Unit 13 · Dissertation toolkit

How to report ANOVA and regression in APA style

APA 7 examples for reporting two-way ANOVA and multiple regression results from SPSS, with a results-section checklist.

Free tutorialPro practiceAbout 5 minutes6 practice questions

Quick answer: How do you report ANOVA and regression in APA style?

  1. Start with descriptives and assumption checks.
  2. Report the main test with its statistic, df, exact p and effect size.
  3. Report follow-up tests and explain the pattern in words.

Report it in APA style: A 2 × 2 ANOVA showed a significant interaction, F(1, 76) = 5.00, p = .028, ηp² = .06.

Last updated November 2026 · Not sure this is the right test? Try the Which statistical test? tool.

Writing a results section

A results section reports what you found, in a logical order, with the statistics that support each claim. It doesn’t interpret or explain why (that goes in the discussion).

When to use it

  • Dissertations, lab reports and journal articles.

How it works

Start with descriptive statistics and any data screening (missing data, outliers, assumption checks and decisions). Then report each hypothesis test in turn: what you tested, the result in words, then the statistics. For ANOVA, give F with both dfs, p and an effect size; report interactions before main effects and explain the pattern. For regression, give the overall model (F, df, p, R²) then each predictor (b or β, p). Use tables when there are many numbers, and don’t repeat them all in the text.

Worked example

A 2 × 2 between-subjects ANOVA showed a significant caffeine × sleep interaction, F(1, 76) = 5.00, p = .028, ηp² = .06. Sleep deprivation slowed reaction times by 60 ms without caffeine but by only 30 ms with caffeine.

Key terms

Effect size
How big an effect is; required by APA 7.
Simple effects
Follow-up tests used to explain an interaction.

Common mistakes

  • Interpreting results in the results section.
  • Reporting only significant findings.
  • Pasting raw SPSS output.

How to do it in SPSS

Reporting a two-way ANOVA

Report the interaction first, then explain it with means. Each effect gets its own F, df, p and effect size.

Results.docx – Word

A 2 (caffeine) × 2 (sleep) between-subjects ANOVA1 showed a significant interaction, F(1, 76) = 5.00, p = .028, ηp2 = .062. Sleep deprivation slowed reaction times by 60 ms without caffeine but by only 30 ms with caffeine3. There were also main effects of sleep, F(1, 76) = 45.00, p < .001, ηp2 = .37, and caffeine, F(1, 76) = 13.89, p < .001, ηp2 = .164.

  1. 1
    Name the designNumber of levels of each factor, and whether factors are between- or within-subjects.
  2. 2
    Full statisticsF with both df, exact p and partial eta squared. Greek letters such as η aren’t italicised.
  3. 3
    Explain the patternSay what the interaction means in plain words, with numbers from the descriptives or simple effects.
  4. 4
    Main effectsReport them after the interaction, and be careful interpreting them when the interaction is significant.

Reporting a multiple regression

State the overall model first, then each predictor. A table of coefficients is usually clearer than listing every number in the text.

Results.docx – Word

A multiple regression showed that revision hours, attendance and anxiety together predicted exam scores, F(3, 116) = 18.12, p < .0011, explaining 32% of the variance (R2 = .32, adjusted R2 = .30)2. Revision hours (β = .41, p < .001) and anxiety (β = −.34, p < .001) were significant predictors3, but attendance was not (β = .09, p = .253)4.

  1. 1
    Overall modelThe ANOVA table’s F with regression and residual df.
  2. 2
    Variance explainedR² as a percentage in words, plus adjusted R².
  3. 3
    Each predictorβ (standardized) or b (unstandardized) with p. Say which you’re using and be consistent.
  4. 4
    Non-significant predictorsReport them too. Leaving them out hides part of your result.

The SPSS syntax

Prefer typing to clicking? Open File › New › Syntax, paste this in, select it and choose Run › Selection. Every dialog's Paste button writes the same kind of code.

* Two-way ANOVA (caffeine.sav).
UNIANOVA rt BY caffeine sleep
  /METHOD=SSTYPE(3)
  /PRINT=ETASQ DESCRIPTIVE
  /DESIGN=caffeine sleep caffeine*sleep.

* Multiple regression (exam_multi.sav).
REGRESSION
  /STATISTICS COEFF OUTS R ANOVA
  /DEPENDENT score
  /METHOD=ENTER hours attendance anxiety.

Practice data

Download the file used in this lesson and run it yourself in SPSS. Your results will closely match the screens above, though a few numbers may differ slightly.

  • caffeine.savReaction times by caffeine and sleep condition (N = 80)
  • exam_multi.savRevision hours, attendance, anxiety and exam score (N = 120)

Now practise it interactively →

Reading is only half of it. Tap through the real SPSS menus, read the output and pick the right write-up in 6 quick questions, with instant feedback on every answer.

Practice for this lesson is part of Pro, with every unit, unlimited hearts and saved progress.

More in Dissertation toolkit