Global synthesis of sea turtle von Bertalanffy growth parameters through Bayesian hierarchical modeling

Knowledge of sea turtle demographic rates is central to modeling their population dynamics, but few studies have quantitatively synthesized existing data globally. Here, we used a Bayesian hierarchical model to conduct a meta-analysis of published von Bertalanffy growth curve parameters (growth coefficient, K; asymptotic length, L-infinity) for chelonid sea turtles. We identified 34 studies for 5 of 6 extant chelonids that met minimum selection criteria. We implemented a suite of models that included a multivariate normal likelihood on the log-transformed values of the 2 parameters to evaluate the influence of species, population (regional management unit, RMU), parameter estimation method (mark-recapture, skeletochronology, length-frequency analysis), latitude, and sampled body size range (all sizes, no large, no small, no large or small) on growth parameter estimates. According to information criteria, the best model included a random effect of species. The second best model also included latitude as a fixed effect, but RMU, parameter estimation method, latitude, and sampled body size ultimately did not strongly influence the means or variances of K and L-infinity among studies. The apparent lack of RMU effect on parameter estimates within species may be an artifact of the small number of RMUs with published growth parameter estimates. The species-specific, and in some cases RMU-specific, posterior means and standard deviations of K and L-infinity from this study would be appropriate priors for future studies of growth in chelonid sea turtles or for models of population dynamics. We highlight the need for expanded study and synthesis of sea turtle somatic growth rates.

Automated summary

This study conducted a meta-analysis of growth curve parameters for chelonid sea turtles using a Bayesian hierarchical model, revealing that the species has a significant influence on the parameters. However, other factors such as geographic location, parameter estimation method, latitude, and sampled body size range had minimal impact on the growth parameter estimates.