A great deal of attention has been paid to the selection of nature reserves. These are important from a conservation viewpoint but, for long-term evaluations, it is important to monitor ecosystems. The need for long-term monitoring plots has been recognized for some time in forest ecology. Of the natural ecosystems, forests are some of the most difficult to monitor because of the time-scales involved in the life-spans of the dominant organisms (100→1000 years). The selection of long-term forest ecosystem monitoring plots is a critical process involving decisions that need to remain valid for many years. Traditional sampling theory suggests that some form of systematic or random sampling may be appropriate, but this is usually inappropriate for the selection of ecosystem monitoring plots. Instead, the selection of plots more closely resembles some of the procedures that are used in the selection of nature reserves. In Switzerland, a monitoring programme has been established which uses a number of criteria for the selection of sites. These include site homogeneity, the abundance and sensitivity of the plant communities to change and the presence of pre-existing data series or monitoring equipment. In addition, the human factor is incorporated by selecting sites from throughout the country, with the willingness of the local forest managers to help with the project being an important factor influencing the final choice of plots. In contrast to most inventories, statistical representativeness is not a requirement for the programme, as the plots are treated as a series of case studies.