Statistics
What is a false negative?
An example in which the model mistakenly predicted the negative class.
Card 1 of 259. Answer: An example in which the model mistakenly predicted the negative class.
An example in which the model mistakenly predicted the negative class.
Card 1 of 259. Answer: An example in which the model mistakenly predicted the negative class.
About · Quizzes · History of AI · To suggest new questions or report an error send me a dm.
A false negative is a case whose true label is positive but which the model predicts as negative: a tumor the scan misses, or spam that reaches the inbox. It is the FN cell of the confusion matrix. In hypothesis testing the matching error, missing a real effect, is a Type II error.
Its rate is measured against the actual positives: false negative rate = FN / (TP + FN) = 1 − recall. Of 5,000 circuit boards, say 80 are faulty and the model flags 68 of them plus 20 good ones. The 12 faulty boards that ship give a false negative rate of 15%, yet accuracy is 99.4% because good boards dominate.
When a miss is expensive, as in cancer screening or safety defects, you lower the decision threshold and accept more false alarms. With calibrated probabilities, predict positive when p > C_FP / (C_FP + C_FN): if a miss costs 9 times a false alarm, the threshold drops from 0.5 to 0.1.