Which of the A–D are NOT validity conditions needed to use a theory-based F-distribution to determine a p-value? (Choose all that apply.) 

A. The sample sizes in each group must be the same. 

B. The standard deviations of each sample are approximately equal (within a factor of 2 of each other). 

C. The means of each sample are approximately equal (within a factor of 2 of each other). 

D. The sample sizes must be relatively large (at least 20 without strong skewedness), or the distribution of the sample data must be approximately symmetric.