Confusion (Error) Matrix Calculator

Inputs

Counts · non-negative integers

Pred. Positive

Pred. Negative

Actual
Positive

True Positive

False Negative

Actual
Negative

False Positive

True Negative

Shaded cells show correct predictions (lighter green) vs errors (lighter red). This coding refers to prediction correctness only.

F-β weight

Quick examples

Results

Total samples: —

Accuracy ACC

—

(TP + TN) / N

Matthews CC MCC

—

(TP·TN − FP·FN) /
√((TP+FP)(TP+FN)(TN+FP)(TN+FN))

F-β score F1

—

(1+β²)·P·R / (β²·P + R)

Predictive values

+ marks metrics about the positive class (what you're testing for). − marks metrics about the negative class. Neither is "good" or "bad" — positive often means the outcome of concern (e.g. injury present).

+Precision PPV

—

TP / (TP + FP)

−Neg. Pred. Value NPV

—

TN / (TN + FN)

+False Disc. Rate FDR

—

FP / (FP + TP) = 1 − PPV

−False Omission FOR

—

FN / (FN + TN) = 1 − NPV

True / false rates

+Sensitivity TPR · Recall

—

TP / (TP + FN)

−Specificity TNR

—

TN / (TN + FP)

−False Pos. Rate FPR

—

FP / (TN + FP) = 1 − TNR

+False Neg. Rate FNR

—

FN / (TP + FN) = 1 − TPR

Class distribution & error

+Positive prevalence

—

(TP + FN) / N

−Negative prevalence

—

(TN + FP) / N

Balanced Accuracy

—

(TPR + TNR) / 2

Error rate

—

(FP + FN) / N = 1 − ACC

Return to trauma.ai