How to Report ANOVA Results in APA Format

APA Reporting Template

Use this template to report your ANOVA results. Replace the bracketed placeholders with your values.

One-Way ANOVA

A one-way analysis of variance (ANOVA) was conducted to compare the effect of [independent variable] on [dependent variable] across [number] conditions: [list conditions]. There was a statistically significant difference between groups, F([df_between], [df_within]) = [F-value], p = [p-value], $\eta^2$ = [eta-squared]. Post-hoc comparisons using the [Tukey HSD / Bonferroni / Games-Howell] test indicated that [group 1] (M = [mean], SD = [SD]) was significantly different from [group 2] (M = [mean], SD = [SD]), p = [p-value]. However, [group 3] (M = [mean], SD = [SD]) did not significantly differ from [group 1] or [group 2].

One-Way ANOVA (Welch's Correction)

Because Levene's test indicated unequal variances, F([df1], [df2]) = [F-value], p = [p-value], a Welch ANOVA was conducted. Results showed a significant effect of [independent variable] on [dependent variable], F([df_between], [df_within]) = [F-value], p = [p-value], $\eta^2$ = [eta-squared]. Games-Howell post-hoc comparisons revealed that [describe pairwise differences].

Worked Example

Scenario: A researcher compared test anxiety scores across three therapy conditions: cognitive-behavioral therapy ($n = 30$), mindfulness-based therapy ($n = 28$), and a waitlist control ($n = 32$).

Results:

• CBT group: $M = 24.3, SD = 6.1$
• Mindfulness group: $M = 27.8, SD = 5.9$
• Waitlist control: $M = 34.5, SD = 7.2$
• $F(2, 87) = 18.46, p < .001, \eta^2 = .30$

APA Write-Up:

A one-way ANOVA was conducted to compare test anxiety scores across three therapy conditions (CBT, mindfulness, and waitlist control). There was a statistically significant difference between groups, F(2, 87) = 18.46, p < .001, $\eta^2$ = .30, indicating a large effect. Tukey HSD post-hoc comparisons revealed that the waitlist control group (M = 34.5, SD = 7.2) reported significantly higher anxiety than both the CBT group (M = 24.3, SD = 6.1), p < .001, and the mindfulness group (M = 27.8, SD = 5.9), p = .002. The CBT and mindfulness groups did not significantly differ from each other, p = .121.

Reporting Checklist

• [ ] Named the type of ANOVA (one-way, factorial, repeated measures)
• [ ] Stated the independent and dependent variables
• [ ] Reported F with both degrees of freedom: F(df_between, df_within)
• [ ] Reported the exact p-value (or p < .001)
• [ ] Included an effect size ($\eta^2$ or partial $\eta^2$)
• [ ] Interpreted the effect size (small = .01, medium = .06, large = .14)
• [ ] Reported post-hoc test results with pairwise p-values
• [ ] Named the post-hoc test used (Tukey HSD, Bonferroni, Games-Howell)
• [ ] Reported group means and standard deviations
• [ ] Mentioned assumption checks if relevant (Levene's test, normality)
• [ ] Used italics for statistical symbols (F, p, M, SD)

Common Mistakes

1. Omitting degrees of freedom — Always report both df_between and df_within. Write F(2, 87), not just F = 18.46.
2. Skipping post-hoc comparisons — A significant omnibus F only tells you that at least one group differs. You must report which groups differ from which.
3. Using the wrong post-hoc test — Use Tukey HSD for equal variances and equal group sizes, Bonferroni for a small number of planned comparisons, and Games-Howell when variances are unequal.
4. Reporting $\eta^2$ as partial $\eta^2$ — These are different statistics. In one-way ANOVA they are identical, but in factorial designs they differ. Label them correctly.
5. Writing "p = .000" — Write p < .001 instead.
6. Forgetting effect size — APA 7th edition requires an effect size measure. Always report $\eta^2$ or partial $\eta^2$.

Non-Significant Results

If your ANOVA is not significant, still report all the same information:

A one-way ANOVA revealed no statistically significant difference in test anxiety scores across the three therapy conditions (CBT, mindfulness, and waitlist control), F(2, 87) = 1.24, p = .294, $\eta^2$ = .03. Descriptive statistics indicated that mean anxiety scores were similar for the CBT group (M = 31.2, SD = 6.8), mindfulness group (M = 30.5, SD = 7.1), and waitlist control (M = 33.0, SD = 6.4).

Do not run post-hoc tests when the omnibus F is not significant.

Results Table Format

For reporting group descriptive statistics and ANOVA results:

For post-hoc pairwise comparisons: