Cluster randomized trial
Set up, run, and review this analysis in Lifescio.
Supported analysis
Within-cluster correlation inflates variance through the design effect 1 + (m − 1) × ICC. The app searches for a whole number of clusters per arm using a cluster-level t approximation and inflates participants per cluster for individual dropout.
Supported scope: The current design assumes equal cluster sizes, common variance and ICC, and no cluster dropout. Unequal sizes, binary outcomes and stepped-wedge designs require other calculations.
Prepare data and configure the analysis
Enter a continuous-outcome Expected mean difference and Individual standard deviation in the same units. Analyzable participants per cluster is the number expected to contribute to analysis, not the number approached. Enter Intracluster correlation as a proportion, such as 0.05, and give participant dropout separately.
This workflow plans equal numbers of equal-sized clusters in two arms using a t-based approximation. It does not support binary outcomes, stepped-wedge designs, unequal cluster sizes, or explicit cluster dropout. Keep a record of the evidence supporting the correlation and expected cluster size; rerun plausible alternatives as separate saved scenarios.
Input reference (7 fields)
Enter your data and prespecified choices. Ranges include both limits. For table fields, use cell editing, Paste data, or Import CSV / TSV. Review whether the first imported row contains headings and map the source columns before applying the import. Empty numeric cells are not treated as zero. Open file is for an exported Lifescio analysis JSON file, not a spreadsheet.
| Input | Format | Allowed range |
|---|---|---|
| Expected mean difference | Number | 0.001–100 |
| Individual standard deviation | Number | 0.001–1000 |
| Analyzable participants per cluster | Whole number | 2–10000 |
| Intracluster correlation | Number | 0–0.99 |
| Target power | Number | 0.5–0.999 |
| Significance level | Number | 0.001–0.2 |
| Participant dropout proportion | Number | 0–0.8 |
Run and review
- Give the analysis a descriptive name and review every example value. Record units, data preparation, and planning assumptions in Reproducibility & notes. For simulations, record the seed and replication or sampling settings.
- Choose Run analysis. Resolve input errors before interpreting output. In the connected app, a run uses a saved input revision; local preview runs need the page to stay open.
- Review Diagnostics for method limitations, warnings, and available numerical checks. A completed run means computation finished; it does not establish that the assumptions fit your study.
- Use the Result table selector to inspect each output. Editing inputs does not recalculate existing results: an earlier-input notice means you need to run again to obtain matching results.
Understand the outputs
In Cluster design, read Clusters per arm first, then Total clusters and Total analyzable. Recruit per cluster includes participant dropout, while Analyzable per cluster retains the planning input. Design effect shows the correlation penalty and Achieved power uses the selected integer cluster count.
Multiply total clusters by recruitment per cluster for the overall recruitment target. Do not round a fractional site estimate yourself or replace a required site with extra participants without recalculating. The output already searches integer cluster counts.
Troubleshooting and common mistakes
If the required count is infeasible, compare scientifically credible effect, correlation, and cluster-size scenarios. Do not lower the correlation solely to meet a recruitment budget. A zero effect cannot support this power calculation, and zero standard deviation is invalid.
Participant dropout cannot stand in for loss of an entire site. If cluster sizes vary substantially or sites may withdraw, the displayed design is incomplete for that setting; use a design-specific calculation before finalizing recruitment.
After correcting inputs, run again and check that the results belong to the new input snapshot. Increasing simulation draws improves numerical precision only; it does not repair invalid data or an unsuitable model.
Save, compare, and export
In the connected app, Save analysis retains the inputs in your account. Run history lets you inspect earlier runs, each with the input revision it used. In local preview, Save analysis downloads an input file instead; download results before leaving the page.
Use Result + inputs for a JSON archive containing the completed result and its inputs, Download CSV for the selected result table, PDF report for a report, and a chart's SVG button for its figure. Table displays round to three decimals; CSV and JSON exports retain calculation precision. Use those values when assessing a result near a decision boundary.
To reopen an archive, select the matching analysis method and choose Open file. Imported inputs start a new draft; a result archive can also display its retained result. It does not attach itself to an existing account analysis or recompute the result. Save or run the imported draft when you want a new account record.