Hierarchical partitioning as an interpretative tool in multivariate inference

    Research output: Contribution to journalArticle

    161 Citations (Scopus)

    Abstract

    Much of biogeography, conservation and evolutionary biology, and ecology involves very large spatial and temporal extents. Direct manipulation to test hypotheses is usually almost impossible at appropriate scales so that multivariate modelling and especially regression are used to draw causal inferences about which 'independent' variables influence the distribution and abundances of species. Such inferences clearly are crucial for the successful management of biological resources and for conserving threatened species. A succession of regression approaches has arisen, many of which yield inconsistent implications. The main problem has been the quest for one (the 'best' or the 'optimal') regression model from which the impacts of independent variables are inferred. This note is to draw the attention of ecologists to a relatively recent method, hierarchical partitioning, that does not aim to identify a best regression model as such but rather uses all models in a regression hierarchy to distinguish those variables that have high independent correlations with the dependent variable. Such variables are likely to be most influential in controlling variation in the dependent variable. Hierarchical partitioning is not to be regarded as a substitute for experimental manipulation when that is appropriate, but it is likely to produce better deductions than common regression approaches in the many ecological situations in which manipulation is impossible or of doubtful value.
    Original languageEnglish
    Pages (from-to)224-228
    Number of pages5
    JournalAustral Ecology
    Volume21
    Issue number3
    Publication statusPublished - 1996

    Fingerprint

    partitioning
    evolutionary biology
    biogeography
    biological resources
    threatened species
    ecologists
    ecology
    Biological Sciences
    modeling
    testing
    methodology
    biological resource
    test
    method
    distribution

    Cite this

    @article{ceab77ea7ce84608a62ecd0e715698a2,
    title = "Hierarchical partitioning as an interpretative tool in multivariate inference",
    abstract = "Much of biogeography, conservation and evolutionary biology, and ecology involves very large spatial and temporal extents. Direct manipulation to test hypotheses is usually almost impossible at appropriate scales so that multivariate modelling and especially regression are used to draw causal inferences about which 'independent' variables influence the distribution and abundances of species. Such inferences clearly are crucial for the successful management of biological resources and for conserving threatened species. A succession of regression approaches has arisen, many of which yield inconsistent implications. The main problem has been the quest for one (the 'best' or the 'optimal') regression model from which the impacts of independent variables are inferred. This note is to draw the attention of ecologists to a relatively recent method, hierarchical partitioning, that does not aim to identify a best regression model as such but rather uses all models in a regression hierarchy to distinguish those variables that have high independent correlations with the dependent variable. Such variables are likely to be most influential in controlling variation in the dependent variable. Hierarchical partitioning is not to be regarded as a substitute for experimental manipulation when that is appropriate, but it is likely to produce better deductions than common regression approaches in the many ecological situations in which manipulation is impossible or of doubtful value.",
    author = "{Mac Nally}, R.",
    note = "Cited By :137 Export Date: 6 June 2017",
    year = "1996",
    language = "English",
    volume = "21",
    pages = "224--228",
    journal = "Austral Ecology",
    issn = "1442-9985",
    publisher = "Wiley-Blackwell",
    number = "3",

    }

    Hierarchical partitioning as an interpretative tool in multivariate inference. / Mac Nally, R.

    In: Austral Ecology, Vol. 21, No. 3, 1996, p. 224-228.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Hierarchical partitioning as an interpretative tool in multivariate inference

    AU - Mac Nally, R.

    N1 - Cited By :137 Export Date: 6 June 2017

    PY - 1996

    Y1 - 1996

    N2 - Much of biogeography, conservation and evolutionary biology, and ecology involves very large spatial and temporal extents. Direct manipulation to test hypotheses is usually almost impossible at appropriate scales so that multivariate modelling and especially regression are used to draw causal inferences about which 'independent' variables influence the distribution and abundances of species. Such inferences clearly are crucial for the successful management of biological resources and for conserving threatened species. A succession of regression approaches has arisen, many of which yield inconsistent implications. The main problem has been the quest for one (the 'best' or the 'optimal') regression model from which the impacts of independent variables are inferred. This note is to draw the attention of ecologists to a relatively recent method, hierarchical partitioning, that does not aim to identify a best regression model as such but rather uses all models in a regression hierarchy to distinguish those variables that have high independent correlations with the dependent variable. Such variables are likely to be most influential in controlling variation in the dependent variable. Hierarchical partitioning is not to be regarded as a substitute for experimental manipulation when that is appropriate, but it is likely to produce better deductions than common regression approaches in the many ecological situations in which manipulation is impossible or of doubtful value.

    AB - Much of biogeography, conservation and evolutionary biology, and ecology involves very large spatial and temporal extents. Direct manipulation to test hypotheses is usually almost impossible at appropriate scales so that multivariate modelling and especially regression are used to draw causal inferences about which 'independent' variables influence the distribution and abundances of species. Such inferences clearly are crucial for the successful management of biological resources and for conserving threatened species. A succession of regression approaches has arisen, many of which yield inconsistent implications. The main problem has been the quest for one (the 'best' or the 'optimal') regression model from which the impacts of independent variables are inferred. This note is to draw the attention of ecologists to a relatively recent method, hierarchical partitioning, that does not aim to identify a best regression model as such but rather uses all models in a regression hierarchy to distinguish those variables that have high independent correlations with the dependent variable. Such variables are likely to be most influential in controlling variation in the dependent variable. Hierarchical partitioning is not to be regarded as a substitute for experimental manipulation when that is appropriate, but it is likely to produce better deductions than common regression approaches in the many ecological situations in which manipulation is impossible or of doubtful value.

    M3 - Article

    VL - 21

    SP - 224

    EP - 228

    JO - Austral Ecology

    JF - Austral Ecology

    SN - 1442-9985

    IS - 3

    ER -