Timeline for When combining p-values, why not just averaging?
Current License: CC BY-SA 3.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 13, 2015 at 20:24 | history | edited | DWin | CC BY-SA 3.0 |
added 153 characters in body
|
| Jul 13, 2015 at 13:53 | comment | added | Elvis | Yes, you're right (though is hardly "unspoken") : the rejection region contains only tuples of "small' p-values. See Zaykin's paper mentioned my amoeba for some stuff about the case where the null is true in many of the tests. | |
| Jul 12, 2015 at 21:14 | comment | added | DWin | The averaging method "emphasizes" or weights the compound hypothesis that both individual hypotheses with be rejected together. That seems to be an unspoken constraint. | |
| Jul 12, 2015 at 20:45 | comment | added | Elvis | You don’t seem to notice that with the "averaging method" and two experiments with $p_1 = 0.05$ and $p_2 = 0.05$, the null hypothesis is rejected (see second drawing in my answer above). | |
| Jul 10, 2015 at 15:21 | comment | added | DWin | I saw it. Wasn't convinced. | |
| Jul 10, 2015 at 8:44 | comment | added | amoeba | This answer (first sentence) assumes that when averaging the $p$-values, the significance cutoff $alpha$ would stay the same, but is not true. Averaging can work just fine. See the answer by @Elvis. | |
| Mar 8, 2015 at 23:24 | history | edited | DWin | CC BY-SA 3.0 |
added 134 characters in body
|
| Dec 7, 2013 at 20:14 | vote | accept | Alby | ||
| Jul 9, 2015 at 23:51 | |||||
| Dec 5, 2013 at 23:43 | history | edited | DWin | CC BY-SA 3.0 |
added 311 characters in body
|
| Dec 5, 2013 at 23:34 | history | edited | DWin | CC BY-SA 3.0 |
added 311 characters in body
|
| Dec 5, 2013 at 16:40 | history | edited | DWin | CC BY-SA 3.0 |
added 1044 characters in body
|
| Dec 5, 2013 at 13:03 | comment | added | Alby | Thank you for your answer. The intuition you mentioned actually makes sense. I would consider those cases you mentioned as more significant. But is there a way to express this idea more mathematically rigorously? | |
| Dec 5, 2013 at 3:47 | history | answered | DWin | CC BY-SA 3.0 |