How to Report ANOVA Results in APA Format (With Examples)

You ran your ANOVA in SPSS and got a significant result. Now comes the part many students struggle with most — writing it up in proper APA format. Getting the format wrong can cost you marks, delay your thesis, or trigger revision requests from reviewers.

This guide gives you exact templates and examples for reporting every type of ANOVA result you are likely to encounter in your thesis or research paper.

The Basic APA Format for ANOVA

Every ANOVA report follows the same general structure:

1. State the test and purpose — What test was run and why
2. Report the main result — The F-statistic, degrees of freedom, p-value, and effect size
3. Describe the means — What the group means and standard deviations were
4. Report post-hoc tests — Which specific groups differed (if the overall test was significant)

The standard format for reporting the F-statistic is:

F(df between, df within) = F-value, p = p-value, η² = effect size

Reporting One-Way ANOVA

Template

A one-way analysis of variance (ANOVA) was conducted to compare the effect of [IV] on [DV] in [group 1], [group 2], and [group 3] conditions. There was a statistically significant difference between groups, F([df between], [df within]) = [F-value], p = [p-value], η² = [eta-squared].

Full Example

A one-way ANOVA was conducted to compare the effect of teaching method (lecture, discussion, and project-based) on final exam scores. There was a statistically significant difference between groups, F(2, 87) = 8.45, p < .001, η² = .16, indicating a large effect.

Post-hoc comparisons using Tukey's HSD test indicated that the mean score for the project-based group (M = 82.40, SD = 9.12) was significantly higher than both the lecture group (M = 72.30, SD = 10.45, p = .001) and the discussion group (M = 74.80, SD = 8.67, p = .012). The lecture and discussion groups did not significantly differ (p = .583).

When Results Are Not Significant

A one-way ANOVA revealed no statistically significant difference in job satisfaction between the three department groups, F(2, 117) = 1.24, p = .294, η² = .02.

When results are not significant, you do not need to report post-hoc tests. Simply report the F-statistic and p-value, optionally with effect size to show the magnitude was negligible.

Reporting Two-Way ANOVA

Two-way ANOVA has three effects to report: two main effects and one interaction. Report all three, starting with the interaction because it determines how you interpret the main effects.

Template

A two-way ANOVA was conducted to examine the effects of [IV1] and [IV2] on [DV].

There was a [significant/non-significant] interaction between [IV1] and [IV2], F([df], [df]) = [F], p = [p], η² = [value].

The main effect of [IV1] was [significant/non-significant], F([df], [df]) = [F], p = [p], η² = [value].

The main effect of [IV2] was [significant/non-significant], F([df], [df]) = [F], p = [p], η² = [value].

Full Example

A 2 × 3 between-subjects ANOVA was conducted to examine the effects of gender (male, female) and teaching method (lecture, discussion, project-based) on exam performance.

There was no significant interaction between gender and teaching method, F(2, 114) = 0.89, p = .414, η² = .02.

There was a significant main effect of teaching method, F(2, 114) = 12.34, p < .001, η² = .18. Post-hoc comparisons using Tukey's HSD test revealed that students in the project-based condition (M = 83.10, SD = 8.45) scored significantly higher than those in the lecture condition (M = 71.90, SD = 11.20, p < .001) and the discussion condition (M = 75.30, SD = 9.80, p = .004).

The main effect of gender was not significant, F(1, 114) = 2.15, p = .145, η² = .02.

When the Interaction Is Significant

If the interaction is significant, the main effects should be interpreted with caution because the effect of one variable depends on the level of the other. Report simple effects instead:

There was a significant interaction between gender and feedback type on task performance, F(1, 96) = 7.82, p = .006, η² = .08. Simple effects analysis revealed that positive feedback significantly improved performance for female participants (p = .001) but not for male participants (p = .342).

Reporting Repeated Measures ANOVA

Repeated measures ANOVA requires additional consideration for the sphericity assumption.

Template

A one-way repeated measures ANOVA was conducted to compare [DV] across [number] time points/conditions.

Mauchly's test indicated that the assumption of sphericity [was/was not] violated, χ²([df]) = [value], p = [p-value]. [If violated: Therefore, degrees of freedom were corrected using Greenhouse-Geisser estimates (ε = [value]).]

There was a statistically significant effect of [time/condition], F([df], [df]) = [F], p = [p], η² = [value].

Full Example

A one-way repeated measures ANOVA was conducted to compare patient anxiety scores at three time points: baseline, post-treatment, and 6-month follow-up.

Mauchly's test indicated that the assumption of sphericity was violated, χ²(2) = 8.42, p = .015. Therefore, degrees of freedom were corrected using Greenhouse-Geisser estimates (ε = .78).

The results showed a statistically significant effect of time on anxiety scores, F(1.56, 43.68) = 18.92, p < .001, η² = .40. Post-hoc pairwise comparisons with Bonferroni correction revealed significant reductions from baseline (M = 48.20, SD = 9.30) to post-treatment (M = 35.60, SD = 8.45, p < .001) and from baseline to follow-up (M = 37.10, SD = 7.80, p < .001). The difference between post-treatment and follow-up was not significant (p = .412).

When Sphericity Is Met

Mauchly's test indicated that the assumption of sphericity was met, χ²(2) = 3.15, p = .207.

When sphericity is met, report the uncorrected (Sphericity Assumed) values from the SPSS output.

Effect Size Reporting

Always report an effect size measure alongside the F-statistic. The most common for ANOVA is partial eta-squared (η²p), which SPSS reports when you check "Estimates of effect size" under Options.

Interpretation Guidelines

η²p Value	Interpretation
.01	Small effect
.06	Medium effect
.14	Large effect

How to Get It in SPSS

1. When setting up your ANOVA, click Options
2. Check Estimates of effect size
3. SPSS will include partial η² in the output table

Reporting Format

Use the symbol η² (or η²p for partial) followed by the value:

F(2, 87) = 8.45, p < .001, η²p = .16

Reporting Post-Hoc Tests

Tukey's HSD (Most Common)

Post-hoc comparisons using Tukey's HSD test indicated that Group A (M = 85.20, SD = 7.30) scored significantly higher than Group B (M = 74.60, SD = 9.80, p < .001) and Group C (M = 76.90, SD = 8.10, p = .002). Groups B and C did not differ significantly (p = .614).

Bonferroni Correction

Pairwise comparisons with Bonferroni correction revealed a significant difference between Time 1 and Time 2 (p = .003), but not between Time 2 and Time 3 (p = .185).

Games-Howell (When Variances Are Unequal)

Because Levene's test indicated unequal variances (p = .012), post-hoc comparisons were conducted using the Games-Howell procedure.

Creating an APA-Style Table

For a thesis, you should include a table summarizing the ANOVA results. Here is the standard format:

Table 1

Analysis of Variance for Exam Scores by Teaching Method

Source	SS	df	MS	F	p	η²p
Between groups	4280.50	2	2140.25	8.45	< .001	.16
Within groups	22035.80	87	253.28
Total	26316.30	89

Also include a descriptive statistics table:

Table 2

Descriptive Statistics for Exam Scores by Teaching Method

Group	n	M	SD
Lecture	30	72.30	10.45
Discussion	30	74.80	8.67
Project-based	30	82.40	9.12

Assumptions to Report

Mention that you checked the key assumptions, especially when writing a thesis:

Levene's Test (Homogeneity of Variances)

Levene's test indicated that the assumption of homogeneity of variances was met, F(2, 87) = 1.45, p = .240.

If violated:

Levene's test indicated unequal variances, F(2, 87) = 4.82, p = .010. Therefore, Welch's ANOVA was used, and Games-Howell post-hoc comparisons were reported.

Normality

The Shapiro-Wilk test indicated that exam scores were approximately normally distributed within each group (all ps > .05).

Common Mistakes to Avoid

1. Forgetting degrees of freedom — ANOVA requires two df values: between-groups and within-groups. Always include both
2. Not reporting effect size — APA guidelines require an effect size measure. η²p is the standard for ANOVA
3. Reporting post-hoc tests when the overall F is not significant — If the overall ANOVA is not significant, do not run or report post-hoc comparisons
4. Using the wrong post-hoc test — Tukey's HSD requires equal variances. If Levene's test is significant, use Games-Howell instead
5. Not reporting sphericity for repeated measures — Always report Mauchly's test result. If violated, use corrected df values
6. Confusing η² with η²p — SPSS reports partial eta-squared (η²p), not eta-squared (η²). Label it correctly
7. Only reporting the p-value — A complete ANOVA report includes the F-statistic, both df values, p-value, and effect size. Reporting just "p < .05" is insufficient
8. Not including descriptive statistics — Always report means and standard deviations for each group

Quick Reporting Checklist

Before submitting your results section, verify you have included:

• The type of ANOVA conducted and why
• The F-statistic with both degrees of freedom
• The exact p-value (or "< .001" for very small values)
• Effect size (η²p) with interpretation
• Means and standard deviations for each group
• Post-hoc test results (if the overall F was significant)
• Assumption checks (Levene's test, sphericity for repeated measures)
• A formatted table summarizing key results

Need help reporting your ANOVA results in APA format or running the complete analysis? Our team handles everything from assumption checking through publication-ready write-up. Get a free quote.