Dealing with many correlated covariates in capture–recapture models.

• Published in: Population Ecology
• Main Authors: Gimenez, Olivier, O., Barbraud, Christophe
• Other Authors: Centre d’Ecologie Fonctionnelle et Evolutive (CEFE), Université Paul-Valéry - Montpellier 3 (UPVM)-Institut National de la Recherche Agronomique (INRA)-Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-École Pratique des Hautes Études (EPHE), Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD France-Sud )-Institut national d’études supérieures agronomiques de Montpellier (Montpellier SupAgro), Centre d'Études Biologiques de Chizé - UMR 7372 (CEBC), Institut National de la Recherche Agronomique (INRA)-La Rochelle Université (ULR)-Centre National de la Recherche Scientifique (CNRS)
• Format: Article in Journal/Newspaper
• Language: English
• Published: HAL CCSD 2017
• Subjects: Animal demography; Population dynamics; Principal-component capture–recapture model; Snow petrel; Survival estimation; [SDE]Environmental Sciences; Snow Petrel
• Online Access: https://hal.science/hal-01574997; https://doi.org/10.1007/s10144-017-0586-1

International audience Capture–recapture models for estimating demographic parameters allow covariates to be incorporated to better understand population dynamics. However, high-dimensionality and multicollinearity can hamper estimation and inference. Principal component analysis is incorporated within capture–recapture models and used to reduce the number of predictors into uncorrelated synthetic new variables. Principal components are selected by sequentially assessing their statistical significance. We provide an example on seabird survival to illustrate our approach. Our method requires standard statistical tools, which permits an efficient and easy implementation using standard software.