Timeline for How robust is the independent samples t-test when the distributions of the samples are non-normal?
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 6, 2015 at 16:30 | comment | added | Silverfish | (+1) I think it might have been worth including the case where one sample was drawn from a skewed population and the other wasn't, as this was what the OP thought might be happening to their data. But it is nice to see an answer with explicit code. (A slight generalisation would actually allow a reader to investigate how well robust methods compare to the traditional t-test, which is a useful pedagogical exercise if you're trying to teach someone the dangers of applying a test whose assumptions have been violated...) | |
| Jan 6, 2015 at 14:11 | history | edited | amoeba | CC BY-SA 3.0 |
prettified (syntax-highlighted) the code block
|
| Jan 6, 2015 at 13:27 | comment | added | Frank Harrell | Since we have an array of robust semi-parametric methods nowadays why is this discussion so worthwhile? | |
| Jan 6, 2015 at 13:21 | history | answered | Wolfgang | CC BY-SA 3.0 |