B1514
Title: Individual random effect models: Accounting for survivorship bias
Authors: Ruth King - University of Edinburgh (United Kingdom) [presenting]
Blanca Sarzo - University of Valencia (Spain)
Rachel McCrea - Lancaster University (United Kingdom)
Abstract: Survivorship bias arises when conclusions are drawn conditional on only the surviving individuals, whilst failing to correct for those individuals who have not survived. The issue has been well studied in many fields, such as economy, construction, forestry, health etc., but has been less well explored within the context of capture-recapture studies. We explore the implications related to survivorship bias that may arise in relation to individual heterogeneity models that are commonly fitted to capture-recapture data. The survivorship bias is manifested within these studies in that weaker individuals are more likely to die at a younger age compared to stronger individuals who may survive for longer within the study period. This implies that weaker individuals have a smaller probability of being observed within the study compared to stronger individuals, thus leading to an overestimate in the survival probabilities. We will initially discuss the impact of survivorship bias on associated survival probabilities within the common Cormack-Jolly-Seber model before describing how we can correct for this issue within capture-recapture studies when individuals are of known age when they are initially observed. To demonstrate the approach, we will initially consider simulated data, before applying the developed approach to data collected on ibex.