Timeline for Bootstrapping and hypothesis testing
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 2, 2016 at 21:26 | answer | added | Ruben van Bergen | timeline score: 4 | |
| Dec 2, 2016 at 19:44 | comment | added | EdM | This Cross Validated page also addresses the inability of bootstrapping to overcome small sample sizes; its advantage is not needing to make assumptions about distributions. Permutation tests might be more useful in some circumstances. | |
| Dec 2, 2016 at 18:57 | comment | added | EdM | Could you say a bit more about specifics of your study: how many samples, numbers of experimental treatments, numbers of metabolites measured, and so on? Those details can make a difference. | |
| Dec 2, 2016 at 18:35 | answer | added | bdeonovic | timeline score: 6 | |
| Dec 2, 2016 at 18:00 | comment | added | Frank Fan | @Repmat Thanks for quick response. I added some more context from the reviewer. | |
| Dec 2, 2016 at 18:00 | history | edited | Frank Fan | CC BY-SA 3.0 |
added 773 characters in body
|
| Dec 2, 2016 at 17:56 | comment | added | Repmat | Actually there about as many variations on the bootstrap as you can possible imagine... Typically you bootstrap the t statistic, and use the distribution instead of the theoretical t distribution. I would like to add that the bootstrapping itself does not save you from small sample problems, as the reviewer appears to think. Can you provide more context? | |
| Dec 2, 2016 at 17:49 | review | First posts | |||
| Dec 2, 2016 at 18:18 | |||||
| Dec 2, 2016 at 17:48 | history | asked | Frank Fan | CC BY-SA 3.0 |