Statistical tools for determining appropriate selection of regression models for analysis of environmental fate datasets

BACKGROUND: In the NAFTA regulatory community, a currently consistent methodology used to estimate dissipation times for environmental fate data is not applied. RESULTS: This work demonstrates through a case study that the inappropriate use of pseudo-first-order regression models can result in inaccurate estimates of soil degradation rates, and it proposes some statistical tools that can be used to identify an appropriate statistical model to fit a particular environmental fate dataset. Diagnostic procedures have been proposed to identify the appropriate scale, and statistical testing procedures have been proposed to select the appropriate model within that scale. CONCLUSION: Results from this work demonstrate that, unless the proposed diagnostic and statistical procedures are used, inaccurate estimates of dissipation times may result. (c) 2008 Society of Chemical Industry.