Bayesian Decision Analysis for Fisheries Management
3 credits; Section 001
Term 2, Tuesdays and Thursdays 9-11 am in AERL 320
Prerequisites and Restrictions
Minimal entry requirement: first year undergraduate calculus and reasonably good quantitative skills such as those gained through FISH 504 and FISH 505. Students wishing to take the course should also have good computing skills and be able to use Excel spreadsheets to implement simple time series models, apply Monte Carlo simulation methods and estimate the parameters of non-linear models. The course is limited to 15 participants.
This course explores the use of Bayesian decision analysis as a quantitative technique with which to inform decision makers about the extent to which alternative decision options may enable them to achieve their objectives, taking into account available information and uncertainty over factors that affect the outcomes of interest. Students are to learn about the conceptual framework for Bayesian decision analysis, attitudes to risk and uncertainty, risk averse and other types of utility functions, minimax and maximin regret and other types of decision making criteria, the concept of expected value of perfect information, different approaches to assigning probabilities to alternative hypotheses, including Bayesian statistical methods, different software options for Bayesian decision analysis calculations, approaches to communicating results obtained from Bayesian decision analysis, the roles of decision analysis results in the making of decisions, and the advantages and limitations of Bayesian decision analysis as an approach to facilitate the use of science in resource management and policy decision making. Lectures and demonstrations will be supplemented with practical sessions, using Excel, WinBUGS, Visual Basic software, and HUGIN software, where students are to work on set problems. Fisheries estimation and decision analysis modeling problems will be explored to highlight the generic features of Bayesian decision analysis and place the approach in the context of on-the-ground management decision making situations..
The course grade will be made up of three components: (1) Four written assignments, each counting for 20% of the final grade: The first three assignments will be deal with conceptual and methodological aspects of decision analysis. The fourth assignment will involve the application of Bayesian decision analysis to a problem of the student’s choice; (2) one seminar presentation summarizing the student’s application of a Bayesian decision analysis for 10% of the final grade; and (3) a 10 minute seminar presentation in which the student summarizes a peer-reviewed published article dealing with the application of Bayesian decision analysis, counting for 10% of the final grade
Dr. Murdoch McAllister