Crocker, Mark (2005) Bayesian analysis of stock-recruitment models in fisheries. Masters thesis, Memorial University of Newfoundland.
- Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.
Bayesian approaches to the analysis of population dynamics are becoming more common in some areas of fisheries research. The search for a stock-recruitment relationship is considered a central problem of fish population dynamics and has been explored in many studies. In this study, posterior distributions are estimated for both the Ricker and Beverton-Holt stock-recruitment curves, using the Normal, Log-normal and Poisson distributions, for both the Baltic Areas 22-24 and NAFO subdivision 3Ps cod stocks. Prior distributions were changed and the sensitivity of the results were investigated. The posterior estimates are sensitive to our choice of prior distribution, which can have an important practical effect on the study of stock-recruitment issues in a number of different fisheries. The Gibbs sampler was used to overcome difficulties in calculating the posterior distributions.
|Item Type:||Thesis (Masters)|
|Additional Information:||Bibliography: leaves 86-91.|
|Department(s):||Science, Faculty of > Mathematics and Statistics|
|Library of Congress Subject Heading:||Bayesian statistical decision theory; Fish stock assessment--Statistical methods.|
Actions (login required)