Development of a stochastic bioeconomic model for the red octopus fishery on the Yucatan Peninsula: Implications for management

Although much effort has been dedicated to the management of the red octopus fishery on the Yucatan Peninsula (Mexico), managers have yet to incorporate economic aspects to ensure sustainable and profitable exploitation of this fishery resource. We developed a bioeconomic model that incorporated the uncertainty for the r and K parameters. We fit 3 models (Schaefer, Fox, and Pella–Tomlinson) to abundance index survey data and used the Akaike information criterion for model selection. The best fit corresponded to the Schaefer model. We built deterministic and stochastic versions of the Gordon–Schaefer model. Economic data (costs and prices) were determined from inter[1]views with fishermen. To estimate the posterior distributions of parameters and indicators, we used Bayesian methods with Markov chain Monte Carlo (MCMC) simulations. The deterministic results suggested that the maximum sustainable income was Mex$851.70 million, with a fishing effort of 3,650 fishing boats, while the maximum sustainable profit was $390.8 million, with a fishing effort of 2,472 fishing boats. The equilibrium point corresponded to an effort of 4,945 fishing boats. Regarding the stochastic model, the MCMC simulation results suggest that the maximum sustainable income distribution was not normal; its average was $856.1 million (SE 1.8) and the most likely value was $849.50 million. The most likely fishing effort at equilibrium was 4,970 fishing boats. Our results suggest the fishery could be operating close to the economic equilibrium point; if this is the case, fishing effort must decrease in order for annual profit to increase. Our approach will help make periodical re-evaluations of the fishery and establish management strategies to ensure the profitable and sustainable exploitation of the red octopus on the Yucatan Peninsula.

Markov Chain Monte Carlo in Practice

Markov chain Monte Carlo (MCMC) is an essential set of tools for estimating features of probability distributions commonly encountered in modern applications. For MCMC simulation to produce reliable outcomes, it needs to generate observations representative of the target distribution, and it must be long enough so that the errors of Monte Carlo estimates are small. We review methods for assessing the reliability of the simulation effort, with an emphasis on those most useful in practically relevant settings. Both strengths and weaknesses of these methods are discussed. The methods are illustrated in several examples and in a detailed case study. Expected final online publication date for the Annual Review of Statistics, Volume 9 is March 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Bayesian Hetero-Elasticnet (A Gibbs Sampler Approach)

Combined heteroscedasticity and multicollinearity as dual non-spherical disturbances were experimented asymptotically. A Gibbs Sampler technique was used to investigate the asymptotic properties of hetero-elasticnet estimator with mean squares error (MSE) and bias as performance metrics. The seed was set to 12345; is set at ; Xs variables were generated as follow: the design matrix was generated from the multivariate normal distribution with mean > 0 and variance . and are truncated with Harvey (1976) heteroscedastic error structure; are collinear covariate with pairwise correlation between 0.6 and 0.9, the sample sizes were 25, 100 and 1000. The number of replications of the experiment was set at 10,000 with burn-in of 1000 which specified the draws that were discarded to remove the effects of the initial values. The thinning was set at 5 to ensure the removal of the effects of autocorrelation in the MCMC simulation. The study found that there is consistency of estimator asymptotically as the sample sizes increases from 25 to 50 so also to 1000, the larger sample size depicted least bias. The estimator exhibited efficiency asymptotically as larger sample sizes depicted least mean squares error. The study therefore recommended Bayesian hetero-elasticnet when data exhibit both heteroscedasticity and multicollinearity. Keywords: Elasticnet; Bayesian Inference and Gibbs sampler

A Bayesian Approach to Measurement of Backtest Overfitting

Quantitative investment strategies are often selected from a broad class of candidate models estimated and tested on historical data. Standard statistical techniques to prevent model overfitting such as out-sample backtesting turn out to be unreliable in situations when the selection is based on results of too many models tested on the holdout sample. There is an ongoing discussion of how to estimate the probability of backtest overfitting and adjust the expected performance indicators such as the Sharpe ratio in order to reflect properly the effect of multiple testing. We propose a consistent Bayesian approach that yields the desired robust estimates on the basis of a Markov chain Monte Carlo (MCMC) simulation. The approach is tested on a class of technical trading strategies where a seemingly profitable strategy can be selected in the naïve approach.

Bayesian Analysis of Two-Parameter Exponentiated Log-logistic Distribution

In this paper, the parameters of the two-parameter exponentiated log-logistic distribution based on a complete sample are estimated using the Markov chain Monte Carlo (MCMC) method. In order to perform full Bayesian analysis of the two-parameter exponentiated log-logistic distribution, the procedures are developed using the MCMC simulation method in Open BUGS, established software. The researcher has obtained the Bayes estimates of the parameters and their probability intervals are presented. The researcher has also discussed the estimation of the reliability function. For illustration under independent gamma priors, the real data set is considered.