1

I have data from three different groups (n=67, 28, 25). Can I use ANOVA to compare them or is the first group size too large relative to the size of the other two groups? I have seen lots of texts that say the groups need to be of equal size but I have seen some suggestions that if the groups size are within a 1:3 ratio (smallest group size to largest group size) ANOVA can be applied.

David
  • 11
  • 1
  • Which texts?? The issues relating to a comparison of means is covered [here](http://stats.stackexchange.com/questions/31326/how-should-one-interpret-the-comparison-of-means-from-different-sample-sizes/31330#31330) -- it makes no difference whether it's a two-group or a three group problem. – Glen_b Feb 03 '15 at 21:21
  • Can you give any references for the two things you've seen in your final sentence? What precisely do they say? – Glen_b Feb 03 '15 at 21:27

0 Answers0