Timeline for About logistic regression in R
Current License: CC BY-SA 3.0
3 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Apr 27, 2014 at 14:12 | comment | added | Frank Harrell | Yes Fisher's test is greatly overused in my humble opinion. But no tests should have a role in most modeling problems, and neither is AIC. AIC is best for comparing two or three pre-specified models. | |
Apr 27, 2014 at 14:03 | comment | added | Raxel | Ok I guess my translation from my mother tongue was wrong. So you think that Fisher's exact test is overused in medical statistics? Also just for short, is the AIC ranking preferable in my approach and if non is clearly favourable should I select one of those models with similar AIC according to different estimators and maybe simplicity? | |
Apr 27, 2014 at 13:12 | history | answered | Frank Harrell | CC BY-SA 3.0 |