Keywords: estimands, safety, benefit-risk
Just as statisticians became comfortable with specifying estimands for efficacy endpoints and explaining them to their clinical colleagues, they face the new challenge of safety estimands. Safety endpoints are multifaceted with frequency, severity, timing, duration and reversibility. They are most often underpowered, unexpected and impossible to impute. Safety estimands are impacted differently by intercurrent events than efficacy estimands. To make this topic even more challenging and interesting, is the pairing of safety and efficacy estimands to conduct a benefit-risk assessment. Dual estimands will be discussed with examples.