Timeline for Analysing significance in grouped variables
Current License: CC BY-SA 3.0
15 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 5, 2019 at 23:42 | comment | added | Glen_b | Interesting that Field omits the options that would for me come right at the top: - use a more suitable distributional model (so the outliers are not outliers), or - use a methodology that's quite robust to outliers. | |
| Feb 18, 2014 at 21:24 | comment | added | Jaap | Technically, you can do that. but why would you? When you have parametric data, use a parametric test. | |
| Feb 18, 2014 at 20:51 | comment | added | puredevotion |
Can I use the Robust Repeated Measures ANOVA from the WRS package also on parametric data?
|
|
| Feb 9, 2014 at 9:31 | history | edited | Jaap | CC BY-SA 3.0 |
fixed typo & added missing transformation
|
| Feb 8, 2014 at 15:50 | history | bounty ended | puredevotion | ||
| Feb 8, 2014 at 15:50 | vote | accept | puredevotion | ||
| Feb 7, 2014 at 16:28 | history | edited | Jaap | CC BY-SA 3.0 |
added some info on outliers
|
| Feb 7, 2014 at 16:22 | comment | added | Jaap | When there is a large difference between median/mean/mode, are those variables still normally distributed? Are those variables skewed? I'll update my answer with some info on dealing with outliers. | |
| Feb 7, 2014 at 13:42 | comment | added | puredevotion | no, the max I've seen is 4 in 1 var. But there tends to be a large difference between de median/mean/mode. And in this research the mode is more important than the mean of the answers | |
| Feb 7, 2014 at 13:37 | comment | added | Jaap | As the outliers occur in seperate variables with only one per variable (in the image), the mean is probably not affected to much. In a condition with 20 outliers, it depends on how they are distributed. Are they concentrated in specific variables? If so, are these varables still normally distributed? | |
| Feb 7, 2014 at 13:01 | comment | added | puredevotion | in general not, 0-2 per condition (thus 13 vars). Some conditions have up to 20. In the image above, there are 3 outliers (little dots in the 3rd condition) | |
| Feb 7, 2014 at 12:41 | comment | added | Jaap | Do you have many outliers? | |
| Feb 7, 2014 at 12:40 | comment | added | Jaap | For a normal ANOVA, 20 participants is not enough. For a repeated measures ANOVA with three repeated measures, 20 participant is acceptable (actually you have 20*3=60 observations). However, working with e.g. 30 participants will increase the reliability. | |
| Feb 7, 2014 at 10:38 | comment | added | puredevotion | Tested for normality, using Wilk-Shapiro test, and all vars are Normal distributed. Can I do an ANOVA over 20 observation? Isn't that too little? Also, looking at the broad sistribution, is the mean too much pushed around due to outliers at 20 observations? | |
| Feb 7, 2014 at 9:59 | history | answered | Jaap | CC BY-SA 3.0 |