The anticipated variance: a tool for the optimization of forest inventory

This paper gives a non-mathematical review of the concept of anticipated variance which allows to solve entirely the optimisation problem for two-phase two-stage forest inventories with cluster or simple random sampling, in the sense that the anticipated variance is minimised for given costs. The anticipated variance is the average of the design-based variance under a local Poisson-model for the spatial distribution of the trees. The resulting sampling rules have a clear intuitive background and require only simple algebra to be implemented. The required parameters can be estimated from any pre-existing two-phase inventory. An example based on the Swiss National Inventory illustrates the method.