Stepped-wedge period data and follow-up
Track repeated observations and missingness
Preserve cluster-period keys and repeated-person identifiers when relevant. Record calendar time and time since transition separately; changing participant composition can affect interpretation.
Flow diagram
Steps
Validate assigned and actual transition
Retain sequence, scheduled date and delivered intervention date.
Construct cluster-period records
Record calendar periods, exposure duration and sampling denominators.
Link repeated participants when applicable
Respect closed/open cohort or repeated cross-sectional sampling.
Track missingness and deviations
Separate absent clusters, missing periods and missing individual outcomes.
Freeze analysis populations
Specify transition-window handling and estimand-specific inclusion.
Stepped-wedge period data and follow-up
End flow
Tables and supporting information
Cluster-period data rules
Do not collapse repeated periods into a single before/after observation.
Assumptions and rationale
Actual transition and assigned schedule differ under deviations; analysis handling must follow the chosen estimand.
Method and protocol evidence
Attach the protocol, methodological sources and versioned software specification supporting these decisions. Record citations and provenance; do not enter participant identifiers.