Population Size Estimation for Open Population Capture-Recapture Using Generalized Estimating Equations

Abstract

This study applied a Generalized Estimating Equation (GEE) approach accounting for heterogeneity, behavioural and environmental effects to estimate the population-size for open population capture-recapture experiment. A non-spatial open population capture-recapture data was simulated using three different trapping occasions (m =4, 5, 6) with population size (N=1000). The GEE estimates for behavioral/heterogeneity covariates and heterogeneity/behavioral/environmental covariates models under different working correlation structures were also presented. The simulation results, show that, for the heterogeneity/behavioral model, the root mean square error (RMSE) for (m = 4, 5, 6) recapture occasions when N=1000 are (199.2171, 199.2573, 1193.2222) and for the heterogeneity/behavioral/environmental covariates model, the RMSE for (m= 4, 5, 6) recapture occasions when N=1000 are (199.2071, 199.2252, 1193.2052). The comparison results between behavioral/heterogeneity covariates model and heterogeneity/behavioral/environmental covariates model show that, the heterogeneity/behavioral/environmental covariates model performs better in estimating the population-size in terms of accuracy as indicated by the smallest values of RMSE. The study concludes that; environmental factors play an important role when estimating the population-size for open population capture-recapture experiments. Capture-recapture, Open oopulation, Population-size, GEE, QIC, RMSE