G*Power for nursing research is useful only when its options accurately represent your question and planned statistical test. The programme calculates what you request; it cannot decide whether your inputs are clinically or methodologically defensible.
Before opening G*Power
- Write the primary hypothesis.
- Name the dependent and independent variables.
- Decide the exact SPSS test.
- Obtain a justified effect-size estimate.
- Separate analysable sample size from recruitment size.
What G*Power can calculate
The official G*Power application supports many t, F, chi-square, z and exact tests, as well as a-priori, compromise, criterion, post-hoc and sensitivity analyses (Faul et al., 2007; Faul et al., 2009). Nursing dissertations most often require an a-priori calculation or a sensitivity analysis.
Step 1: choose the test family
Select t tests for many mean comparisons, F tests for ANOVA and regression models, chi-square tests for categorical associations, and exact or z tests only when the proposed model requires them. Do not select a family from the wording of the research topic alone.
Step 2: choose the statistical test
Within each family, distinguish independent from paired comparisons, fixed-model regression from change in R², and omnibus ANOVA from specific contrasts. A repeated-measures nursing intervention is not equivalent to a cross-sectional comparison of different participants.
Step 3: select the analysis type
| G*Power analysis | Question answered | Best use |
|---|---|---|
| A priori | How many observations are required? | Planning recruitment |
| Sensitivity | What effect is detectable with a fixed sample? | Feasibility-limited dissertation |
| Post hoc | What power follows from a specified effect and sample? | Limited diagnostic use |
| Compromise | How should Type I and II errors be balanced? | Specialist design decisions |
Step 4: enter a defensible effect size
Use a comparable nursing study, meta-analysis, pilot or clinically important difference. Check whether the published value is already standardised and whether it matches the same design. For example, an independent-groups effect should not be copied into a paired analysis without adjustment.
Step 5: enter alpha, power and design inputs
Common planning values are alpha 0.05 and power 0.80 or 0.90, but these are decisions, not automatic defaults. Add the number of groups, predictors, measurements, allocation ratio or correlation among repeated measures when requested.
Step 6: calculate and interrogate the result
Record total sample size, group sizes, numerator degrees of freedom and actual power. Then use the X–Y plot or repeat calculations across plausible effects. A single output based on an uncertain effect should not be treated as exact.
How to use this screen: Check that the selected test and analysis type correspond to the nursing hypothesis before interpreting the calculated sample. Retain the input values and output table because they allow a supervisor or examiner to reproduce the calculation.
Transfer the plan into SPSS
G*Power designs the sample; SPSS analyses the collected data. Keep the test names aligned across the protocol, G*Power output and SPSS procedure. If you calculated for two independent groups but later run a repeated-measures model, the original target may no longer be suitable.
Frequently asked questions
Is G*Power free?
Yes. Use the official Heinrich Heine University Düsseldorf source rather than an unofficial download site.
Does G*Power work for prevalence surveys?
A precision-based proportion calculation is often clearer. G*Power may address a hypothesis about proportions but not every survey objective.
What version should I report?
Report the version actually used and retain the saved output or screenshot.
Can G*Power justify a completed sample?
A sensitivity analysis can describe detectable effects, but it should not be misrepresented as an a-priori recruitment calculation.
Related Nursing Guides
- Effect Size for Nursing Research: SPSS and G*Power Guide
- Missing Data in Nursing Research: SPSS Dissertation Guide
- Statistical Power in Nursing Research: Avoid Weak Studies
Conclusion
Use G*Power as a transparent calculation tool, not a substitute for statistical reasoning. Correct test selection, justified inputs and reproducible reporting are what make the output defensible in a nursing dissertation.
Continue with our nursing SPSS sample-size and power analysis service, SPSS data-analysis service, statistical-test selection guide, SPSS output interpretation guide, or contact us.
References
- Faul, F., Erdfelder, E., Lang, A.-G. and Buchner, A. (2007) ‘G*Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences’, Behavior Research Methods, 39, pp. 175–191.
- Faul, F., Erdfelder, E., Buchner, A. and Lang, A.-G. (2009) ‘Statistical power analyses using G*Power 3.1’, Behavior Research Methods, 41, pp. 1149–1160.
- Kang, H. (2021) ‘Sample size determination and power analysis using the G*Power software’, Journal of Educational Evaluation for Health Professions, 18, 17.
- Lakens, D. (2022) ‘Sample size justification’, Collabra: Psychology, 8(1), 33267.
