Can we all agree to stop saying "Type I" and "Type II" errors and just say "false positives" and "false negatives"?
-
-
Freq.statistics ITSELF is confusing 'cause it assesses P(D|H). Usually, what we want to know is P(H|D).
-
Specifically,Type I errors are conditional on H0=true. But you can't learn P(H0) from freq.stat. So TypeI error is a guess
- Još 2 druga odgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.