stats-problem with doing mulitple t-tests for mulitple comparisons of data...
as opposed to using one-way anova?
please correct me if i'm wrong, but isn't the major problem with performing multiple 2-sample t-test for say 3 sets of data that the type I error is much larger than anticipated...?
please correct me if i'm wrong, but isn't the major problem with performing multiple 2-sample t-test for say 3 sets of data that the type I error is much larger than anticipated...?
thanks.
With three samples you have 3 pairwise tests, the problem is that they are
not independent tests, and so even raising the thresholds for acceptance
rejection does not give you what you want without a lot of work on the
correction for the correlations.