Results of Bayesian methods depend on details of implementation: an example of estimating salmon escapement goals

Abstract Bayesian methods have been proposed to estimate optimal escapement goals, using both knowledge about physical determinants of salmon productivity and stock-recruitment data. The Bayesian approach has several advantages over many traditional methods for estimating stock productivity: it allows integration of information from diverse sources and provides a framework for decision-making that takes into account uncertainty reflected in the data. However, results can be critically dependent on details of implementation of this approach. For instance, unintended and unwarranted confidence about stock-recruitment relationships can arise if the range of relationships examined is too narrow, if too few discrete alternatives are considered, or if data are contradictory. This unfounded confidence can result in a suboptimal choice of a spawning escapement goal.

[1]  O. Iribarne,et al.  How good are empirical predictions of natural mortality , 1993 .

[2]  Alan E. Gelfand,et al.  Bayesian statistics without tears: A sampling-resampling perspective , 1992 .

[3]  Richard D. Methot,et al.  Synthetic Estimates of Historical Abundance and Mortality for Northern Anchovy , 1989 .

[4]  Harold J. Geiger,et al.  Escapement goals for sockeye salmon with informative prior probabilities based on habitat considerations , 1991 .

[5]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[6]  B. Fischhoff,et al.  Assessing uncertainty in physical constants , 1986 .

[7]  Adrian E. Raftery,et al.  Benefits of a Bayesian Approach for Synthesizing Multiple Sources of Evidence and Uncertainty Linked , 1993 .

[8]  John G. Pope,et al.  A comparison of the performance of various methods for tuning VPAs using effort data , 1985 .

[9]  Carl J. Walters,et al.  Adaptive Management of Renewable Resources , 1986 .

[10]  R. F. Blackett.  Establishment of Sockeye (Oncorhynchus nerka) and Chinook (O. tshawytscha) Salmon Runs at Frazer Lake, Kodiak Island, Alaska , 1979 .

[11]  Murdoch K. McAllister,et al.  A Bayesian estimation and decision analysis for an age-structured model using biomass survey data , 1994 .

[12]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[13]  J. Koenings,et al.  Density-Dependent, Trophic Level Responses to an Introduced Run of Sockeye Salmon (Oncorhynchus nerka) at Frazer Lake, Kodiak Island, Alaska , 1988 .

[14]  S. Frederick,et al.  Choosing fisheries harvest policies : when does uncertainty matter? , 1995 .

[15]  P. R. Neal,et al.  Catch-Age Analysis with Auxiliary Information , 1985 .

[16]  David A. Fournier,et al.  A General Theory for Analyzing Catch at Age Data , 1982 .

[17]  Stephen M. Fried,et al.  Inseason Forecasting of Bristol Bay, Alaska, Sockeye Salmon (Oncorhynchus nerka) Abundance Using Bayesian Probability Theory , 1988 .

[18]  E. Pikitch,et al.  The predictive power of empirical relationships describing size selectivity, with application to gadoid fish , 1994 .

[19]  Ray Hilborn,et al.  Analysis of contradictory data sources in fish stock assessment , 1993 .

[20]  Laura J. Richards,et al.  Use of contradictory data sources in stock assessments , 1991 .

[21]  C. Walters,et al.  Quantitative Fisheries Stock Assessment , 1992, Springer US.

[22]  Carl J. Walters,et al.  Calculation of Bayes Posterior Probability Distributions for Key Population Parameters , 1994 .