The false-negative rate (FNR) measures the proportion of actual positive instances that a classifier incorrectly labels negative. It is calculated as FN / (FN + TP) × 100 and is the inverse of the true positive rate. section 5.2.4
Use the rate to:
- Quantify how often a model misses actual positives. section 5.2.4
- Compare missed-positive errors with false-positive errors when their consequences differ. section 5.2.4
- Evaluate logistic-regression classification alongside accuracy, true-positive rate, and other performance measures. section 5.3
Raisin classification
The classifier produced 66 false negatives and 384 true positives, so FNR = 66 / (66 + 384) × 100 = 14.67%. Thus, it missed about 15% of actual positive instances. section 5.2.4
Table 5.1 Confusion matrix for raisin classification. A confusion matrix stores classification metrics from a regression with actual and predicted binary outcomes.
|
Predicted
|
|||
|---|---|---|---|
|
Kecimen (0)
|
Besni (1)
|
||
|
Actual
|
Kecimen (0)
|
tn
|
fp
|
|
Besni (1)
|
fn
|
tp
|
|
Read false negatives and true positives from the actual-versus-predicted confusion matrix before calculating the rate. section 5.2.4
