Efficiency evaluation of MEV spatial sampling strategies: a scenario analysis

Authors:
Giovanni Lafratta
Affiliations:
Department of Business, Statistical, Technological and Environmental Sciences (DASTA), "G. d'Annunzio" University, Viale Pindaro 42, 65127 Pescara, Italy
Venue:
Computational Statistics & Data Analysis
Year:
2006

Citing 0
Cited 3

Valid hypothesis testing in face of spatially dependent data using multi-layer perceptrons and sub-sampling techniques

Computational Statistics & Data Analysis
Spatial sampling plans to monitor the 3-D spatial distribution of extremes in soil pollution surveys

Computational Statistics & Data Analysis
Reinforcement learning-based design of sampling policies under cost constraints in Markov random fields: Application to weed map reconstruction

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.03

Visualization

Abstract

The minimum estimation variance (MEV) spatial sampling strategy is compared with some further strategies based on systematic designs and the sample mean. Since in environmental surveys data are usually collected repeatedly in time at sites whose selection is based on practical circumstances only, it seems worth measuring the efficiency of spatial sampling strategies through the expectation of design mean square errors under several superpopulation models assumed about the fixed population generating process. Relating the study to specific superpopulations, MEV efficiencies can be calculated and a quantitative evaluation is made possible by the use of scenario analyses for several sample sizes and different models of spatial drift and correlations. The MEV strategy revealed itself to be the relatively more efficient one under realistic conditions of nonstationary spatial drifts and bounded sample sizes.