When variances across groups are unequal, which of the following is not an appropriate course of action?
A) Use Welch's F-ratio.
B) Use Games-Howell post hoc tests.
C) Transform the data.
D) Use Friedman's ANOVA.

Question

Quizplus · Accepted Answer

Using Friedman's ANOVA is not appropriate when variances across groups are unequal as it assumes that the data are measured on an ordinal scale and assumes homogeneity of variances across groups. The other options, including using Welch's F-ratio, Games-Howell post hoc tests, and transforming the data, can all be appropriate when variances across groups are unequal.

When Variances Across Groups Are Unequal, Which of the Following