Assessing Local Impacts: Progress and Some Problems

Environmental impact assessment is discussed for the case of a single biological species, when observations can be taken at both the affected (Impact) area and a nearby control. A procedure for testing the null hypothesis is described and problems of model uncertainty are discussed. It is argued that no single number, such as the p-value for this test, can adequately summarize the data. Several summaries are needed in order to adequately describe the size of the effect and the strength of the evidence and to allow for model uncertainty. Some suggestions are offered.