A New Adaptive Sequential Design for Sampling Rare and Clustered Populations

Designing an efficient large-area survey is a challenge for ecologists. Adaptive sampling designs can be efficient because it ensures survey effort is targeted to subareas of high interest. In two-stage sampling, higher density primary sample units are usually of more interest than lower density primary units when populations are rare and clustered. Two-stage sequential sampling has been suggested as a method for allocating second stage sample effort among primary units. We present a modification called adaptive two-stage sequential sampling. In this method, the adaptive part of the allocation process means the design is more flexible in how much extra effort can be directed to higher-abundance primary units