Bootstrap confidence intervals for adaptive cluster sampling

Consider a collection of spatially clustered objects where the clusters are geographically rare. Of interest is estimation of the total number of obje cts on the site from a sample of plots of equal size. Under these spatial c onditions, adaptive cluster sampling of plots is generally useful in improv ing efficiency in estimation over simple random sampling without replacemen t (SRSWOR). In adaptive cluster sampling, when a sampled plot meets some pr edefined condition, neighboring plots are added to the sample. When populat ions are rare and clustered, the usual unbiased estimators based on small s amples are often highly skewed and discrete in distribution. Thus, confiden ce intervals based on asymptotic normal theory may not be appropriate. We i nvestigated several nonparametric bootstrap methods for constructing confid ence intervals under adaptive cluster sampling. To perform bootstrapping, w e transformed the initial sample in order to include the information from t he adaptive portion of the sample yet maintain a fixed sample size. In gene ral, coverages of bootstrap percentile methods were closer to nominal cover age than the normal approximation.