How to Report ANOVA Results in APA Style (7th Edition)

You have run your ANOVA in SPSS, the output is full of numbers, and now you have to turn it into a sentence your supervisor will accept. This guide shows you exactly how to report ANOVA results in APA style (7th edition): which numbers to take from the SPSS output, how to format them, and what a complete results paragraph looks like. The good news is that APA reporting follows one repeatable pattern — learn the template once, and you can report any ANOVA in a few sentences.

Table of Contents

What APA 7th edition requires for ANOVA reporting

Every ANOVA report needs the same core ingredients:

The test statistic: the F value, written in italics.
Degrees of freedom: two numbers in parentheses — the between-groups (effect) degrees of freedom first, then the within-groups (error) degrees of freedom.
The p-value: written as p = .032, or p < .001 when SPSS prints .000.
An effect size: usually eta-squared (η²) or partial eta-squared (η_p²). APA 7th edition expects an effect size alongside every significance test.
Descriptive statistics: the group means and standard deviations, either in the text or in a table.
Post-hoc results: if the omnibus test is significant and you have three or more groups, report which pairs differ.

The standard template looks like this:

F(2, 87) = 6.42, p = .002, η² = .13

Read it as: an F-statistic with 2 and 87 degrees of freedom, equal to 6.42, with a p-value of .002 and an eta-squared of .13.

Step 1: Run the ANOVA in SPSS and find the numbers you need

Before you can report anything, you need the right numbers. Here is the click-by-click route for a one-way ANOVA — SPSS does not print eta-squared by default in this dialog, so many students report an ANOVA with no effect size at all.

Click Analyze > Compare Means > One-Way ANOVA.
Move your dependent variable (for example, exam score) into the Dependent List box.
Move your grouping variable (for example, study method) into the Factor box.
Click Options, tick Descriptive and Homogeneity of variance test, then click Continue.
Click Post Hoc, tick Tukey, then click Continue.
Click OK to run the analysis.

From the output, collect: each group’s mean (M), standard deviation (SD) and sample size (n) from the Descriptives table; the F value, the Sig. column (your p-value) and both degrees of freedom from the ANOVA table; and the Tukey results for each pair of groups from the Multiple Comparisons table. Also check Levene’s test: if it is significant (p < .05), the equal-variances assumption is violated — report that and consider Welch’s ANOVA instead.

For the effect size, use the General Linear Model route, which prints partial eta-squared:

Click Analyze > General Linear Model > Univariate.
Move your dependent variable into Dependent Variable and your grouping variable into Fixed Factor(s).
Click Options, tick Estimates of effect size and Descriptive statistics, then click Continue.
Click OK.

Read partial eta-squared from the Tests of Between-Subjects Effects table. For a one-way ANOVA it equals eta-squared, so report it as η².

The paste-ready SPSS syntax

The commands below run the same one-way ANOVA with descriptives, Levene’s test, Tukey post-hoc tests, and partial eta-squared. Replace score and group with your own variable names.

ONEWAY score BY group
  /STATISTICS DESCRIPTIVES HOMOGENEITY
  /MISSING ANALYSIS
  /POSTHOC=TUKEY ALPHA(0.05).

UNIANOVA score BY group
  /METHOD=SSTYPE(3)
  /PRINT=ETASQ DESCRIPTIVE HOMOGENEITY
  /POSTHOC=group(TUKEY)
  /CRITERIA=ALPHA(.05)
  /DESIGN=group.

The first command gives you the ANOVA table and Tukey comparisons; the second gives you partial eta-squared. Run both, and you have every number this guide asks for.

How to report a one-way ANOVA: a worked example

Suppose three groups of students used different study methods. Your SPSS output gives F(2, 87) = 6.42, p = .002, η² = .13. A complete APA report reads:

A one-way ANOVA was conducted to compare exam scores across the three study methods. There was a statistically significant difference between groups, F(2, 87) = 6.42, p = .002, η² = .13. Students who used spaced practice scored highest (M = 78.4, SD = 9.2), followed by students who used self-testing (M = 72.6, SD = 10.1) and students who re-read their notes (M = 68.9, SD = 8.7). Tukey post-hoc tests showed that spaced practice scored significantly higher than re-reading (p = .001), while self-testing did not differ significantly from either of the other groups (both p > .05).

That paragraph names the test, gives the full statistic, reports the p-value and effect size, gives the group means and standard deviations, and reports the post-hoc comparisons — everything a reader needs to reconstruct the result.

If the result is not significant, report it the same way — a non-significant result is still a result:

There was no statistically significant difference between groups, F(2, 87) = 1.18, p = .312, η² = .03.

Do not report post-hoc tests after a non-significant ANOVA.

How to report post-hoc tests

Report the test you used, the pairs that differ, and the p-value for each comparison:

Tukey HSD post-hoc tests revealed that Group A scored significantly higher than Group C (p = .004), but Group A did not differ significantly from Group B (p = .214), and Groups B and C did not differ significantly (p = .089).

Always name the post-hoc test (Tukey, Bonferroni, Games-Howell) — different tests can give different answers. Report exact p-values for the comparisons that matter, not just “significant” or “not significant”.

How to report a two-way ANOVA

A two-way ANOVA has three results: two main effects and one interaction. Report all three, even the non-significant ones, and interpret the interaction first — a significant interaction changes what the main effects mean.

A two-way ANOVA was conducted to examine the effects of study method and gender on exam scores. There was a significant main effect of study method, F(2, 84) = 5.91, p = .004, η_p² = .12. The main effect of gender was not significant, F(1, 84) = 0.87, p = .354, η_p² = .01. The interaction between study method and gender was not significant, F(2, 84) = 1.42, p = .247, η_p² = .03.

For factorial ANOVA, report partial eta-squared (η_p²), which is what SPSS prints. If the interaction is significant, follow it with simple-effects analyses or an interaction plot, and describe the pattern in words.

How to report a repeated-measures ANOVA

Repeated-measures ANOVA adds one extra duty: sphericity. Check Mauchly’s test in the SPSS output. If it is significant, sphericity is violated and you must report the Greenhouse-Geisser corrected degrees of freedom:

Mauchly’s test indicated that the assumption of sphericity had been violated, χ²(2) = 9.84, p = .007; therefore, Greenhouse-Geisser corrected values are reported (ε = .78). There was a significant effect of time on anxiety scores, F(1.56, 46.80) = 8.23, p = .002, η_p² = .22.

Note the decimal degrees of freedom — the tell-tale sign of a Greenhouse-Geisser correction. If Mauchly’s test is not significant, report sphericity as assumed and use the uncorrected degrees of freedom, but still mention that you checked.

How to report an ANCOVA

ANCOVA follows the same pattern, with one addition: report the covariate and whether it was significant, and report adjusted means rather than raw means.

A one-way ANCOVA was conducted to compare post-test scores across the three teaching methods, controlling for pre-test scores. The covariate, pre-test score, was significantly related to post-test score, F(1, 86) = 24.51, p < .001, η_p² = .22. After controlling for pre-test scores, there was a significant difference between teaching methods, F(2, 86) = 4.76, p = .011, η_p² = .10. Adjusted means were highest for the workshop group (M_adj = 81.2), followed by the lecture group (M_adj = 76.5) and the self-study group (M_adj = 73.8).

Reporting in APA style (7th ed.): formatting rules

APA 7th edition has strict formatting rules, and getting them wrong is the easiest way to lose marks on an otherwise correct analysis.

Italics: F, p, M, SD and Greek letters used as statistics (η²) are italicised; the numbers themselves are not.
Spaces: put a space on both sides of the equals sign: F(2, 87) = 6.42, not F(2,87)=6.42.
Decimal places: report F-values and effect sizes to two decimal places; report p-values to two or three decimal places.
Leading zeros: statistics that cannot exceed 1 (p-values, correlations, eta-squared) have no zero before the decimal point: p = .002, η² = .13.
p = .000 does not exist: SPSS prints .000 when the p-value rounds to zero. Always write p < .001 instead.
Exact p-values: report the exact value SPSS gives you (p = .032) rather than p < .05, unless the value is below .001.

Reporting ANOVA results in an APA table

For a thesis, put the full ANOVA results in a table and keep the text for interpretation. An APA 7th edition ANOVA table has no vertical lines and only three horizontal lines, with columns for Source, SS, df, MS, F, p and η². In the text, write only: “As shown in Table 1, there was a significant difference between groups…” — never repeat the table’s numbers in the paragraph.

Common mistakes when reporting ANOVA results

Reporting F without degrees of freedom. “F = 6.42, p = .002″ is incomplete — without the degrees of freedom, the F-value is meaningless.
Forgetting the effect size. A significant p-value with 500 participants can reflect a trivial effect. Always report η² or η_p².
Writing p = .000. A p-value is never exactly zero; write p < .001.
Reporting post-hoc tests after a non-significant ANOVA. If the omnibus test is not significant, stop there.
Reporting only the significant results. Non-significant main effects and interactions belong in the results section too.

Key Takeaways

Every ANOVA report needs five things: the F-value, both degrees of freedom, the p-value, an effect size, and the group means and standard deviations.
Use the template F(df1, df2) = x.xx, p = .xxx, η² = .xx — and never write p = .000; it is always p < .001.
Switch on effect sizes in SPSS before you run the analysis: use Analyze > General Linear Model > Univariate and tick Estimates of effect size.
Report post-hoc tests only when the omnibus ANOVA is significant, and always name the test you used.
For two-way ANOVA, report both main effects and the interaction; for repeated measures, report Mauchly’s test and use Greenhouse-Geisser corrections when sphericity is violated.

Frequently asked questions

How do I report ANOVA results in APA format?

Report the F-statistic in italics with both degrees of freedom in parentheses, the exact p-value, and an effect size: F(2, 87) = 6.42, p = .002, η² = .13. Add the group means and standard deviations, and the post-hoc results if the ANOVA is significant.

What does F(2, 87) mean in APA reporting?

The first number in parentheses (2) is the between-groups degrees of freedom — the number of groups minus one. The second number (87) is the within-groups (error) degrees of freedom — the total sample size minus the number of groups.

Do I report eta-squared or partial eta-squared?

For a one-way ANOVA, they are identical, so report η². For factorial ANOVA, repeated-measures ANOVA and ANCOVA, SPSS prints partial eta-squared, so report η_p².

What p-value do I write when SPSS shows .000?

Write p < .001. SPSS rounds very small p-values to .000, but a p-value is never exactly zero, and APA style requires the “less than .001” format.

Need this done on your data? Get a free quote → /services/