Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses

N.V. Sarlis, S-R. Christopoulos

    Research output: Contribution to journalArticle

    9 Citations (Scopus)
    36 Downloads (Pure)

    Abstract

    The Receiver Operating Characteristics (ROC) is used for the evaluation of prediction methods in various disciplines like meteorology, geophysics, complex system physics, medicine etc. The estimation of the significance of a binary prediction method, however, remains a cumbersome task and is usually done by repeating the calculations by Monte Carlo. The FORTRAN code provided here simplifies this problem by evaluating the significance of binary predictions for a family of ellipses which are based on confidence ellipses and cover the whole ROC space.
    Original languageEnglish
    Pages (from-to)1172–1176
    JournalComputer Physics Communications
    Volume185
    Issue number3
    DOIs
    Publication statusPublished - Dec 2013

    Fingerprint

    ellipses
    confidence
    Visualization
    receivers
    predictions
    Geophysics
    Meteorology
    FORTRAN
    geophysics
    meteorology
    complex systems
    medicine
    Medicine
    Large scale systems
    Physics
    physics
    evaluation

    Bibliographical note

    Creative Commons Attribution Non-Commercial No Derivatives License

    Keywords

    • Receiver Operating Characteristics (ROC)
    • Complex systems
    • Systems obeying power laws
    • Significance level
    • p-value

    Cite this

    Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses. / Sarlis, N.V.; Christopoulos, S-R.

    In: Computer Physics Communications, Vol. 185, No. 3, 12.2013, p. 1172–1176.

    Research output: Contribution to journalArticle

    @article{b691df67ffd040e48a5f03cb020ac81d,
    title = "Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses",
    abstract = "The Receiver Operating Characteristics (ROC) is used for the evaluation of prediction methods in various disciplines like meteorology, geophysics, complex system physics, medicine etc. The estimation of the significance of a binary prediction method, however, remains a cumbersome task and is usually done by repeating the calculations by Monte Carlo. The FORTRAN code provided here simplifies this problem by evaluating the significance of binary predictions for a family of ellipses which are based on confidence ellipses and cover the whole ROC space.",
    keywords = "Receiver Operating Characteristics (ROC), Complex systems, Systems obeying power laws, Significance level, p-value",
    author = "N.V. Sarlis and S-R. Christopoulos",
    note = "Creative Commons Attribution Non-Commercial No Derivatives License",
    year = "2013",
    month = "12",
    doi = "10.1016/j.cpc.2013.12.009",
    language = "English",
    volume = "185",
    pages = "1172–1176",
    journal = "Computer Physics Communications",
    issn = "0010-4655",
    publisher = "Elsevier",
    number = "3",

    }

    TY - JOUR

    T1 - Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses

    AU - Sarlis, N.V.

    AU - Christopoulos, S-R.

    N1 - Creative Commons Attribution Non-Commercial No Derivatives License

    PY - 2013/12

    Y1 - 2013/12

    N2 - The Receiver Operating Characteristics (ROC) is used for the evaluation of prediction methods in various disciplines like meteorology, geophysics, complex system physics, medicine etc. The estimation of the significance of a binary prediction method, however, remains a cumbersome task and is usually done by repeating the calculations by Monte Carlo. The FORTRAN code provided here simplifies this problem by evaluating the significance of binary predictions for a family of ellipses which are based on confidence ellipses and cover the whole ROC space.

    AB - The Receiver Operating Characteristics (ROC) is used for the evaluation of prediction methods in various disciplines like meteorology, geophysics, complex system physics, medicine etc. The estimation of the significance of a binary prediction method, however, remains a cumbersome task and is usually done by repeating the calculations by Monte Carlo. The FORTRAN code provided here simplifies this problem by evaluating the significance of binary predictions for a family of ellipses which are based on confidence ellipses and cover the whole ROC space.

    KW - Receiver Operating Characteristics (ROC)

    KW - Complex systems

    KW - Systems obeying power laws

    KW - Significance level

    KW - p-value

    U2 - 10.1016/j.cpc.2013.12.009

    DO - 10.1016/j.cpc.2013.12.009

    M3 - Article

    VL - 185

    SP - 1172

    EP - 1176

    JO - Computer Physics Communications

    JF - Computer Physics Communications

    SN - 0010-4655

    IS - 3

    ER -