Timeline for Should a contingency table be "symmetric"?
Current License: CC BY-SA 4.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 25, 2022 at 15:10 | comment | added | kjetil b halvorsen♦ | See somewhat similar stats.stackexchange.com/questions/428059/…, and this stored google search | |
| Oct 25, 2022 at 13:36 | comment | added | craszer | ok, thanks! would just applying fishers exact to a half empty table work from your point of view? | |
| Oct 25, 2022 at 13:31 | comment | added | kjetil b halvorsen♦ | That means you have a special kind of contingency table, needing special models, not the usual chisq test. Put all counts above the diagonal, and let the lower part be undefined. But you also has some counts on the diagonal, what does those mean? | |
| Oct 25, 2022 at 13:19 | comment | added | craszer | to be honest, if a conflict ends up above or below the diagonal is not clear to me. It happens somewhere in the code and I never questioned it because it didnt seem important. I think it is random. | |
| Oct 25, 2022 at 12:59 | comment | added | kjetil b halvorsen♦ | OK, but then how do you decide where (below/above) diagonal to put a certain conflict? That seems to be unimportant ... | |
| Oct 25, 2022 at 12:55 | comment | added | craszer | done. who initiated a conflict is not important to me, even if rows and columns could be read like that. im just interested in the sum. | |
| Oct 25, 2022 at 12:54 | history | edited | craszer | CC BY-SA 4.0 |
added 358 characters in body
|
| Oct 25, 2022 at 12:36 | comment | added | kjetil b halvorsen♦ | What distinguishes then row/cols? The cluster initiating a conflict, if that makes sense? Please add all new information as an edit to the post! | |
| Oct 25, 2022 at 12:31 | comment | added | craszer | The rows and column represent clusters of countries. The numbers in the cells represent conflicts that took place between countries in the clusters (actually, the level of analysis is the cluster). | |
| Oct 25, 2022 at 12:07 | comment | added | kjetil b halvorsen♦ | You need to tell us what the row/col categories represent. But no, there is no requirement that the table should be symmetric. What usually is required, is that in the table each event should be counted exactly once. | |
| Oct 25, 2022 at 12:05 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| S Oct 25, 2022 at 9:45 | review | First questions | |||
| Oct 25, 2022 at 10:18 | |||||
| S Oct 25, 2022 at 9:45 | history | asked | craszer | CC BY-SA 4.0 |