Comparison of classical vs. inverse sampling for estimating plant cover using Monte Carlo simulations

摘要

Inverse and classical point techniques for estimating percent cover of rare species are considered. A Monte Carlo simulations is used to study the statistical properties of these estimators as influenced by the spatial distribution and association of individual species and to examine the effect of an error in estimating percent cover for the purpose of determining sample sizes. In each case considered, the performance of inverse sampling is comparable with or better than the classical tehcnique. This improvement is due to the fact that inverse sampling fixes the number of hits required to achieve a specified bound on the error of estimation insted of fixing the sample size as with the classical technique.