What are survival data?

• A. Time to event data (outcome of interest is time until death)
• B. Cross-sectional prevalence data
• C. Binary outcomes
• D. Repeated measures of continuous variables

Answer: (A)

Survival data are time-to-event data, where the outcome is the duration until a specified event occurs (often death). You follow individuals from a defined starting point and record how long it takes for the event to happen; if the event hasn’t occurred by the end of the study or a person is lost to follow-up, their data are censored, meaning their exact time to event is unknown beyond that point. This focus on time until the event and the handling of censoring is what differentiates survival data and drives analyses such as Kaplan-Meier curves and Cox proportional hazards models, which describe how survival probability or hazard changes over time. The event can be death, but it can also be other outcomes like relapse, hospitalization, or failure of a treatment. By contrast, cross-sectional prevalence data capture a snapshot of who has the condition at a single time point; binary outcomes are just yes/no results without time information; and repeated measures of continuous variables track levels over time without necessarily tying them to a specific event timing.