Outcomes and estimands

Define outcomes and comparison targets

An estimand specifies the quantity the study aims to estimate. Define the population, strategies, outcome and horizon, including treatment changes and competing events. Safety outcomes are included when relevant, not because the study is assumed to be a trial.

Flow diagram

Steps

Comparative study objectives

Define the population and exposure or treatment strategies. State whether the objective is an association or a causal effect.

Primary outcomes

Define validated outcome algorithms, assessment windows and the primary contrast before examining group results.

Secondary outcomes

Specify secondary questions, priorities and the approach to multiple comparisons.

Safety outcomes, if relevant

Define adverse outcomes and ascertainment independent of exposure group. Include these when relevant to the study question.

Define comparative estimands

Specify target population, strategies, outcome, time horizon, treatment-change handling, competing events and summary measure.

Assess ascertainment and missing outcomes

Examine differential surveillance, care outside the data source and the assumptions behind missingness or censoring adjustment.