Timeline for Confusion about Anderson-Darling test
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 28, 2019 at 0:01 | history | tweeted | twitter.com/StackStats/status/1177734927858765825 | ||
| Sep 27, 2019 at 19:58 | answer | added | Josh | timeline score: 1 | |
| Sep 27, 2019 at 19:53 | comment | added | Josh | You should get a new p-value every time under the null. The p-values should be uniformly distributed under the null. | |
| Sep 27, 2019 at 18:50 | history | edited | user14717 | CC BY-SA 4.0 |
deleted 1 character in body
|
| Sep 27, 2019 at 17:33 | history | edited | user14717 | CC BY-SA 4.0 |
added 614 characters in body
|
| Sep 27, 2019 at 17:01 | comment | added | Josh | This argument seems to assume independence among the terms in sum. F_n(x_i) and F_n(X_j) are dependent. Also the simulation you provided was over a the null hypothesis. It will in that case, converge to a distribution with quantiles 0.576 (85%) 0.656 (90%) 0.787 (95%) 0.918 (97.5%) 1.092 (99%) | |
| Sep 27, 2019 at 17:01 | history | edited | user14717 | CC BY-SA 4.0 |
added 237 characters in body
|
| Sep 27, 2019 at 16:45 | history | edited | user14717 | CC BY-SA 4.0 |
added 95 characters in body
|
| Sep 27, 2019 at 14:19 | history | edited | user14717 | CC BY-SA 4.0 |
added 29 characters in body
|
| Sep 27, 2019 at 12:50 | history | asked | user14717 | CC BY-SA 4.0 |