I have the following dilemma:

**Design:**

1 (Group: Patient vs. Control_1 vs. Control_2) between-factors design arrayed as a 1-way ANOVA

**Analysis:**

Following a main effect of group perform I perform all pairwise comparisons using Tukey tests.

**Question:**

Cohen's d for paired comparisons is the mean difference divided by the pooled standard deviation. This information is not available for Tukey tests. Is there a way to compute Cohen's d or a standardized effect size from these data?

**Contents**hide

#### Best Answer

You can easily compute Cohen's $d$ using the three means and ANOVA output. The square-root of the MS-error (or MS-residual depending on which program you used) is the pooled within-groups standard deviation. Thus, simply divide each mean difference by this value.

### Similar Posts:

- Solved – Why is the Tukey confidence interval wider than the T-test confidence interval
- Solved – Why is the Tukey confidence interval wider than the T-test confidence interval
- Solved – Post Hoc test: Fisher LSD or pairwise two sample t.tests
- Solved – Cohen’s d for unequal variance
- Solved – Difference between Cohen’s d and beta coefficient in a standardized regression model with dumthe coded predictor variable