OUTLIER-RESISTANT ESTIMATORS FOR POISSON SAMPLING - A NOTE

Poisson (3P) sampling is a commonly used method for generating estimat es of timber volume. The usual estimator employed is the adjusted esti mator, (Y) over cap(a). The efficiency of this estimator can be greatl y influenced by the presence of outliers. We formalize such a realisti c situation for high-value timber estimation for which (Y) over cap(a) is inefficient. Here, y(i) = beta x(i) for all but a few units in a p opulation for which y(i) is large and x(i) very small. This situation can occur when estimating the net volume of high-value standing timber , such as that found in the Pacific Northwest region of the United Sta tes. A generalized regression estimator and an approximate Srivastava estimator are not affected by such data points. Simulations on a small population illustrate these ideas.