View source: R/ppv_range_plots.R
| plot_error_rate_conf | R Documentation |
Creates a ggplot visualization showing the mistaken identification rate (from target-absent lineups) across confidence levels.
plot_error_rate_conf(ppv_range_obj, show_points = TRUE)
ppv_range_obj |
A lineup_ppv_range object from ppv_range_by_confidence(), or a dataframe with columns: confidence, error_rate |
show_points |
Logical. Whether to show points at each confidence level (default = TRUE) |
The error rate is computed from target-absent (culprit-absent) lineups as: (suspect IDs + filler IDs) / target-absent trials in that confidence bin
The denominator is the number of target-absent trials within the bin, so the value is the share of responses at that confidence that were identifications. It is not a calibration measure and need not fall as confidence rises: when rejections occur mainly at low confidence, the rate is near 1 in the higher bins.
A ggplot2 object
data(lineup_example)
ppv_range <- ppv_range_by_confidence(lineup_example,
confidence_bins = c(0, 60, 80, 100))
plot_error_rate_conf(ppv_range)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.