Timeline for Transforming Negatively Skewed Independent Groups
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 1, 2015 at 20:54 | comment | added | cxds | Ok, great, I will give that a go. Thank you so much for all your help | |
| Mar 1, 2015 at 15:18 | comment | added | Nick Cox | Your results are less worrying to me than they appear to be to you. For example, one extreme skewness appears to be for some binary variable, for which no transformation will improve anything at all! Neurosis about e.g. Kolmogorov-Smirnov tests like yours is uncalled for; just because normality tests are failed doesn't mean that there exists a simple universal transformation that would reverse the problem (if it is one). I'd back up t-tests with Mann-Whitney where you are asking different questions and making weaker questions and be worried most if they gave very different signals. | |
| Mar 1, 2015 at 13:27 | comment | added | cxds | I have added some of the data to the original question, including skewness measures - does that help at all? | |
| Mar 1, 2015 at 12:15 | comment | added | Nick Cox | t-tests often work quite well if data are not normally distributed: see e.g. Rupert G. Miller 1986 Beyond ANOVA New York: John Wiley. The data are "so skewed"; you haven't shown us the data, or any graphs, or even cited results for any skewness measures. | |
| Mar 1, 2015 at 11:31 | comment | added | cxds | Which I think would require the data to be normally distributed? Any suggestions about alternative analysis strategies would be much appreciated | |
| Mar 1, 2015 at 11:30 | comment | added | cxds | Initially I was planning to run t-tests on each of the measures separately comparing Uganda and the UK, then calculate a composite score and do the same, and then finally look at whether any demographic variables mediate any of the differences between variables in Ug & UK, or any of the relationships between variables. | |
| Mar 1, 2015 at 11:30 | comment | added | cxds | This is for my dissertation and I was told by my supervisor that if the data wasn't normal it would need transforming before running t-tests. It is a cross-cultural comparison of executive functions in children in Uganda and the UK. So the scores are performance on the Advanced DCCS, the Corsi Blocks Task & the Heads-Toes-Knees-Shoulders task. This is why the data are so skewed, because for a number of the sections of the tasks the children perform at ceiling, or at least within each culture all perform at a relatively similar level. There will also be data on verbal fluency and creativity. | |
| Mar 1, 2015 at 0:36 | history | answered | Nick Cox | CC BY-SA 3.0 |