A bootstrap method for estimating bias and variance in statistical fisheries modelling frameworks using highly disparate datasets

Statistical models of marine ecosystems use a variety of data sources to estimate parameters using composite or weighted likelihood functions with associated weighting issues and questions on how to obtain variance estimates. Regardless of the method used to obtain point estimates, a method is required for variance estimation. A bootstrap technique is introduced for the evaluation of uncertainty in such models, taking into account inherent spatial and temporal correlations in the datasets, which are commonly transferred as assumptions from a likelihood estimation procedure into Hessian-based variance estimation procedures. The technique is demonstrated on a real dataset and the effects of the number of bootstrap samples on estimation bias and variance estimates are studied. Although the modelling framework and bootstrap method can be applied to multispecies and multiarea models, for clarity the case study described is of a single-species and single-area model.

[1]  Ransom A. Myers,et al.  Statistical analysis of catch-at-age data with correlated errors , 1995 .

[2]  Robin Cook,et al.  Estimating uncertainty in fish stock assessment and forecasting , 2001 .

[3]  Gunnar Stefánsson,et al.  Statistical evaluation and modelling of the stomach contents of Icelandic cod (Gadus morhua) , 1997 .

[4]  Gunnar Stefansson,et al.  A simple implementation of the statistical modelling framework Gadget for cod in Icelandic waters , 2007 .

[5]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

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

[7]  Höskuldur Björnsson,et al.  Assessment of golden redfish (Sebastes marinus L) in Icelandic waters , 2003 .

[8]  C. F. Wu,et al.  Resampling Inference with Complex Survey Data , 1988 .

[9]  E. Knut,et al.  Paris Meeting of the International Council for the Exploration of the Sea , 1923, Nature.

[10]  K.,et al.  NOT TO BE CITED WITHOUT PRIOR REFERENCE TO THE AUTHORS International Council for the Exploration of the Sea , 2003 .

[11]  Stephen J. Smith.  Bootstrap confidence limits for groundfish trawl survey estimates of mean abundance , 1997 .

[12]  R. Hilborn,et al.  Fisheries stock assessment and decision analysis: the Bayesian approach , 1997, Reviews in Fish Biology and Fisheries.

[13]  Birgir Hrafnkelsson,et al.  A model for categorical length data from groundfish surveys , 2004 .

[14]  Pierre Petitgas,et al.  Geostatistics in fisheries survey design and stock assessment: models, variances and applications , 2001 .

[15]  Russell B. Millar.  Reference priors for Bayesian fisheries models , 2002 .

[16]  FrancisR.I.C. Chris,et al.  Data weighting in statistical fisheries stock assessment models , 2011 .

[17]  Olena Babak,et al.  Estimation of the Length Distribution of Marine Populations in the Gaussian-multinomial Setting using the Method of Moments , 2007 .

[18]  R. Sitter.  A resampling procedure for complex survey data , 1992 .

[19]  P J McCarthy,et al.  The bootstrap and finite population sampling. , 1985, Vital and health statistics. Series 2, Data evaluation and methods research.

[20]  S. Gross.  MEDIAN ESTIMATION IN SAMPLE SURVEYS , 2002 .

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

[22]  Gunnar Stefansson,et al.  ISSUES IN MULTISPECIES MODELS , 2003 .

[24]  Feifang Hu,et al.  The weighted likelihood , 2002 .

[25]  André E. Punt,et al.  Measuring uncertainty in fisheries stock assessment: the delta method, bootstrap, and MCMC , 2013 .

[26]  S. Lahiri.  Theoretical comparisons of block bootstrap methods , 1999 .

[27]  Ransom A. Myers,et al.  Density-Dependent Juvenile Mortality in Marine Demersal Fish , 1993 .

[28]  Gunnar Stefánsson,et al.  Comparing Different Information Sources in a Multispecies Context , 1998 .

[29]  André E. Punt,et al.  A review of integrated analysis in fisheries stock assessment , 2013 .

[30]  Terrance J. Quinn,et al.  Fishery Stock Assessment Models , 1998 .

[31]  R. Jennrich.  Asymptotic Properties of Non-Linear Least Squares Estimators , 1969 .

[32]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[33]  John Sibert,et al.  AD Model Builder: using automatic differentiation for statistical inference of highly parameterized complex nonlinear models , 2012, Optim. Methods Softw..

[34]  John Vandermeer,et al.  Choosing category size in a stage projection matrix , 2004, Oecologia.

[35]  ' RICHARD.METHOT,et al.  Synthetic Estimates of Historical Abundance and Mortality for Northern Anchovy , 2022 .

[36]  Darren J. Wilkinson,et al.  Parallel Bayesian Computation , 2005 .

[37]  Gunnar Stefansson,et al.  On the use of tagging data in statistical multispecies multi-area models of marine populations , 2008 .

[38]  Yong Chen,et al.  Impacts of outliers and mis-specification of priors on Bayesian fisheries-stock assessment , 2000 .

[39]  Gunnar Stefansson,et al.  Points of view: A framework for multispecies modelling of Arcto-boreal systems , 1998, Reviews in Fish Biology and Fisheries.

[40]  D. Howell,et al.  Modelling multi-species interactions in the Barents Sea ecosystem with special emphasis on minke whales and their interactions with cod, herring and capelin , 2009 .

[41]  Michael Pennington,et al.  Assessing the Effect of Intra-Haul Correlation and Variable Density on Estimates of Population Characteristics from Marine Surveys , 1994 .

[42]  André E. Punt,et al.  Comparison of Uncertainty Estimates in the Short Term Using Real Data , 2000 .

[43]  A random effects population dynamics model based on proportions-at-age and removal data for estimating total mortality , 2012 .

[44]  D. Doak,et al.  Incorporating diverse data and realistic complexity into demographic estimation procedures for sea otters. , 2006, Ecological applications : a publication of the Ecological Society of America.

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

[46]  James N. Ianelli,et al.  Statistical Issues in Fisheries' Stock Assessments * , 2002 .

[47]  Gunnar Stefánsson,et al.  Icelandic Groundfish Survey Data Used to Improve Precision in Stock Assessments , 1989 .

[48]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[49]  P. McCullagh,et al.  Generalized Linear Models , 1972, Predictive Analytics.

[50]  Changbao Wu,et al.  Asymptotic Theory of Nonlinear Least Squares Estimation , 1981 .

[51]  Ian G. Taylor,et al.  A comparison of stock assessment uncertainty estimates using maximum likelihood and Bayesian methods implemented with the same model framework , 2013 .

[52]  G. Oehlert.  A note on the delta method , 1992 .

[53]  Vasily Demyanov,et al.  Improving ecological impact assessment by statistical data synthesis using process‐based models , 2006 .

[54]  Gunnar Stefansson,et al.  A Case Study of Sampling Strategies for Estimating the Length Composition of Commercial Catches: The Sri Lankan Shrimp Trawl Fishery , 2011 .

[55]  Kristin Helle,et al.  Survey design considerations for estimating the length composition of the commercial catch of some deep-water species in the northeast Atlantic , 2004 .

[56]  Debashis Kushary,et al.  Bootstrap Methods and Their Application , 2000, Technometrics.