Do statistical inferences allowing three alternative decisions give better feedback for environmentally precautionary decision-making?

Environmental policies and guidelines often specify standards for environmental indicators. The first part of this paper argues that, where compliance with these standards is assessed with the help of statistical inference, an inference employing a three-alternatives decision rule can provide more sensible feedback to environmental managers for precautionary decision-making. The second part of the paper shows how a three-alternatives statistical inference about compliance with a percentile standard might be applied to a small number of observations using a non-parametric binomial interval. This interval expression of uncertainty results in the sample size requirements for various percentile ranks becoming explicit.     

A statistical study of the quality of surface water intended for human consumption near Valencia (Spain)

Water quality in the European Union is subject to legislation through directives that are applicable in all Member States. The directives specify a set of physical and chemical parameters that should be regularly controlled using a network of sampling points, with sampling based on the intended use of the water. This paper presents the results of a statistical comparison of the quality of water intended for human consumption at two different locations (the Canal de Benagéber and the Canal Júcar-Turia) near the town of Valencia (Spain). These are currently the only canals that could supply Valencia and other nearby towns with drinking water. The parameters considered in this paper are the ones specified in the European directives for determining the quality of water intended for human consumption. These directives specify that the 95th percentile of the distribution of each parameter should be used to assess water quality, so accurate estimation of these percentiles was essential in this paper. We found statistically significant differences among locations in chlorides, sulfates, temperature, coloration, and manganese, but the results varied depending on the statistical tests that we used; parametric methods gave better results than nonparametric methods.