Alternative spatiotemporal imputation methods for catch rate standardisation

    Research output: ThesisMaster's Thesis

    69 Downloads (Pure)

    Abstract

    An index of fish abundance is often calculated from the estimated marginal means predicted from a generalised linear model fitted to fishery catch rate data with suitable explanatory variables. However, fishing grounds can change, because fleets often shift their activity to target different areas of a fish population over time, which can lead to spatiotemporal gaps in catch rate data. These missing data, if ignored, may result in a biased index. This thesis develops and evaluates several alternative imputation methods for reducing such biases. Evaluations were done by analysing both simulated and real fisheries datasets.
    Original languageEnglish
    QualificationMasters
    Awarding Institution
    • The University of Western Australia
    Award date19 May 2017
    DOIs
    Publication statusUnpublished - 2017

    Fingerprint

    standardization
    fishery
    fish
    method
    rate
    index

    Cite this

    @phdthesis{3ac17eaef8f04ac586aaccdf912db882,
    title = "Alternative spatiotemporal imputation methods for catch rate standardisation",
    abstract = "An index of fish abundance is often calculated from the estimated marginal means predicted from a generalised linear model fitted to fishery catch rate data with suitable explanatory variables. However, fishing grounds can change, because fleets often shift their activity to target different areas of a fish population over time, which can lead to spatiotemporal gaps in catch rate data. These missing data, if ignored, may result in a biased index. This thesis develops and evaluates several alternative imputation methods for reducing such biases. Evaluations were done by analysing both simulated and real fisheries datasets.",
    keywords = "Imputation, Fish, Simulation, Catch rates, Fishery stock assessment, Generalised linear model",
    author = "Marriott, {Ross James}",
    year = "2017",
    doi = "10.4225/23/594767b6abc7f",
    language = "English",
    school = "The University of Western Australia",

    }

    TY - THES

    T1 - Alternative spatiotemporal imputation methods for catch rate standardisation

    AU - Marriott, Ross James

    PY - 2017

    Y1 - 2017

    N2 - An index of fish abundance is often calculated from the estimated marginal means predicted from a generalised linear model fitted to fishery catch rate data with suitable explanatory variables. However, fishing grounds can change, because fleets often shift their activity to target different areas of a fish population over time, which can lead to spatiotemporal gaps in catch rate data. These missing data, if ignored, may result in a biased index. This thesis develops and evaluates several alternative imputation methods for reducing such biases. Evaluations were done by analysing both simulated and real fisheries datasets.

    AB - An index of fish abundance is often calculated from the estimated marginal means predicted from a generalised linear model fitted to fishery catch rate data with suitable explanatory variables. However, fishing grounds can change, because fleets often shift their activity to target different areas of a fish population over time, which can lead to spatiotemporal gaps in catch rate data. These missing data, if ignored, may result in a biased index. This thesis develops and evaluates several alternative imputation methods for reducing such biases. Evaluations were done by analysing both simulated and real fisheries datasets.

    KW - Imputation

    KW - Fish

    KW - Simulation

    KW - Catch rates

    KW - Fishery stock assessment

    KW - Generalised linear model

    U2 - 10.4225/23/594767b6abc7f

    DO - 10.4225/23/594767b6abc7f

    M3 - Master's Thesis

    ER -