Optimal sampling designs for dependent spatial units
Roberto Benedetti, Daniela Palma · Environmetrics · 1995
Abstract A geographical domain is partitioned into a set, with cardinalityN, of areal units (i.e. census tracts), each of them having an attribute variablez.Observations are often to be recorded for a subsetSof areal units whose cardinality isn.Under the hypothesis of dependence of the underlying data generating processZ, the following questions are considered: which is the best linear unbiased estimator (BLUE) of the mean of the processZ, and which is the subsetSthat minimizes the variance of this estimator? A weighted average estimator is used and the performances of some combinatorial optimization algorithms are tested to solve this problem. The simulated annealing algorithm is shown to be a suitable solution even when dealing with large data sets. Moreover, numerical comparisons are made between sampling designs obtained by using simulated annealing and the classical simple random and systematic sampling criteria.