Question about correlations?

Question

I have a data set of 150 with three different groups. The group sizes are 128, 12, and 9 (one unknown).

Anyway, I ran a correlation analysis for each group and a large number of the correlations are not significant for the smaller groups.

Is this more likely due to group size or could it be a "real" group characteristic? I seem to remember that the larger the group size, the more likely you are to see a significant relationship...

Answer 1

This is very likely due to the small group sizes.  It is more difficult to prove signifigance for a small group.  As the sample size gets larger, you can discern smaller signifigant effects.