Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions

摘要: We discuss hidden Markov-type models for fitting a variety of multistate random walks to wildlife movement data. Discrete-time Markov (HMMs) achieve considerable computational gains by focusing on observations that are regularly spaced in time, and which the measurement error is negligible. These conditions often met, particular data related terrestrial animals, so likelihood-based HMM approach feasible. describe number extensions HMMs animal modeling, including more flexible state transition individual effects (fitted non-Bayesian framework). In we consider so-called semi-Markov models, may substantially improve goodness fit provide important insights into behavioral switching dynamics. To showcase expediency these methods, an application hierarchical model multiple bison paths.