Modeling shark bycatch: The zero-inflated negative binomial regression model with smoothing

Mihoko Minami, C. E. Lennert-Cody, W. Gao, M. Román-Verdesoto

Research output: Contribution to journalArticle

133 Citations (Scopus)

Abstract

The zero-inflated negative binomial (ZINB) regression model with smoothing is introduced for modeling count data with many zero-valued observations, and its use is illustrated with shark bycatch data from the eastern Pacific Ocean tuna purse-seine fishery for 1994-2004. Based on the generalized information criterion, the ZINB regression model provided a better fit to the data than either Poisson, negative binomial or zero-inflated Poisson regression models. To demonstrate the utility of the ZINB regression model for the standardization of catch data, standardized temporal trends in bycatch rates estimated with the ZINB regression model are computed and compared to those obtained from fits of the other three types of models to the same data. With the exception of the negative binomial, estimated temporal trends were more similar among models than would have been inferred from an analysis of model fit. Comparison of trends among models suggests that the negative binomial regression model may overestimate model coefficients when fitted to data with many zero-valued observations.

Original languageEnglish
Pages (from-to)210-221
Number of pages12
JournalFisheries Research
Volume84
Issue number2
DOIs
Publication statusPublished - 2007 Apr
Externally publishedYes

Fingerprint

bycatch
shark
sharks
smoothing
modeling
catch statistics
tuna
standardization
Pacific Ocean
fishery
fisheries

Keywords

  • CPUE
  • EM algorithm
  • GAM
  • GLM
  • Negative binomial
  • Shark
  • Spline smoothing
  • Zero-inflated

ASJC Scopus subject areas

  • Aquatic Science

Cite this

Modeling shark bycatch : The zero-inflated negative binomial regression model with smoothing. / Minami, Mihoko; Lennert-Cody, C. E.; Gao, W.; Román-Verdesoto, M.

In: Fisheries Research, Vol. 84, No. 2, 04.2007, p. 210-221.

Research output: Contribution to journalArticle

Minami, Mihoko ; Lennert-Cody, C. E. ; Gao, W. ; Román-Verdesoto, M. / Modeling shark bycatch : The zero-inflated negative binomial regression model with smoothing. In: Fisheries Research. 2007 ; Vol. 84, No. 2. pp. 210-221.
@article{029bcda1a9754c30b9e80acfbbf89f36,
title = "Modeling shark bycatch: The zero-inflated negative binomial regression model with smoothing",
abstract = "The zero-inflated negative binomial (ZINB) regression model with smoothing is introduced for modeling count data with many zero-valued observations, and its use is illustrated with shark bycatch data from the eastern Pacific Ocean tuna purse-seine fishery for 1994-2004. Based on the generalized information criterion, the ZINB regression model provided a better fit to the data than either Poisson, negative binomial or zero-inflated Poisson regression models. To demonstrate the utility of the ZINB regression model for the standardization of catch data, standardized temporal trends in bycatch rates estimated with the ZINB regression model are computed and compared to those obtained from fits of the other three types of models to the same data. With the exception of the negative binomial, estimated temporal trends were more similar among models than would have been inferred from an analysis of model fit. Comparison of trends among models suggests that the negative binomial regression model may overestimate model coefficients when fitted to data with many zero-valued observations.",
keywords = "CPUE, EM algorithm, GAM, GLM, Negative binomial, Shark, Spline smoothing, Zero-inflated",
author = "Mihoko Minami and Lennert-Cody, {C. E.} and W. Gao and M. Rom{\'a}n-Verdesoto",
year = "2007",
month = "4",
doi = "10.1016/j.fishres.2006.10.019",
language = "English",
volume = "84",
pages = "210--221",
journal = "Fisheries Research",
issn = "0165-7836",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Modeling shark bycatch

T2 - The zero-inflated negative binomial regression model with smoothing

AU - Minami, Mihoko

AU - Lennert-Cody, C. E.

AU - Gao, W.

AU - Román-Verdesoto, M.

PY - 2007/4

Y1 - 2007/4

N2 - The zero-inflated negative binomial (ZINB) regression model with smoothing is introduced for modeling count data with many zero-valued observations, and its use is illustrated with shark bycatch data from the eastern Pacific Ocean tuna purse-seine fishery for 1994-2004. Based on the generalized information criterion, the ZINB regression model provided a better fit to the data than either Poisson, negative binomial or zero-inflated Poisson regression models. To demonstrate the utility of the ZINB regression model for the standardization of catch data, standardized temporal trends in bycatch rates estimated with the ZINB regression model are computed and compared to those obtained from fits of the other three types of models to the same data. With the exception of the negative binomial, estimated temporal trends were more similar among models than would have been inferred from an analysis of model fit. Comparison of trends among models suggests that the negative binomial regression model may overestimate model coefficients when fitted to data with many zero-valued observations.

AB - The zero-inflated negative binomial (ZINB) regression model with smoothing is introduced for modeling count data with many zero-valued observations, and its use is illustrated with shark bycatch data from the eastern Pacific Ocean tuna purse-seine fishery for 1994-2004. Based on the generalized information criterion, the ZINB regression model provided a better fit to the data than either Poisson, negative binomial or zero-inflated Poisson regression models. To demonstrate the utility of the ZINB regression model for the standardization of catch data, standardized temporal trends in bycatch rates estimated with the ZINB regression model are computed and compared to those obtained from fits of the other three types of models to the same data. With the exception of the negative binomial, estimated temporal trends were more similar among models than would have been inferred from an analysis of model fit. Comparison of trends among models suggests that the negative binomial regression model may overestimate model coefficients when fitted to data with many zero-valued observations.

KW - CPUE

KW - EM algorithm

KW - GAM

KW - GLM

KW - Negative binomial

KW - Shark

KW - Spline smoothing

KW - Zero-inflated

UR - http://www.scopus.com/inward/record.url?scp=33847057703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847057703&partnerID=8YFLogxK

U2 - 10.1016/j.fishres.2006.10.019

DO - 10.1016/j.fishres.2006.10.019

M3 - Article

AN - SCOPUS:33847057703

VL - 84

SP - 210

EP - 221

JO - Fisheries Research

JF - Fisheries Research

SN - 0165-7836

IS - 2

ER -