Why are the degrees of freedom from one way repeated measures ANOVA fractional?
With most analyses, the number of degrees of freedom equals a positive integer. Each analysis has a simple rule to compute the number of degrees of freedom, which is usually based on number of values or number of groups.
With one-way repeated measures ANOVA, Prism gives you the choice of assuming sphericity or not:
If you answer No, Prism will use the Geisser-Greenhouse correction, and the degrees of freedom will be smaller than they would have been and will not be integers.
Keywords: fractions, decimal places, decimal point