Bayesian estimator for the total number of distinct species when quadrat sampling is used
Abstract:A Bayesian estimator for the total number of distinct species present in the region of investigation is constructed when the quadrat sampling procedure is used to collect a sample of species. The estimator is based on a model similar to that used by Mingoti and Meeden, and uses as a special case the zero truncated negative binomial distribution as a prior distribution for the true number S of distinct species in the region. Confidence intervals are also obtained. Simple comparisons with the first-order jackknife estimator and the empirical Bayesian estimator are performed.
Document Type: Research Article
Publication date: May 1, 1999