4

Following on from this question on reporting eta squared, I would like to report 95% CIs for my effect size point estimates (partial eta and eta squared values).

  • What statistics do I need to know and is there a straight forward formula for calculation?
Community
  • 1
Short Elizabeth
  • 731
  • 2
  • 10
  • 12
  • Very interesting. Normally I care alot about such things, but this one i have never thought of before. – rolando2 Sep 24 '11 at 12:35
  • http://stats.stackexchange.com/questions/15958/how-to-interpret-and-report-eta-squared-partial-eta-squared-in-statistically-s is a post with a good long answer providing some alternatives to eta (it's the answer that mentions Cohen several times). It's possible that these alternatives have a straightforward confidence interval. Like rolando2, I find the question interesting, but don't know the answer. – zbicyclist Sep 25 '11 at 01:28

1 Answers1

3

As a preliminary answer:

Jeromy Anglim
  • 42,044
  • 23
  • 146
  • 250
  • I'm impressed. I've seen some of Karl Weunsch's work before, on teaching statistics, and liked that too. Thanks for pointing this out, Jeremy. – rolando2 Sep 26 '11 at 23:12