A general framework for modeling memory in capture—Recapture data
International audience In classical multisite capture-recapture (CR) models, the probability of moving to a new location depends only on the current site occupied. Yet, it is known that some species, such as Canada geese (Branta canadensis), have a strong tendency to return to sites visited earlier...
Published in: | Journal of Agricultural, Biological, and Environmental Statistics |
---|---|
Main Authors: | , , |
Other Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2009
|
Subjects: | |
Online Access: | https://hal.science/hal-02126332 https://doi.org/10.1198/jabes.2009.06108 |
Summary: | International audience In classical multisite capture-recapture (CR) models, the probability of moving to a new location depends only on the current site occupied. Yet, it is known that some species, such as Canada geese (Branta canadensis), have a strong tendency to return to sites visited earlier during their life. To account for this "phenomenon of memory," several authors have considered CR models in which transition probabilities depend not only on the current location of the individuals but also on the sites previously visited. In this article, we clarify the differences between these previous "memory" models and provide a general framework for the study of memory using CR data. We illustrate this study with the reanalysis of the movements of Canada geese among three wintering sites. This article has supplementary material online. |
---|