The main input are 2 logical vectors of prediction and criterion values.
classtable(
prediction_v = NULL,
criterion_v = NULL,
sens.w = NULL,
cost.v = NULL,
correction = 0.25,
cost.outcomes = list(hi = 0, fa = 1, mi = 1, cr = 0),
na_prediction_action = "ignore"
)logical. A logical vector of predictions.
logical. A logical vector of (TRUE) criterion values.
numeric. Sensitivity weight parameter (from 0 to 1, for computing wacc).
Default: sens.w = NULL (to enforce that actual value is being passed by the calling function).
list. An optional list of additional costs to be added to each case.
numeric. Correction added to all counts for calculating dprime.
list. A list of length 4 with names 'hi', 'fa', 'mi', and 'cr' specifying
the costs of a hit, false alarm, miss, and correct rejection, respectively.
For instance, cost.outcomes = listc("hi" = 0, "fa" = 10, "mi" = 20, "cr" = 0) means that
a false alarm and miss cost 10 and 20, respectively, while correct decisions have no cost.
What happens when no prediction is possible? (experimental).
The primary confusion matrix is computed by confusionMatrix of the caret package.