1

My 8 year old daughter is conducting an experiment to assess memory. She has 3 groups. Condition 1, Condition 2 and Control. Does she simply run a t-test for group 1 against Control and then another t-test for group 2 against Control, then a t-test for group 1 against group 2?

gung - Reinstate Monica
  • 132,789
  • 81
  • 357
  • 650
Barry
  • 11
  • 1

1 Answers1

2

The most basic approach is a one-way ANOVA. It will determine if any significant differences exist among Condition 1, Condition 2 and the Control. If you do find a significant difference then you can use a multiple comparison test (such as Tukey's Method) to determine which groups are different.

So, ANOVA for the general "are there differences" and Tukey for "Which are different". Looks like you want to do Tukey's test.

  • 1
    Note that Tukey's test controls the experiment-wise error rate across all 3 comparisons, & that's *not* conditional on the result of the ANOVA F-test. See ["Do we need a global test before post-hoc tests?"](http://stats.stackexchange.com/questions/9751/do-we-need-a-global-test-before-post-hoc-tests). – Scortchi - Reinstate Monica Sep 12 '14 at 14:54
  • @Scortchi thanks...you've disabused me of a notion that was told to us in school...it makes sense, since Tukey does control for such errors. I was told...erroneously, I suppose, that Tukey's test was somehow conditional on a significant F-test...but i think they were confusing Tukey's test with Scheffe's test. Thanks again. –  Sep 12 '14 at 15:23
  • You're welcome. Scheffe's test doesn't rely on a previous ANOVA F-test to control the experiment-wise error rate either. Fisher's protected LSD does rely on a previous ANOVA F-test, (but doesn't truly control the experiment-wise error rate). – Scortchi - Reinstate Monica Sep 12 '14 at 15:33
  • @Scortchi thanks for clarifying...I just took a look through some old textbooks...and lo and behold..Tukey's test is always presented as a "follow-up" test (although not strictly said that is must follow)...probably a source of a lot of the confusion. –  Sep 12 '14 at 15:50