

Examples

# \donttest{
if (requireNamespace("glmmTMB", quietly = TRUE)) {
  x <- sad_data(SADRustSoybean, wide = c(UN = "unaided", SAD = "aided"), group = "sad")
  rt <- sad_raters(sad_fit(x))
  plot_sad_raters(rt)
}
#> Structure 'full' did not converge; trying the next one.
#> Structure 'noim' did not converge; trying the next one.

# }