In stats classes I teach, I express similar sentiments (using @drob's older tweets!) & tell my students that I will only use FP/FN going forward & that if they read Type I/II elsewhr, they can think of the mistakes the villagers made the 1st & 2nd time when the boy cried wolf!
-
-
-
Here are those tweets:https://twitter.com/drob/status/781491432720834560?s=19 …
- Još 1 odgovor
Novi razgovor -
-
-
I like that "Type 1 error" and "Type 2 error" are both 4 syllables, just like "false negative" and "false positive". So they aren't briefer than the thing they describe (at least out loud, and even by char count it's not a huge win).
-
I have issues with "false positive" and "false negative" too. Then again perhaps it is deliberate irony that the terminology for errors is a source of error.
- Još 3 druga odgovora
Novi razgovor -
-
-
Type V errors are correctly calling all tests, but shifted by one sample to the left.
-
I thought Type V was when you sort the data before running your analysis:https://stats.stackexchange.com/questions/185507/what-happens-if-the-explanatory-and-response-variables-are-sorted-independently …
Kraj razgovora
Novi razgovor -
-
-
Good ol' A-theory and B-theory of time. And Kahneman's System 1 and System 2.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
It took me way too long to get this. But now that I do this tweet is great. I am tired.
-
Yep, I got it on the second time it popped up in my feed...
Kraj razgovora
Novi razgovor -
-
-
I have always found terms used in Signal theory easier to understand- hit, miss, false alarm, true rejection
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
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.
