Re: Compares scores amongst groups - Basic Question

Hi Shawn,

If you want to see if there is variation between these 15 groups
overall, ANOVA does apply.

If you don't know the variation within these particular groups, do you
at least know the standard deviation of the test in general--e.g., in
the population or for some other sample? Is it a standard test? Also,
do you know the N's of each group?

A correlation *might* apply if, for example, there are two types of
groups and you want to know if there's a difference between these two
types. But then you'd be better off using ANOVA. In this case you
could do ANOVA without knowing variation within groups.

--
John Uebersax PhD

.