Journal
ECOLOGICAL INDICATORS
Volume 38, Issue -, Pages 192-197Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.ecolind.2013.11.008
Keywords
Bayesian statistics; Change point; environmental standards; Everglades; simulation
Categories
Funding
- University of Toledo through University Research Council
Ask authors/readers for more resources
Many statistical models are available for detecting and quantifying ecological thresholds. The proper model can be selected through the comparison of the goodness-of-fit of multiple alternative models to the same data. In the context of selecting the appropriate threshold model, three sources of information should be used: patterns in model residuals, model predicted versus observed, and the posterior change point distributions. Applying alternative models to several ecological metrics measured along a total phosphorus gradient from a mesocosm experiment conducted in the Everglades, I conclude that changes in these metrics along the gradient are more likely to be gradual. The previously found strong threshold response is likely a result of the use of the step function model. (C) 2013 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available