Limited-Information Modeling of Loggerhead Turtle Population Size

• Activity Number: 667
• Type: Contributed
• Date/Time: Thursday, August 2, 2012 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): David Hitchcock*+ and John Grego
• Companies: University of South Carolina and University of South Carolina
• Keywords: ecological statistics ; environmental statistics ; capture-recapture ; Bayesian methods ; Metropolis-Hastings

Abstract

We estimate the size of a population of female loggerhead turtles. In traditional capture-recapture studies, individual animals are tagged and information about which animals are captured repeatedly is crucial. For our turtle data, information about individual turtles is not available. Rather, we observe only the counts of successful and failed nestings at a location over three days. We view the turtles' nesting behavior as an alternating renewal process, model it parametrically, and derive probability distributions that describe the behavior of the turtles during the three days via a 3-way contingency table. To estimate the relevant cell probabilities, we adopt a Bayesian approach, taking advantage of strong prior information about certain parameter values. We use a Metropolis-Hastings algorithm to sample from a relevant posterior distribution and derive an estimate of the total population size. A simulation study illustrates the quality and robustness of the method and informs the choices of the algorithm's tuning parameters for the turtle data analysis. We illustrate the method using a data set from loggerhead turtle sites along the South Carolina coast.