Introduction
Many nursing and healthcare students collect data from the same participants at baseline, post-intervention, and follow-up, then get stuck at the analysis stage. The dataset may include pain scores before treatment, knowledge scores after education, or anxiety scores across several visits, but the student may not know whether SPSS repeated measures ANOVA is the right test.
The difficulty is not only choosing the test. Students also need to know how to arrange the dataset, define the within-subjects factor, read Mauchly’s test of sphericity, choose the correct correction row, interpret pairwise comparisons, and report the result in APA 7th edition format.
SPSS repeated measures ANOVA helps students test whether the mean score changes across three or more related measurements from the same participants. It is useful in nursing dissertations, capstones, quality improvement projects, and healthcare intervention studies where change over time matters.
Need help running repeated measures ANOVA in SPSS? Our SPSS Data Analysis Help service can help you check assumptions, run the test, interpret SPSS output, and prepare APA-style results for your nursing research.
What Is Repeated Measures ANOVA in SPSS?
Repeated measures ANOVA in SPSS compares mean scores from the same participants measured repeatedly across three or more time points or related conditions. The repeated measurements must belong to the same outcome variable.
For example, a nursing student may measure medication knowledge before patient education, immediately after education, and four weeks later. Because the same participants provide all three scores, the measurements are related. Repeated measures ANOVA tests whether the average knowledge score differs across those time points.
Common nursing and healthcare examples include pain scores measured before treatment, after treatment, and at follow-up; anxiety scores across three clinical visits; patient satisfaction scores across three stages of care; and medication adherence scores measured at baseline, four weeks, and eight weeks.
The key point is simple: the same people are measured more than twice on the same continuous or approximately continuous outcome.
When Should You Use SPSS Repeated Measures ANOVA?
Use repeated measures ANOVA when the same participants are measured three or more times and the research question asks whether the mean score changes across those repeated measurements. The repeated factor may represent time, condition, trial, session, or stage of care.
The outcome should be continuous or approximately continuous. Examples include test scores, pain ratings, anxiety scale scores, confidence scores, adherence scores, or patient satisfaction scale scores.
Do not use this test for only two related measurements. If you have pretest and posttest only, a paired-samples t-test is usually the simpler option. Do not use it for independent groups only, because one-way ANOVA is designed for different participants in different groups. If your design includes repeated time points and a group variable, such as intervention versus control, you may need mixed ANOVA instead.
Repeated measures ANOVA may also be unsuitable when missing data are heavy, time intervals are unequal, or the dataset has a complex longitudinal structure.
Repeated Measures ANOVA vs Paired t-Test, One-Way ANOVA, and Mixed ANOVA
A paired-samples t-test compares the same participants on two related measurements. For example, it can compare pretest and posttest knowledge scores.
Repeated measures ANOVA compares the same participants across three or more measurements. For example, it can compare pretest, posttest, and follow-up knowledge scores.
One-way ANOVA compares three or more independent groups, such as three different patient groups or three separate nursing cohorts. The participants are not the same across groups.
Mixed ANOVA combines a repeated-measures factor with a between-subjects group factor. For example, it can test whether knowledge changes over three time points differently for intervention and control groups.
Keep the test matched to the design. Wrong test selection can lead to incorrect interpretation, even when the SPSS output looks complete. For broader test-selection support, see Inferential Statistics Help for Nursing Research.
Example Nursing Research Questions for Repeated Measures ANOVA
A repeated measures design fits questions where one group is followed across time or exposed to several related conditions.
Example 1: Does patient education improve medication knowledge from pretest to posttest to follow-up? The within-subjects factor is time, with three levels: pretest, posttest, and follow-up. The continuous outcome is medication knowledge score.
Example 2: Do mean pain scores differ across baseline, 24 hours, and 48 hours after an intervention? The within-subjects factor is time, and the outcome is pain score.
Example 3: Does nurse confidence change across three simulation training sessions? The within-subjects factor is session, and the outcome is confidence score.
Example 4: Do anxiety scores change across admission, discharge, and follow-up? The within-subjects factor is care stage, and the outcome is anxiety score.
Each example uses the same participants across three related measurements, which is why repeated measures ANOVA fits.
Before Running Repeated Measures ANOVA in SPSS
SPSS repeated measures ANOVA usually requires a wide-format dataset. Each row represents one participant. Each repeated measurement appears in a separate column.
For a three-time-point medication knowledge study, the columns may be named knowledge_pretest, knowledge_posttest, and knowledge_followup. The order of these variables matters because SPSS uses the order to define the time points.
Before running the test, confirm that the outcome was measured consistently across time. Check variable labels so each time point is clear. Review missing values, outliers, impossible values, and descriptive statistics. Means and standard deviations should be inspected before inferential testing, which connects with Descriptive Data Analysis in Nursing Research.
You should also confirm that the same participants provided repeated scores. If different participants completed different time points, the design may not be a standard repeated measures ANOVA.
Assumptions of Repeated Measures ANOVA
Repeated measures ANOVA has several assumptions.
The repeated dependent variable should be continuous or approximately continuous. Nursing scale scores, test scores, and clinical scores often meet this condition when measured appropriately.
The measurements must be related. The same participants should provide scores at each time point or condition.
There should be no severe outliers. Extreme values can distort means, standard deviations, and the F-test.
Normality should be reviewed, especially in small samples. Students can inspect distributions, histograms, Q-Q plots, or descriptive statistics for each time point and for difference scores.
Sphericity is the major assumption students often find confusing. It means that the variances of the differences between all pairs of repeated measurements are approximately equal. Mauchly’s test is commonly used to check this assumption in SPSS. Sphericity matters because violations can affect the Type I error rate in repeated measures ANOVA (Blanca et al., 2023).
How to Run SPSS Repeated Measures ANOVA
To run repeated measures ANOVA in SPSS:
- Open the dataset in SPSS.
- Click Analyze.
- Select General Linear Model.
- Click Repeated Measures.
- Enter the within-subjects factor name, such as Time.
- Enter the number of levels, such as 3 for baseline, posttest, and follow-up.
- Click Add.
- Click Define.
- Move the repeated-measure variables into the within-subjects boxes in the correct order.
- Click Options.
- Select descriptive statistics and effect size if required.
- Request estimated marginal means or pairwise comparisons if needed.
- Choose a Bonferroni adjustment for pairwise comparisons if appropriate.
- Click Continue.
- Click OK.
IBM lists the procedure under Analyze > General Linear Model > Repeated Measures and notes that the Options menu can request estimated marginal means and other useful statistics (IBM Corp., n.d.).
SPSS Repeated Measures ANOVA Output: What to Read
Within-Subjects Factors
This table confirms how SPSS ordered the repeated measurements. Check it first. If baseline, posttest, and follow-up are in the wrong order, the interpretation may be wrong.
Descriptive Statistics
This table shows the mean and standard deviation for each time point or condition. It helps you understand the pattern before reading significance tests.
Mauchly’s Test of Sphericity
This table helps decide whether the sphericity assumption is met. It affects which row you report in the Tests of Within-Subjects Effects table.
Tests of Within-Subjects Effects
This table gives the main F-test for change across time or condition. It includes different rows such as Sphericity Assumed, Greenhouse-Geisser, Huynh-Feldt, and Lower-bound.
Pairwise Comparisons
Pairwise comparisons show which specific time points differ. A significant main effect tells you that at least one mean differs, but pairwise comparisons show where the differences occur.
How to Interpret Mauchly’s Test of Sphericity
Mauchly’s test checks whether the sphericity assumption has been met. If Mauchly’s test is not significant, sphericity is usually treated as met, and students often report the Sphericity Assumed row.
If Mauchly’s test is significant, sphericity is violated. In that case, use a corrected row such as Greenhouse-Geisser or Huynh-Feldt. These corrections adjust degrees of freedom to reduce the risk of an inflated Type I error.
Greenhouse-Geisser is often treated as the more conservative correction, especially when the violation is stronger. Huynh-Feldt may be used when the violation is less severe. Students should follow their statistical plan, assignment rubric, or supervisor guidance.
Laerd Statistics describes sphericity as equality of the variances of differences between related groups and explains why repeated-measures ANOVA is sensitive to this assumption (Laerd Statistics, n.d.).
How to Interpret Tests of Within-Subjects Effects
The Tests of Within-Subjects Effects table gives the main repeated-measures result. Do not report a row randomly.
If sphericity is met, use the Sphericity Assumed row. If sphericity is violated, use the appropriate correction row, usually Greenhouse-Geisser or Huynh-Feldt, depending on your statistical plan.
Report the F value, degrees of freedom, p-value, and effect size if required. A significant result means that at least one repeated measurement differs from another. It does not tell you which time points are different.
UCLA’s SPSS repeated-measures guide shows that the within-subjects test is used to evaluate whether scores change over time in repeated-measures analysis (UCLA OARC, n.d.).
How to Interpret Pairwise Comparisons
Pairwise comparisons identify where the differences occur. For example, they can show whether medication knowledge increased from pretest to posttest, whether it remained higher at follow-up, and whether posttest and follow-up differ.
Use adjusted p-values when multiple comparisons are made. Bonferroni adjustment is commonly requested in SPSS because it helps control the risk of false positives across several comparisons.
Interpret direction, not only significance. A useful results sentence should say whether scores increased, decreased, or stayed stable.
Example: Knowledge scores increased from pretest to posttest and remained higher at follow-up, but the posttest-to-follow-up difference was not statistically significant.
This interpretation connects the numbers to the nursing intervention.
Effect Size in Repeated Measures ANOVA
SPSS may provide partial eta squared. This effect size helps describe the magnitude of the repeated-measures effect.
A statistically significant p-value does not automatically mean the result is clinically important. A small change may be statistically significant in a large sample but may not matter in practice. A moderate change in a small quality improvement project may be clinically meaningful even when the p-value is borderline.
Nursing students should interpret effect size alongside descriptive means, confidence intervals where available, sample size, intervention goals, and clinical context. This is part of sound inferential interpretation and connects with Inferential Data Analysis in Nursing Research.
Common Mistakes in SPSS Repeated Measures ANOVA
Common mistakes include:
- Using repeated measures ANOVA for only two time points
- Treating repeated measurements as independent groups
- Entering time-point variables in the wrong order
- Ignoring Mauchly’s test of sphericity
- Reporting the wrong correction row
- Reporting a significant main effect without pairwise comparisons
- Ignoring missing values
- Forgetting effect size
- Treating statistical significance as clinical importance
- Copying SPSS tables without explaining the research question
The goal is not to paste every SPSS table. The goal is to report the correct result and explain what it means for the nursing or healthcare study.
If your repeated measures ANOVA output has confusing sphericity results, multiple correction rows, unclear pairwise comparisons, or APA reporting issues, our Dissertation Data Analysis Help service can help you interpret the output and write the results clearly.
How to Report Repeated Measures ANOVA in APA 7th Edition
Repeated measures ANOVA APA reporting should include the research purpose, outcome variable, repeated-measures factor, number of time points, descriptive means and standard deviations, sphericity decision, F statistic, degrees of freedom, p-value, effect size, pairwise comparisons, and interpretation.
APA Style guidance supports clear reporting of numbers and statistics in research writing (American Psychological Association, 2024).
Example with sphericity met:
“A repeated measures ANOVA was conducted to examine changes in medication knowledge across pretest, posttest, and follow-up. Mauchly’s test indicated that the assumption of sphericity was not violated, χ²(2) = 3.18, p = .204. The effect of time was statistically significant, F(2, 58) = 12.46, p < .001, partial η² = .30.”
Example with Greenhouse-Geisser correction:
“Mauchly’s test indicated that the assumption of sphericity was violated, χ²(2) = 8.91, p = .012. Therefore, Greenhouse-Geisser corrected results were interpreted. The effect of time was statistically significant, F(1.54, 44.67) = 9.82, p = .001, partial η² = .25.”
Replace all values with your exact SPSS output.
Repeated Measures ANOVA Example in Nursing Research
A nursing student evaluates whether a patient education intervention improves medication knowledge at pretest, posttest, and four-week follow-up.
The dataset is arranged with one row per participant and three columns for knowledge_pretest, knowledge_posttest, and knowledge_followup. Descriptive statistics show that the mean knowledge score increased from pretest to posttest and remained higher at follow-up.
The student runs repeated measures ANOVA in SPSS with Time as the within-subjects factor. Mauchly’s test is reviewed first. If it is not significant, the student reports the Sphericity Assumed row, and if it is significant, the student reports the Greenhouse-Geisser or Huynh-Feldt corrected row.
If the within-subjects effect is significant, pairwise comparisons are reviewed. The student may find that pretest differs from posttest and follow-up, while posttest and follow-up do not differ. This would suggest that the intervention improved knowledge and that the improvement was maintained at follow-up.
The write-up should connect the statistical finding to the intervention, not only report p-values.
When Repeated Measures ANOVA May Not Be Enough
Repeated measures ANOVA is not always the best method. Another approach may be needed when many participants have missing follow-up data, time intervals are unequal, or measurements are nested within sites, wards, or clinics.
A different method may also be required when the study has an intervention group and a control group, when covariates must be controlled, or when the outcome is ordinal, binary, or highly non-normal.
Depending on the research question, students may need mixed ANOVA, repeated measures ANCOVA, a nonparametric alternative, or linear mixed models. Linear mixed models are often considered when missing data patterns or complex longitudinal structures make standard repeated measures ANOVA too limited.
Do not switch methods only because one output looks easier. Match the method to the design, assumptions, and research question.
When to Get Help With SPSS Repeated Measures ANOVA
Get help when you are unsure whether repeated measures ANOVA fits your study design. This is common when the dataset has unclear time-point variables, missing follow-up values, unequal intervals, or both repeated and group factors.
Support is also useful when Mauchly’s test is significant and the correction rows are confusing. Many students report the wrong row from the Tests of Within-Subjects Effects table or forget to interpret pairwise comparisons after a significant main effect.
Students may also need help when effect size is required, a supervisor asks for APA reporting revisions, or the findings must be connected to hypotheses and clinical meaning.
For SPSS setup, assumption checks, pairwise comparisons, and results interpretation, SPSS Data Analysis Help can support your repeated-measures analysis from dataset review to final write-up.
Conclusion
SPSS repeated measures ANOVA helps nursing and healthcare students test whether the same participants’ mean scores change across three or more time points or related conditions. It is especially useful for pretest-posttest-follow-up studies, intervention evaluations, simulation training studies, quality improvement projects, and repeated clinical measurements.
Accurate reporting requires more than running the menu. Students must prepare the dataset correctly, check assumptions, read Mauchly’s test, use the correct correction row, interpret pairwise comparisons, report effect size, and explain the finding in relation to the research question.
Need expert help with SPSS repeated measures ANOVA, Mauchly’s test, Greenhouse-Geisser correction, pairwise comparisons, or APA 7th edition reporting? Upload your dataset, research questions, hypotheses, and rubric through our SPSS Data Analysis Help page for focused nursing research support.
FAQs
1. What is repeated measures ANOVA in SPSS?
Repeated measures ANOVA in SPSS compares mean scores from the same participants measured across three or more time points or related conditions.
2. When should I use repeated measures ANOVA instead of a paired t-test?
Use a paired t-test when the same participants have two related measurements. Use repeated measures ANOVA when they have three or more related measurements.
3. What is Mauchly’s test of sphericity in SPSS?
Mauchly’s test checks whether the sphericity assumption is met. Sphericity means the variances of differences between repeated measurements are approximately equal.
4. What if sphericity is violated in repeated measures ANOVA?
If sphericity is violated, report a corrected result such as Greenhouse-Geisser or Huynh-Feldt, depending on your statistical plan or supervisor guidance.
5. How do I report repeated measures ANOVA in APA 7th edition format?
Report the outcome, time points, descriptive statistics, Mauchly’s test or correction used, F statistic, degrees of freedom, p-value, effect size, pairwise comparisons, and interpretation.
References
American Psychological Association. (2024). Numbers and statistics guide.
Blanca, M. J., Alarcón, R., Arnau, J., Bono, R., & Bendayan, R. (2023). Repeated measures ANOVA and adjusted F-tests when sphericity is violated: Which procedure is best? Frontiers in Psychology, 14, Article 1192453.
IBM Corp. (n.d.). GLM repeated measures options. IBM Documentation.
Laerd Statistics. (n.d.). An introduction to, testing for, and interpreting sphericity.
UCLA Office of Advanced Research Computing. (n.d.). Repeated measures analysis with SPSS.
