Simultaneously test within-subjects and between-subjects factors on a continuous outcome.
Mixed ANOVA (also called split-plot ANOVA) combines at least one within-subjects factor (repeated measures across time or conditions) with at least one between-subjects factor (independent groups). It is among the most common designs in intervention research: participants are randomly assigned to groups (between factor) and measured at multiple time points (within factor). The critical question is whether the trajectory of change over time differs between groups — the Group × Time interaction.
StatRyx handles sphericity testing and Greenhouse-Geisser correction for the within-subjects factor, computes main effects and interactions with partial eta-squared, and produces pairwise post-hoc comparisons for significant effects — all in APA 7 format.
A mixed ANOVA combines a between-subjects factor (different people in each group) with a within-subjects factor (the same people measured repeatedly). It gives three tests: the main effect of group, the main effect of time, and the group × time interaction. In an intervention study the interaction is the result that matters — it shows whether the groups changed differently over time. Sphericity applies to the within-subjects factor, and homogeneity of variance to the groups at each time point.
| Source | F | df | p | partial η² |
|---|---|---|---|---|
| Group (between) | 12.4 | 1, 98 | < .001 | .11 |
| Time (within, GG) | 28.7 | 1.82, 178.4 | < .001 | .23 |
| Group × Time | 9.34 | 1.82, 178.4 | < .001 | .09 |
A 2 (group: treatment vs. control) × 3 (time: baseline, 3 months, 6 months) mixed ANOVA revealed a significant Group × Time interaction, F(1.82, 178.4) = 9.34, p < .001, partial η² = .09. The treatment group showed significantly greater improvement over time.
Yes. You can run it without an account (3 free analyses), and a free account adds 10 more — a one-time allowance, no payment needed. Every result includes the APA 7 write-up. Paid plans (Student from $9/month) add more analyses and Word, PDF and Excel export.
The Group × Time interaction tells you whether groups change differently over time — usually the central question in intervention research. If non-significant, interpret main effects instead.
Report the interaction first, then the main effects, each with F, df, p and partial η²: "A 2 × 3 mixed ANOVA showed a significant group × time interaction, F(1.82, 178.4) = 9.34, p < .001, partial η² = .09." Then report simple effects of time within each group.
It depends on the effect and the correlation between repeated measures. For a medium interaction effect with two groups and three time points, power analyses typically suggest around 25–30 participants per group. Higher correlations between time points reduce the number needed.
Then the groups did not change differently over time, and you interpret the main effects: the time effect shows overall change for everyone, and the group effect shows an overall difference averaged across time points.
Run a Mixed ANOVA on your data →