Accounting for correlated observations in an age-based state-space stock assessment model

Research output: Contribution to journalJournal articleResearchpeer-review

367 Downloads (Pure)

Abstract

Fish stock assessment models often relyon size- or age-specific observations that are assumed to be statistically independent of each other. In reality,
these observations are not raw observations, but rather they are estimates from a catch-standardization model or similar summary statistics based
on observations from many fishing hauls and subsamples of the size and age composition of the data. Although aggregation mitigates the strong
intra-haul correlation between sizes/ages that is usually found in haul-by-haul data, violations of the independence assumption can have a large
impact on the results and specifically on reported confidence bounds. A state-space assessment model that allows for correlations between age
groups within years in the observation model for catches and surveys is presented and applied to data on several North Sea fish stocks using various
correlation structures. In all cases the independence assumption is rejected. Less fluctuating estimates of the fishing mortality is obtained due to a
reduced process error. The improved model does not suffer from correlated residuals unlike the independent model, and the variance of forecasts is
decreased.
Original languageEnglish
JournalICES Journal of Marine Science
Volume73
Issue number7
Pages (from-to)1788-1797
ISSN1054-3139
DOIs
Publication statusPublished - 2016

Cite this

@article{03186ac4a4184d36baa45f9c952e6d17,
title = "Accounting for correlated observations in an age-based state-space stock assessment model",
abstract = "Fish stock assessment models often relyon size- or age-specific observations that are assumed to be statistically independent of each other. In reality,these observations are not raw observations, but rather they are estimates from a catch-standardization model or similar summary statistics basedon observations from many fishing hauls and subsamples of the size and age composition of the data. Although aggregation mitigates the strongintra-haul correlation between sizes/ages that is usually found in haul-by-haul data, violations of the independence assumption can have a largeimpact on the results and specifically on reported confidence bounds. A state-space assessment model that allows for correlations between agegroups within years in the observation model for catches and surveys is presented and applied to data on several North Sea fish stocks using variouscorrelation structures. In all cases the independence assumption is rejected. Less fluctuating estimates of the fishing mortality is obtained due to areduced process error. The improved model does not suffer from correlated residuals unlike the independent model, and the variance of forecasts isdecreased.",
author = "Berg, {Casper Willestofte} and Anders Nielsen",
year = "2016",
doi = "10.1093/icesjms/fsw046",
language = "English",
volume = "73",
pages = "1788--1797",
journal = "I C E S Journal of Marine Science",
issn = "1054-3139",
publisher = "Oxford University Press",
number = "7",

}

Accounting for correlated observations in an age-based state-space stock assessment model. / Berg, Casper Willestofte; Nielsen, Anders.

In: ICES Journal of Marine Science, Vol. 73, No. 7, 2016, p. 1788-1797.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Accounting for correlated observations in an age-based state-space stock assessment model

AU - Berg, Casper Willestofte

AU - Nielsen, Anders

PY - 2016

Y1 - 2016

N2 - Fish stock assessment models often relyon size- or age-specific observations that are assumed to be statistically independent of each other. In reality,these observations are not raw observations, but rather they are estimates from a catch-standardization model or similar summary statistics basedon observations from many fishing hauls and subsamples of the size and age composition of the data. Although aggregation mitigates the strongintra-haul correlation between sizes/ages that is usually found in haul-by-haul data, violations of the independence assumption can have a largeimpact on the results and specifically on reported confidence bounds. A state-space assessment model that allows for correlations between agegroups within years in the observation model for catches and surveys is presented and applied to data on several North Sea fish stocks using variouscorrelation structures. In all cases the independence assumption is rejected. Less fluctuating estimates of the fishing mortality is obtained due to areduced process error. The improved model does not suffer from correlated residuals unlike the independent model, and the variance of forecasts isdecreased.

AB - Fish stock assessment models often relyon size- or age-specific observations that are assumed to be statistically independent of each other. In reality,these observations are not raw observations, but rather they are estimates from a catch-standardization model or similar summary statistics basedon observations from many fishing hauls and subsamples of the size and age composition of the data. Although aggregation mitigates the strongintra-haul correlation between sizes/ages that is usually found in haul-by-haul data, violations of the independence assumption can have a largeimpact on the results and specifically on reported confidence bounds. A state-space assessment model that allows for correlations between agegroups within years in the observation model for catches and surveys is presented and applied to data on several North Sea fish stocks using variouscorrelation structures. In all cases the independence assumption is rejected. Less fluctuating estimates of the fishing mortality is obtained due to areduced process error. The improved model does not suffer from correlated residuals unlike the independent model, and the variance of forecasts isdecreased.

U2 - 10.1093/icesjms/fsw046

DO - 10.1093/icesjms/fsw046

M3 - Journal article

VL - 73

SP - 1788

EP - 1797

JO - I C E S Journal of Marine Science

JF - I C E S Journal of Marine Science

SN - 1054-3139

IS - 7

ER -