Bayesian stock assessment: a review and example application using the logistic model

Abstract

. 1998. Bayesian stock assessment: a review and example application using the logistic model. -ICES Journal of Marine Science, 55: 1031-1060.Bayesian statistical methods have recently been combined with conventional methods for fisheries stock assessment (e.g. catch-age analysis) to provide a conceptually elegant approach for providing fishery management advice under uncertainty. Uncertainties in the advice provided can be conveyed using posterior probability distributions (or ''posteriors'') for the potential outcomes of each policy option. Posteriors can be estimated using data (e.g. catch-age data and relative abundance indices) for the fish population of interest and prior probability distributions for population model parameters (e.g. stock-recruit function parameters) based on data from similar fish populations. Despite growing interest, Bayesian methods remain accessible to relatively few. To increase the accessibility of these methods, the conceptual basis for Bayesian statistical estimation is reviewed and set in the context of fisheries stock assessment. The use of Bayesian methods is illustrated by fitting a logistic model to relative abundance indices for Namibian hake (Merlucius capensis and M. paradoxus) and presenting a decision analysis of alternative harvest policy options. Some alternative approaches are outlined for constructing prior and posterior probability distributions and some recent applications in fisheries. Some of the problems that can be encountered while implementing Bayesian methods are also discussed.1998 International Council for the Exploration of the Sea

Stock assessment for the western winter-spring cohort of neon flying squid (<em>Ommastrephes bartramii</em>) using environmentally dependent surplus production models

“…Atypical errors should also be noted in the data. Mis-specification of prior distribution and the choice of an inappropriate likelihood function may result in unreliable posterior distribution for parameters in Bayesian inference (Berger 1994, Adkison and Peterman 1996, McAllister and Kirkwood 1998, Chen et al 2000. In this paper, we used Bayesian inference to estimate the parameters of the four surplus production models, and attempted to interpret the data consistently by using standardized CPUE and modifying the yearly catch from 2003 to 2013.…”

Bayesian state-space models with multiple CPUE data: the case of a mullet fishery

“…The lognormal multiplicative structure used in both process and observation models has been used in this form by other authors as well (McAllister and Kirkwood 1998, Meyer and Millar 1999, Brodziak and Ishmura 2011.…”

“…Regarding the SP model parameters, the required priors consist of the probability distribution for the support capac-ity (K), the maximum intrinsic growth rate (r) and the shape parameter (z). Based on recommendations by McAllister and Kirkwood (1998) and Millar and Meyer (2000), vague priors for all parameters of the model were assumed, as shown in Table 1. A vague prior is a probability distribution carrying very little information, which is selected primarily for structural convenience (e.g.…”

Stock assessment of the red spiny lobster (Panulirus argus) caught in the tropical southwestern Atlantic

“…Informative or non-informative priors can be used here, depending on the availability of information and knowledge on the species and the stock being analyzed, or even on similar species or stocks (McAllister et al, 1994;Punt & Hilborn, 1997;McAllister & Kirkwood, 1998). As no relevant data were found on these parameters in the literature, the priors used for analysis are noninformative or convey little information.…”