Model-based inferences from adaptive cluster sampling

Adaptive cluster sampling is useful for exploring populations of rare plant and animal species which cluster together because it allows sampling effort to be concentrated in areas where observed values are high. This allows more useful data to be collected with less effort than simpler sampling methods which ignore the population structure. In this paper, we take a model based approach in a Bayesian framework to make inference about the number of individuals in a sparse, clustered population. This approach allows us to use knowledge of the population to inform both the sampling design and inference, thereby making coherent use of the data in the analysis and resulting in improved population estimates. The methodology is compared to the design-based modified HorvitzThompson estimator through analysis of the examples presented in the defining paper of Thompson (1990).