Regulatory Science: Mathematical vs. Statistical Models
DOI:
https://doi.org/10.21423/JRS-V04N04P010Keywords:
statistics, models, prediction, water quality, natural variabilityAbstract
Natural resource companies do not object to environmental regulations that are consistent and support predictability. Consistency and predictability are critical for decision making under conditions of uncertainty. Natural ecosystems are inherently variable across a broad range of temporal and spatial scales; climate change, drought, and societal desires for sustainability make people more aware of this variability. The science used for development and enforcement of environmental regulations has not kept pace with developments in ecological theory and the analytical tools capable of describing, characterizing, classifying, and predicting natural ecosystems as well as distinguishing natural variability from anthropogenic changes.
Because natural resource industries (agriculture, energy, mining) provide the base for all economic and societal activities it is critical that environmental statutes and regulations be regularly updated to use the most technically sound and legally defensible scientific knowledge and tools.
Mathematical models were the tools of choice when environmental statutes and regulations were introduced, perhaps because they were successfully applied to static components of the built environment such as buildings and bridges. While their limitations for highly variable natural ecosystems were accepted then, there is now no benefit to not replacing them with statistical models.
This paper describes limitations in policy and regulatory decision-making based on mathematical models and explains how the appropriate statistical models avoid the subjectivity and rigidity of the former. Changing the basis of determining and justifying policy and environmental regulations is consistent with the concepts of regulatory science applied to human health.
https://doi.org/10.21423/jrs-v04n04p010 (DOI assigned 5/14/2019)
References
[link]. URL http://www.nars.org/
A. Moghissi, S. Straja, B. Love, D. Bride, R. Stough. Innovation in regulatory science: evolution of a new scientific discipline. 16 (2014) 155-165.
A. Moghissi, N. Gurudas, S. Pei, D. McBride, N. Swetnam. Scientific ethics: emphasizing regulatory science requirements. 17 (2015) 61-73.
[link]. URL http://serc.carleton.edu/introgeo/mathstatmodels/index.html
USEPA 1997. The enhanced stream water quality model qual2e and qual2e-uncas: Documentation and user model. Technical Report EPA/600-3-87/007, Environmenal Reseearch Laboratory, US Environmental Protection Agency.
K. Smith, L. Balistrierib, A. Todda, Using biotic ligand models to predict metal toxicity in mineralized systems, Applied Geochemistry 57 (2015) 55–72.
J. McConaghie, A. Matzke. Technical support document: An evaluation to derive statewide copper criteria using the biotic ligand model. Technical report, Oregon Department of Environmental Quality. 2016.
[link]. URL http://www.appl-ecosys.com/publications/censored-chemical-analyses.pdf
F. Harrell Jr.. Regression Modeling Strategies. Springer. 2010.
B. Cade, B. Noon, A gentle introduction to quantile regression for ecologists, Frontiers in Ecology and Environment 1(8) (2003) 412–420.
B. Cade, Estimating equivalence with quantile regression, Ecological Applications 21(1) (2011) 281–289.
B. Everitt, T. Hothorn. An Introduction to Applied Multivariable Analysis With R. Springer. 2011.
P. Mielke Jr., K. Berry. Permutation Methods: A Distance Function Approach, Springer Series in Statistics. Springer. 2001.
J. Bobbin, F. Recknagel . Mining water quality time series for predictive rules of algal blooms by genetic algorithms. In Proc. of the Int. Conference MODSIM 99, 1999.
A. Eckner. A framework for the analysis of unevenly spaced time series data. In development; not yet submitted for publication. 2014.
R. Krzysztofowicz, Bayesian models of forecasted time series, Water Resources Bulletin 21(5) (1985) 805–814.
D. Lettenmaier, Detection of trends in water quality data from records with dependent observations, Water Resources Research 12(5) (1976) 1037–1046.
J. Aitchison. The statistical analysis of compositional data, Monographs on statistics and applied probability. Chapman & Hall. 1986.
[link]. URL http://www.appl-ecosys.com/publications/biota-to-set-wq-standards.pdf
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
By submitting content to the Journal of Regulatory Science (JRS), authors agree to the following terms:
- Authors retain copyright and grant the JRS the right of first publication. Authors retain patent, trademark, and other intellectual property rights (including research data) and grant third parties the right to use, reproduce, and share the article according to the Creative Commons — Attribution-NonCommercial 4.0 International — CC BY-NC 4.0 license agreement. The JRS is an open access journal and, as a result, articles are free to use with proper acknowledgment of the work's authorship and initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process.
- If excerpts from other copyrighted works are included, the author(s) must obtain written permission from the copyright owners and credit the source(s) in the article.
- The publication of the submission has been approved by all co-authors and responsible authorities at the institute or organization where the work has been carried out.
- Copyright has not been breached in seeking publication of the submission.
