Ecological Grouping of Survey Sites When Sampling Artefacts are Present
提出一种基于模型的聚类方法，在生态调查数据存在采样伪迹时，仍能对调查地点进行合理分组，用于植被类型分类和鱼类群落分析。
Summary Grouping sites on the basis of their biological information is a common goal in ecology that has scientific and management applications. Two applications are studied in this work: classifying vegetation types for management units and predicting these units into unsampled space, and finding assemblages of fish and investigating how the presence of these assemblages varies with covariates. Data that are used to find the groupings often have extraneous sources of variation, such as those related to sampling, which are often ignored but should be accounted for when finding the groupings. In ecological studies, this is increasingly common as data sets are now being combined from many smaller survey efforts. We show, through a model-based clustering method, how the groupings can be obtained, while accounting for sampling artefacts.