Power Analysis & Sample Size Module
The Power Analysis & Sample Size Module helps researchers determine how many participants a study needs and whether a completed study had enough statistical power to detect the effect it was looking for.
Statistical power is the probability that a study will detect a real effect when one exists. At 80% power, a study has an 80% chance of finding a true effect and a 20% chance of missing it. Power analysis links four quantities -- sample size, effect size, significance level (alpha), and power (1 - beta) -- so that fixing any three determines the fourth.
What the module does
| Capability | What it does |
|---|---|
| Sample size calculation (a-priori) | Calculate participants needed using validated formulas for each study design |
| Post-hoc power calculation | Check whether a completed study had enough power |
| Broad design coverage | Paired/independent means, proportions, correlations, odds ratios, relative risk, survival, ROC AUC, and more |
| Effect-size computation | Enter raw values, tool computes standardised effect size (e.g. Cohen's d) |
| Manuscript methods text | Generate ready-to-paste methods paragraph with citations |
| Power curves | Interactive charts showing how power changes with sample size and effect size |
Two kinds of calculation
| Mode | Question it answers | When you use it |
|---|---|---|
| A-priori (prior) sample size | "How many participants do I need?" | Design phase, before collecting data |
| Post-hoc power | "Did my study have enough power?" | After data collection, to interpret results |
Best practice: calculate sample size during the design phase to prevent enrolling too few participants to reach a conclusion or more than necessary.
Three ways to reach a calculator
| Pathway | For researchers who... | How it works |
|---|---|---|
| I Know My Goal (Purpose-driven) | Know research objective but not exact test | State objective, module matches to right calculator |
| I Know My Outcome (Outcome-driven) | Know data type to collect | Pick outcome type, guided wizard routes you |
| I Know My Test (Advanced) | Know exactly which test needed | Jump straight to specific calculator |
All three pathways lead to the same underlying calculators.
The calculator families
| Group | Contents |
|---|---|
| Outcome-Driven Calculations | Outcome-Based Sample Size Wizard |
| Prior Power Calculations | 11 a-priori calculators: paired/independent means, proportions, correlation, two correlations, odds ratio, relative risk, survey/prevalence, Mead Method (animal studies), survival (hazard ratio), ROC AUC |
| Post-Hoc Power Calculations | 8 power calculators: two proportions, two means, paired means, correlation, chi-square, ANOVA, odds ratio, relative risk |
Methods Section feature
After calculation, each calculator produces a manuscript-ready paragraph describing the test used, parameters entered, computed effect size, and resulting sample size or power -- with academic citations (e.g. Cohen, 1988). Text can be copied with one click for research proposals, manuscripts, or ethics submissions.
Who the module is for
- Thesis and dissertation projects -- justifying sample size in a proposal
- Peer-reviewed journal submissions -- reporting a-priori power analysis
- Ethics committee and regulatory submissions -- auditable sample-size reports
- Grant and funding proposals -- clear power-analysis section with exportable methods text