Stepped-wedge endpoints and estimands

Define effects and exposure duration

The intervention effect may depend on time since adoption. Define the target weighting over periods and exposure durations and the treatment of transition or learning periods.

Flow diagram

Stepped-wedge endpoints and estimandsF1.S1Define outcomes and observationunitsF1.S2Define intervention-effect timingF1.S3Specify target estimand andweightingF1.S4Handle transition and intercurrenteventsF1.S5Prioritize planned contrastsF1.N1Stepped-wedge estimandsEndpointObservationunitCalendar periodExposuredurationTargetweightingPrimary effectDuration effectSafetyF1.N2Assumptions and rationaleF1.N3Method and protocol evidenceF1.S0 Start flowStepped-wedge endpoints and estimandsF1.S999 End flowEnd flow

Steps

Define outcomes and observation units

Specify cluster-period or individual repeated measurements.

Define intervention-effect timing

Distinguish immediate effects from effects varying by time since transition.

Specify target estimand and weighting

Record calendar-period and population weighting.

Handle transition and intercurrent events

Specify wash-in exclusions, delayed delivery and cluster or person loss.

Prioritize planned contrasts

Identify confirmatory versus exploratory duration and subgroup questions.

Stepped-wedge endpoints and estimands

End flow

Tables and supporting information

Stepped-wedge estimands

Stepped-wedge estimandsEndpointObservationunitCalendar periodExposuredurationTargetweightingPrimary effectDuration effectSafety

Preserve both calendar time and time since intervention.

Assumptions and rationale

A constant treatment-effect model can misrepresent effects that evolve with exposure duration.

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.

Sources