Print PagePopulation modeling requires estimation of vital rates. Modeling vital rates with generalized linear mixed models is a powerful and flexible way to accomplish this. We recently introduced a model for estimating vital rates and their covariation as a function of known and unknown effects, using generalized linear mixed models (GLMMs) implemented in a hierarchical Bayesian framework (Evans et al. 2010). In particular, this included a model-wide year effect (YEAR) influencing all vital rates, which we used to estimate covariation between vital rates due to exogenous factors not directly included in the model. This YEAR effect connects the GLMMs of vital rates into one large model; we refer to this as the “connected GLMMs” approach. Here we used a simulation study to evaluate the performance of a simplified version of the connected GLMMs model, compared to separate GLMMs of vital rates, in terms of their ability to estimate vital rates and their covariation. We simulated data from known relationships between vital rates and a covariate, inducing correlations among the vital rates. We then estimated those correlations from the simulated data using connected vs. separate GLMMs with year random effects. We compared precision and accuracy of estimated vital rates and their correlations under three scenarios of the pervasiveness of the exogenous effect (and thus true correlations).
Results/Conclusions
The two approaches provided equally good point estimates of vital rate parameters, but connected GLMMs provided better estimates of correlations between vital rates than separate GLMMs, both in terms of accuracy and precision, when the common influence on vital rates is pervasive. Even when the exogenous factor affects few parts of the life cycle, connected GLMMs do not perform worse than separate GLMMs at estimating correlations between vital rates. We discuss the situations where connected GLMMs might be best used, as well as further areas of investigation for this approach.
phone 202-833-8773