Multivariate State Hidden Markov Models for Mark-Recapture Data

摘要: State-based Cormack-Jolly-Seber (CJS) models have become an often used method for assessing states or conditions of free ranging animals through time. Although originally envisioned to account differences in survival and observation processes when are moving though various geographical strata, it has evolved model vital rates different life-history diseased states. We further extend this useful class the case multivariate state data. Researchers can record values several interest, e.g., geographic location reproductive state. Traditionally, these would be aggregated into one with a single probability uncertainty. However, by modeling as vector, partial knowledge vector well dependence between variables parsimonious way. A hidden Markov formulation allows straightforward maximum likelihood inference. The proposed HMM demonstrated study using data from California sea lion study.