Modelling Rare Events in an Adaptive Cluster Sampling Design with Heterogeneity among Networks and within the Network Units

Rare events population (φ) is hard-to-reach, sparsely distributed and clustered; an Adaptive Cluster Sampling (ACS) the design to collect information from φ. Researchers Policy Makers have modelled φ in ACS with homogeneity assumptions. This study heterogeneity among networks within network units. Data International Institute of Tropical Agriculture on Culcasia Scandens, understory plant simulation were used validate model. Estimators for total average number rare derived their statistical properties examined. Bayesian Model was embedded designed develop model predicting events. Parameters α, β λ control expected grid cells events, conditional sub-network each respectively. Markov Chain Monte-Carlo Algorithm R Winbugs software estimated these parameters. The robustness examined its Sensitivity Analysis carried out. Diagnostic checks done proposed compared existing samples converged represented target posterior lies 95% HPD credible interval. estimators unbiased, consistent efficient. criterion inference robust a good fit. results revealed that event best under