marked: an R package for maximum likelihood and Markov Chain Monte Carlo analysis of capture–recapture data

摘要: Summary We describe an open-source r package, marked, for analysis of mark–recapture data to estimate survival and animal abundance. Currently, marked is capable fitting Cormack–Jolly–Seber (CJS) Jolly–Seber models with maximum likelihood estimation (MLE) CJS Bayesian Markov Chain Monte Carlo methods. The can be fitted MLE using optimization code in R or Automatic Differentiation Model Builder. latter allows incorporation random effects. Some package features include: (i) individual-specific time intervals between sampling occasions, (ii) generation starting values from generalized linear model approximations (iii) prediction demographic parameters associated unique combinations individual time-specific covariates. We demonstrate a commonly analysed European dipper (Cinclus cinclus) set. The will most useful ecologists large sets many covariates.