作者: Lorenzo Fattorini , Piermaria Corona , Gherardo Chirici , Maria Chiara Pagliarella
DOI: 10.1002/ENV.2332
关键词: Operations research 、 Horvitz–Thompson estimator 、 Grid 、 Estimator 、 Computer science 、 Land use 、 Estimation 、 Variable (computer science) 、 Sampling (statistics) 、 Statistics 、 Land cover
摘要: The purpose of this paper is to compare some spatial strategies for sampling polygons onto a grid partitioning study area. Most the schemes considered in are aimed at avoiding selection neighboring polygons. When one or more auxiliary variables similar well correlated with values survey variable, information adopted estimation level by means difference regression estimators, design level, using determine inclusion probabilities. Applications large-scale forest inventories, land use estimation, and cover discussed. A simulation performed terms bias (if present), accuracy, accuracy estimation. designed mimic inventories starting from real situations. An application plan future surveys Italy reported. Copyright © 2015 John Wiley & Sons, Ltd.