Research overview: state-space models for telemetry

State-space models provide a unified statistical framework that separates the true, unobserved movement process from the noisy observation process that telemetry produces. This overview explains how they simultaneously account for location error and model the animal's movement, yielding filtered and smoothed estimates of position, behavioral state, and movement parameters. By formally handling measurement error, state-space models are well suited to coarse or irregular data, including older Argos fixes and gappy GPS records. For felid studies, they can clean trajectories, infer behavioral modes, and propagate uncertainty into downstream analyses of home range and selection. The overview discusses Bayesian and likelihood implementations and computational demands. State-space modeling underlies many modern movement methods, offering a principled bridge from imperfect data to ecological inference.