type I versus type II error
Statistical concept distinguishing false positives (type I) from false negatives (type II); a trade-off one can tune in a filtering system.
As defined in Conversations with Tyler 2023 Retrospective
Where it comes up · 1
Most important claims · 1 of 1Search all claims for “type I versus type II error” →
- An AI reading filter that's roughly 87 percent accurate is almost certainly a help rather than a hindrance, because one can always set the trade-off between type I and type II error—if it leaves in too much, the reader would have faced that content anyway, so there is no realistic scenario where it isn't a net help.Conversations with Tyler 2023 Retrospective