|
Companies:
|
U.S. Environmental Protection Agency, Office of the Science Advisor and Department of Statistics, University of British Columbia and Neptune & Company, Inc. and Probability, Statistics, & Information and MacStat Consulting, Ltd. and University of Michigan
|
|
Abstract:
|
Environmental statistics is essential to protecting human health and the natural environment. Statistical verbiage and references to methodology frequently appear in policy and guidance documents, as well as rules and regulations, suggesting or even mandating specific, and sometimes inappropriate, statistical methods. Method specificity is motivated and constrained by the requirement a non-statistician have access to simple software packages that produce results automatically. This conflicts with the fundamental paradigm of statistical science that rules out such uncritical, mechanical use of methods, often driven by flow charts. Instead, defensible conclusions often require context-specific analyses to support decision-making based on a wide variety of data and designs for data collection. The field of statistics continues to evolve, and discourse on the interface of policy, regulation, and statistics is key to addressing the complex environmental issues we face. This panel brings together individuals with different experiences and perspectives to introduce fundamental issues, generate discussion, and motivate future participation.
|
