Designing sampling plans to capture rare objects |
| |
Authors: | Hongmei Zhang |
| |
Institution: | Department of Epidemiology and Biostatistics, University of South Carolina, Columbia, SC 29208, USA |
| |
Abstract: | This article focuses on two‐phase sampling designs for a population with unknown number of rare objects. The first phase is used to estimate the number of rare or potentially rare objects in a population, and the second phase to design sampling plans to capture a certain number or a certain proportion of such type of objects. A hypergeometric‐binomial model is applied to infer the number of rare or potentially rare objects and Monte Carlo simulation based approaches are developed to calculate needed sample sizes. Simulations and real data applications are discussed. The Canadian Journal of Statistics 37: 417–434; 2009 © 2009 Statistical Society of Canada |
| |
Keywords: | Bayesian hierarchical model hypergeometric‐binomial model Markov Chain Monte Carlo (MCMC) rare categories species problem MSC 2000: Primary— Bayesian inference (62F15) secondary— Point estimation (62F10) |
|
|