Timeline for Asymptotic properties of ANOVA when the number of groups goes to infinity
Current License: CC BY-SA 4.0
6 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Aug 15, 2020 at 8:04 | vote | accept | 香结丁 | ||
Aug 6, 2020 at 17:51 | answer | added | Mickybo Yakari | timeline score: 1 | |
Aug 4, 2020 at 9:32 | answer | added | Gilles Mordant | timeline score: 1 | |
Aug 3, 2020 at 10:13 | comment | added | 香结丁 | @GillesMordant Thank you so much! But I am still a little confused. Since $J \rightarrow \infty$, the number of parameters that need to be examined also goes to infinity, some extra assumptions may need to clarify. I will extremely appreciate you if you can provide me some articles or notes that involve this question! | |
Aug 3, 2020 at 9:51 | comment | added | Gilles Mordant | The solution will depend on your assumptions on how the triangular array of $N_j$ behaves. If you keep the classical ANOVA assumptions (that is homoscedasticity and normality of errors), the calculations remain the same as in the classical case excepted that the first sum is indexed by J and J goes to infinity. | |
Aug 2, 2020 at 11:02 | history | asked | 香结丁 | CC BY-SA 4.0 |