ANOVA Posthoc: Any way I can do posthoc with groups of less than 2 people?

[morepil]

Hi.

As the title says,
I'm trying to run a post-hoc (I am accustomed to using Tukey, I don't know why) for a one-way-ANOVA, but I have about 10 groups and I think 2 of the groups has 1 people, and 2 groups have 2 people in it, each.
So SPSS doesn't let me do it.
It says: "... because at least one group has fewer than two cases"?

Any ways I can do a post hoc with groups with less than 2 people?

 

[Karabiner]

You do not have variance within n=1 groups.

With kind regards

Karabiner

 

[morepil]

yeah but what about the other groups? There's about 10 groups and only 2 of them are non-calculable. The variance between the other groups, no way to get it?

 

[Karabiner]

So why don't you leave the n=1 groups compeletely out of the analysis?

With kind regards

Karabiner

 

[morepil]

Yeah that's what I thought of doing but wanted to make sure that it's the proper way to go...

Thanks a lot!