Red Door Analytics

More than one thing can happen first, and one of them stops the clock. Treating a competing death as censoring answers a different question — what would happen if it could not occur — which is rarely the one being asked.

Also called cumulative incidence.

A narrower method under survival analysis.

Competing risks: Two Aalen–Johansen curves, stacked, so the upper edge is the probability of having died of anything and each band is a real share of the original cohort.
Two Aalen–Johansen curves, stacked, so the upper edge is the probability of having died of anything and each band is a real share of the original cohort. Censoring the other cause instead asks what would happen if it could not occur, which is a different question and usually not the one being asked.

Working on competing risks?

We do this every week — as a collaborator on your study, or as the people who wrote the software you are using.

Get in touch Start a project