How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters?
We present a Bayesian approach of a Ricker stock-recruitment (S/R) analysis accounting for measurement errors on S/R data. We assess the sensitivity of posterior inferences to (i) the choice of Ricker model parameterizations, with special regards to management-related ones, and (ii) prior parameter...
Published in: | Canadian Journal of Fisheries and Aquatic Sciences |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Canadian Science Publishing
2001
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1139/f01-167 http://www.nrcresearchpress.com/doi/pdf/10.1139/f01-167 |
id |
crcansciencepubl:10.1139/f01-167 |
---|---|
record_format |
openpolar |
spelling |
crcansciencepubl:10.1139/f01-167 2023-12-17T10:27:26+01:00 How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? Rivot, E Prévost, E Parent, E 2001 http://dx.doi.org/10.1139/f01-167 http://www.nrcresearchpress.com/doi/pdf/10.1139/f01-167 en eng Canadian Science Publishing http://www.nrcresearchpress.com/page/about/CorporateTextAndDataMining Canadian Journal of Fisheries and Aquatic Sciences volume 58, issue 11, page 2284-2297 ISSN 0706-652X 1205-7533 Aquatic Science Ecology, Evolution, Behavior and Systematics journal-article 2001 crcansciencepubl https://doi.org/10.1139/f01-167 2023-11-19T13:38:49Z We present a Bayesian approach of a Ricker stock-recruitment (S/R) analysis accounting for measurement errors on S/R data. We assess the sensitivity of posterior inferences to (i) the choice of Ricker model parameterizations, with special regards to management-related ones, and (ii) prior parameter distributions. Closed forms for Ricker parameter posterior distributions exist given S/R data known without error. We use this property to develop a procedure based on the RaoBlackwell formula. This procedure achieves integration of measurement errors by averaging these closed forms over possible S/R data sets sampled from distributions derived from a stochastic model relating field data to the S and R variables. High-quality Bayesian estimates are obtained. The analysis of the influence of different parameterizations and of the priors is made easier. We illustrate our methodological approach by a case study of Atlantic salmon (Salmo salar). Posterior distributions for S and R are computed from a markrecapture stochastic model. Ignoring measurement errors underestimates parameter uncertainty and overestimates both stock productivity and density dependence. We warn against using management-related parameterizations because it makes the strong prior assumption of long-term sustainability of stocks. Posterior inferences are sensitive to the choice of prior. The use of informative priors as a remedy is discussed. Article in Journal/Newspaper Atlantic salmon Salmo salar Canadian Science Publishing (via Crossref) Canadian Journal of Fisheries and Aquatic Sciences 58 11 2284 2297 |
institution |
Open Polar |
collection |
Canadian Science Publishing (via Crossref) |
op_collection_id |
crcansciencepubl |
language |
English |
topic |
Aquatic Science Ecology, Evolution, Behavior and Systematics |
spellingShingle |
Aquatic Science Ecology, Evolution, Behavior and Systematics Rivot, E Prévost, E Parent, E How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? |
topic_facet |
Aquatic Science Ecology, Evolution, Behavior and Systematics |
description |
We present a Bayesian approach of a Ricker stock-recruitment (S/R) analysis accounting for measurement errors on S/R data. We assess the sensitivity of posterior inferences to (i) the choice of Ricker model parameterizations, with special regards to management-related ones, and (ii) prior parameter distributions. Closed forms for Ricker parameter posterior distributions exist given S/R data known without error. We use this property to develop a procedure based on the RaoBlackwell formula. This procedure achieves integration of measurement errors by averaging these closed forms over possible S/R data sets sampled from distributions derived from a stochastic model relating field data to the S and R variables. High-quality Bayesian estimates are obtained. The analysis of the influence of different parameterizations and of the priors is made easier. We illustrate our methodological approach by a case study of Atlantic salmon (Salmo salar). Posterior distributions for S and R are computed from a markrecapture stochastic model. Ignoring measurement errors underestimates parameter uncertainty and overestimates both stock productivity and density dependence. We warn against using management-related parameterizations because it makes the strong prior assumption of long-term sustainability of stocks. Posterior inferences are sensitive to the choice of prior. The use of informative priors as a remedy is discussed. |
format |
Article in Journal/Newspaper |
author |
Rivot, E Prévost, E Parent, E |
author_facet |
Rivot, E Prévost, E Parent, E |
author_sort |
Rivot, E |
title |
How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? |
title_short |
How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? |
title_full |
How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? |
title_fullStr |
How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? |
title_full_unstemmed |
How robust are Bayesian posterior inferences based on a Ricker model with regards to measurement errors and prior assumptions about parameters? |
title_sort |
how robust are bayesian posterior inferences based on a ricker model with regards to measurement errors and prior assumptions about parameters? |
publisher |
Canadian Science Publishing |
publishDate |
2001 |
url |
http://dx.doi.org/10.1139/f01-167 http://www.nrcresearchpress.com/doi/pdf/10.1139/f01-167 |
genre |
Atlantic salmon Salmo salar |
genre_facet |
Atlantic salmon Salmo salar |
op_source |
Canadian Journal of Fisheries and Aquatic Sciences volume 58, issue 11, page 2284-2297 ISSN 0706-652X 1205-7533 |
op_rights |
http://www.nrcresearchpress.com/page/about/CorporateTextAndDataMining |
op_doi |
https://doi.org/10.1139/f01-167 |
container_title |
Canadian Journal of Fisheries and Aquatic Sciences |
container_volume |
58 |
container_issue |
11 |
container_start_page |
2284 |
op_container_end_page |
2297 |
_version_ |
1785579308157239296 |