Timeline for Why are Type-II errors in hypothesis testing considered to be errors?
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 4, 2017 at 19:46 | comment | added | David C. Norris | Connecting NHST with the actions that typically ensue, as Zahava Kor does here, seems the simplest and most direct way to appreciate Type II errors as 'errors'. In some contexts, such as that of drug development which Zahava Kor cites specifically, the NHST is embedded within a plan of action such that the epistemic outcome of the test determines actions. In connection with medicine generally, it helps to appreciate Braithwaite's magnificent EBM’s Six Dangerous Words JAMA. 2013;310(20):2149-2150. doi:10.1001/jama.2013.281996. | |
| Jun 30, 2017 at 14:44 | comment | added | Zahava Kor | Why do you say this? Of course we are doing what we are supposed to do when the null hypothesis is true - we are staying with the current behavior, which is the correct thing to do under your assumption that the null hypothesis is true. | |
| Jun 28, 2017 at 22:07 | comment | added | Sanket Kedia | Going by this logic, failing to reject a true null hypothesis should not be a true positive. It should be an error because we are not doing what we are supposed to do when the null hypothesis is true. | |
| Jun 28, 2017 at 16:41 | history | answered | Zahava Kor | CC BY-SA 3.0 |