Optimized estimation of the Weibull distribution parameters

Kim Wallin

    Research output: Book/ReportReport

    20 Citations (Scopus)

    Abstract

    The Weibull distribution is extensively used in analysing brittle materials such as ceramics. Usually the distribution is fitted to data sets based on less than 50 specimens. This number of specimens is so small that the reliability of the fit can become questionable. The fit can also be unreliable due to the fact that there exists a large number of different methods to determine the Weibull parameters, all of which yield different results. Therefore, it is imperative to use a method yielding optimum reliability for the parameters. In this report the accuracy of different methods for determining the Weibull distribution parameters are compared. A bias corrected maximum likelihood estimation method is presented, and it is proposed that this method is used for analysis of brittle materials.
    Original languageEnglish
    Place of PublicationEspoo
    PublisherVTT Technical Research Centre of Finland
    Number of pages19
    ISBN (Print)951-38-3414-X
    Publication statusPublished - 1989
    MoE publication typeD4 Published development or research report or study

    Publication series

    SeriesValtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports
    Number604
    ISSN0358-5077

    Fingerprint

    Weibull distribution
    Brittleness
    Maximum likelihood estimation

    Keywords

    • mechanical properties
    • ceramics
    • statistical analysis

    Cite this

    Wallin, K. (1989). Optimized estimation of the Weibull distribution parameters. Espoo: VTT Technical Research Centre of Finland. Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports, No. 604
    Wallin, Kim. / Optimized estimation of the Weibull distribution parameters. Espoo : VTT Technical Research Centre of Finland, 1989. 19 p. (Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports; No. 604).
    @book{afa1dff265cc4e718546f11f06d4b28d,
    title = "Optimized estimation of the Weibull distribution parameters",
    abstract = "The Weibull distribution is extensively used in analysing brittle materials such as ceramics. Usually the distribution is fitted to data sets based on less than 50 specimens. This number of specimens is so small that the reliability of the fit can become questionable. The fit can also be unreliable due to the fact that there exists a large number of different methods to determine the Weibull parameters, all of which yield different results. Therefore, it is imperative to use a method yielding optimum reliability for the parameters. In this report the accuracy of different methods for determining the Weibull distribution parameters are compared. A bias corrected maximum likelihood estimation method is presented, and it is proposed that this method is used for analysis of brittle materials.",
    keywords = "mechanical properties, ceramics, statistical analysis",
    author = "Kim Wallin",
    note = "CA: MET PGN: 17 p. + app. 1 p.",
    year = "1989",
    language = "English",
    isbn = "951-38-3414-X",
    series = "Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports",
    publisher = "VTT Technical Research Centre of Finland",
    number = "604",
    address = "Finland",

    }

    Wallin, K 1989, Optimized estimation of the Weibull distribution parameters. Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports, no. 604, VTT Technical Research Centre of Finland, Espoo.

    Optimized estimation of the Weibull distribution parameters. / Wallin, Kim.

    Espoo : VTT Technical Research Centre of Finland, 1989. 19 p. (Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports; No. 604).

    Research output: Book/ReportReport

    TY - BOOK

    T1 - Optimized estimation of the Weibull distribution parameters

    AU - Wallin, Kim

    N1 - CA: MET PGN: 17 p. + app. 1 p.

    PY - 1989

    Y1 - 1989

    N2 - The Weibull distribution is extensively used in analysing brittle materials such as ceramics. Usually the distribution is fitted to data sets based on less than 50 specimens. This number of specimens is so small that the reliability of the fit can become questionable. The fit can also be unreliable due to the fact that there exists a large number of different methods to determine the Weibull parameters, all of which yield different results. Therefore, it is imperative to use a method yielding optimum reliability for the parameters. In this report the accuracy of different methods for determining the Weibull distribution parameters are compared. A bias corrected maximum likelihood estimation method is presented, and it is proposed that this method is used for analysis of brittle materials.

    AB - The Weibull distribution is extensively used in analysing brittle materials such as ceramics. Usually the distribution is fitted to data sets based on less than 50 specimens. This number of specimens is so small that the reliability of the fit can become questionable. The fit can also be unreliable due to the fact that there exists a large number of different methods to determine the Weibull parameters, all of which yield different results. Therefore, it is imperative to use a method yielding optimum reliability for the parameters. In this report the accuracy of different methods for determining the Weibull distribution parameters are compared. A bias corrected maximum likelihood estimation method is presented, and it is proposed that this method is used for analysis of brittle materials.

    KW - mechanical properties

    KW - ceramics

    KW - statistical analysis

    M3 - Report

    SN - 951-38-3414-X

    T3 - Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports

    BT - Optimized estimation of the Weibull distribution parameters

    PB - VTT Technical Research Centre of Finland

    CY - Espoo

    ER -

    Wallin K. Optimized estimation of the Weibull distribution parameters. Espoo: VTT Technical Research Centre of Finland, 1989. 19 p. (Valtion teknillinen tutkimuskeskus. Tutkimuksia - Research Reports; No. 604).