Validity and power of the case-only approach in prospective cohort and case- cohort studies with time-to-event endpoints: a simulation study

Objective The powerful case-only (CO) approach has been extended for examining statistical interactions for time-to-event outcomes in the context of randomized clinical trials (RCT), but has not yet been investigated in prospective observational data. Methods In our simulation study, we explore the CO approach for time-to-event outcomes in scenarios with main effects of different strength and compare its results with classical Cox proportional hazard and logistic regression models. Results In the cohort settings it was consistently valid and had a similar power as the benchmark analyses. In contrast, in the case-cohort design, the CO approach was valid and more powerful only in the scenario with just one main effect. However, in the presence of two moderate main effects, estimators may be biased, with a moderately inflated type I error rate. In a real-world example of a cohort study, the CO design represents an efficient approach that can be applied at an early follow-up time. Conclusion Under a variety of circumstances, the CO approach is always as powerful, and in some situations even more powerful than the standard models for time-to-event data, but can be biased in the presence of two main effects in the case-cohort framework.