Two statistical methods for the detection of environmental thresholds

A nonparametric method and a Bayesian hierarchical modeling method are proposed in this paper for the detection of environmental thresholds. The nonparametric method is based on the reduction of deviance, while the Bayesian method is based on the change in the response variable distribution parameters. Both methods are tested using macroinvertebrate composition data from a mesocosm experiment conducted in the Everglades wetlands, where phosphorus is the limiting nutrient. Using the percent of phosphorus tolerant species and a dissimilarity index as the response variables, both methods resulted in a similar and well-defined TP concentration threshold, with a distribution function that can be used to determine the probability of exceeding the threshold.