Timeline for Correction of p-values for multiple regression models with multiple comparisons
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 17, 2018 at 7:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Sep 12, 2018 at 18:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Aug 10, 2018 at 2:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jul 10, 2018 at 5:46 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jan 5, 2018 at 18:16 | answer | added | mzunhammer | timeline score: 1 | |
| Jan 5, 2018 at 17:58 | comment | added | Michael R. Chernick | The issue is what are the hypotheses that you want to test simultaneously. The n you need would be the number of hypotheses. The p-value you are looking for is the probability of simultaneously rejecting all null hypotheses when the null hypotheses are true. Bonferroni is only one of several ways to approximate this p-value. In fact Bonferroni is very conservative in that it underestimates this p-value and is some cases by a large margin. You also could look at bootstrap and permutation methods (resampling approaches) as well as a method due to Tukey. | |
| Jan 5, 2018 at 16:27 | review | First posts | |||
| Jan 5, 2018 at 17:58 | |||||
| Jan 5, 2018 at 16:24 | history | asked | 2gs | CC BY-SA 3.0 |