ROOM: RSCC, F1
Time-to-event data are encountered in many wildlife applications including time-to-infection, death, antler drop, nest destruction, toxin dilution, pathogen elimination, etc. This data is unique because the outcome of interest is not only whether an event occurred, but also when that event occurred. Traditional regression methods are not appropriate for addressing event and time aspects of time to event data. Nor are these methods equipped to easily handle censoring, a special type of missing data that occurs in time-to-event analyses when subjects do not experience the event of interest during the follow-up time. We will present analyses techniques for time to event data that allow for the evaluation of covariate effects, address issues with uncertainty in observed data (such as unknown fates, or uncertainty in the exact time of the event). We demonstrate techniques using the R software package, and focus on a Bayesian implementation of these methods.
Organizers: Robin Russell, Kezia Manlove, Dan Walsh
Supported by: Biometrics Working Group, Wildlife Disease Working Group