Survival analysis encompasses a collection of statistical methods for describing time to event data. It originates from clinical studies, where physicians are mostly interested in assessing the effect of a new therapy on survival against a control group, or how certain features represent a risk of an adverse event in time. This post introduces the challenges related to survival analysis (censoring) and explains popular metrics to evaluate survival models, sharing practical Python examples along the way. Let us imagine to be clinical researchers. As we want to assess that the new treatment has a significant effect in preventing an adverse event (such as death), we monitor the patients of both groups for a certain period of time. This condition goes under the name of right censoring, and it is a common trait of survival analysis studies.