Time-to-event analysis

Abstract

Survival analysis (or time-to-event analysis) deals with data where the outcome of interest is the length of time until the occurrence of an event. This type of analysis is unique because the event may not occur in all participants (known as censoring). A previous article in this journal covered the basic aspects of conventional survival analysis. In this article, we discuss two unique features – nonproportional hazards (PH) and competing risks.

Keywords

• kaplan–meier estimate
• proportional hazards model
• survival analysis