I didn't seem to find any clear information on this but on other multiple comparisons.
Hi, Jochen, will try to get the R software, cause SPSS doesn't seem to have some of the modified flexible options you mentioned. I am particularly interested in when the assumptions of equal variance and sample size are violated, yet only one control group is to be compared with test groups
Hello Jochen Wilhelm,
I have read your comments on unequal sample-sizes for Dunnett.
You said "Dunnett's test assume that there are equal numbers of trials in each group, but more flexible options are nowadays readily available in many statistics packages such as R".
Do you know which R package the old wikipedia page was refering to? It seems the page has changed its comments.
Thank you
If the sample sizes are not equal, Dunnett's test performed by Prism (up to 7.04 and 7.0d) is not quite right. If the control has a larger sample size (as it should), the multiplicity-adjusted P values from Prism were a tiny bit too low. If you don't look at the multiplicity-adjusted P value but just at the decision of whether or not a difference was statistically significant, Prism was a bit too liberal about assigning "significance".
- Badges
- Science topic
- Similar topics
- Biological Science
- Immunology
- Antibodies