Analysis Of Wildebeest Density Distribution In Relation To Resources Using Bayesian Approach: A Case Study Of The Amboseli Ecosystem, Kenya.

Abstract

For a long time ecological models; have been largely based on the frequentist approach which deals with point estimation. However, in recent years, Bayesian methods have become more common in many domains including ecological modeling (Gelman et al., 2004). Although Bayesian methods have been studied for many years, it is only recently that their practical application has become truly widespread, largely due to high computational overhead of performing the marginalization (integration and summations), which lie at the heart of the Bayesian paradigm. For this reason, more traditional approaches based on point estimation of parameters have typically been the method of choice. However, availability of fast computers and development of Markov chain Monte Carlo (MCMC) techniques and variation inference have greatly extended the range of models amenable to a Bayesian treatment. This project investigates the hypothesis that resource availability can be used to predict the density distribution of wildebeest ( Connochaetes taurinus) in the Amboseli ecosystem. Bayesian models were developed to predict the density distribution of wildebeest in the Amboseli region as seasons progressed. The predictor variables used included grass height, grass greenness, habitat and a season's indicator variable. The models were fitted on wildebeest density data sampled by aerial survey method using the Jolly II method based on a grid system which was carried out by ARCP between 1975 and 2006. This approach offers a robust solution to modeling density distribution providing a more realistic assessment of error and uncertainty in the results. We illustrate the approach with sample data sets for wildebeest in Amboseli ecosystem, Kenya.