Application of the Dempster-Shafer theory of evidence for accident probability estimates

Jan Holmberg, Pekka Silvennoinen, Juhani Vira

    Research output: Contribution to journalArticleScientificpeer-review

    1 Citation (Scopus)

    Abstract

    Application of the Bayes' formula leaves little room for representation of ignorance and vagueness in quantitative estimates. Adhering to the classical probability calculus, the Bayesian approach can only replace ignorance with indifference. Shafer's belief functions are different in this respect. Free from the additivity requirement of classical probabilities, they preserve the vagueness of subjective beliefs. Together with Dempster's combination rule the belief functions offer an alternative to the Bayesian updating of probability estimates. In this paper the two methods are compared in a risk analysis application. While the results given by the Dempster-Shafer theory are, in essence, similar to those from the Bayesian analysis, the new method offers some presentational advantages for both the input and output data.
    Original languageEnglish
    Pages (from-to)47-58
    JournalReliability Engineering and System Safety
    Volume26
    Issue number1
    DOIs
    Publication statusPublished - 1989
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Accidents
    Risk analysis

    Cite this

    @article{c4534eb11c93485b9238349d6445041e,
    title = "Application of the Dempster-Shafer theory of evidence for accident probability estimates",
    abstract = "Application of the Bayes' formula leaves little room for representation of ignorance and vagueness in quantitative estimates. Adhering to the classical probability calculus, the Bayesian approach can only replace ignorance with indifference. Shafer's belief functions are different in this respect. Free from the additivity requirement of classical probabilities, they preserve the vagueness of subjective beliefs. Together with Dempster's combination rule the belief functions offer an alternative to the Bayesian updating of probability estimates. In this paper the two methods are compared in a risk analysis application. While the results given by the Dempster-Shafer theory are, in essence, similar to those from the Bayesian analysis, the new method offers some presentational advantages for both the input and output data.",
    author = "Jan Holmberg and Pekka Silvennoinen and Juhani Vira",
    year = "1989",
    doi = "10.1016/0951-8320(89)90083-5",
    language = "English",
    volume = "26",
    pages = "47--58",
    journal = "Reliability Engineering and System Safety",
    issn = "0951-8320",
    publisher = "Elsevier",
    number = "1",

    }

    Application of the Dempster-Shafer theory of evidence for accident probability estimates. / Holmberg, Jan; Silvennoinen, Pekka; Vira, Juhani.

    In: Reliability Engineering and System Safety, Vol. 26, No. 1, 1989, p. 47-58.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Application of the Dempster-Shafer theory of evidence for accident probability estimates

    AU - Holmberg, Jan

    AU - Silvennoinen, Pekka

    AU - Vira, Juhani

    PY - 1989

    Y1 - 1989

    N2 - Application of the Bayes' formula leaves little room for representation of ignorance and vagueness in quantitative estimates. Adhering to the classical probability calculus, the Bayesian approach can only replace ignorance with indifference. Shafer's belief functions are different in this respect. Free from the additivity requirement of classical probabilities, they preserve the vagueness of subjective beliefs. Together with Dempster's combination rule the belief functions offer an alternative to the Bayesian updating of probability estimates. In this paper the two methods are compared in a risk analysis application. While the results given by the Dempster-Shafer theory are, in essence, similar to those from the Bayesian analysis, the new method offers some presentational advantages for both the input and output data.

    AB - Application of the Bayes' formula leaves little room for representation of ignorance and vagueness in quantitative estimates. Adhering to the classical probability calculus, the Bayesian approach can only replace ignorance with indifference. Shafer's belief functions are different in this respect. Free from the additivity requirement of classical probabilities, they preserve the vagueness of subjective beliefs. Together with Dempster's combination rule the belief functions offer an alternative to the Bayesian updating of probability estimates. In this paper the two methods are compared in a risk analysis application. While the results given by the Dempster-Shafer theory are, in essence, similar to those from the Bayesian analysis, the new method offers some presentational advantages for both the input and output data.

    U2 - 10.1016/0951-8320(89)90083-5

    DO - 10.1016/0951-8320(89)90083-5

    M3 - Article

    VL - 26

    SP - 47

    EP - 58

    JO - Reliability Engineering and System Safety

    JF - Reliability Engineering and System Safety

    SN - 0951-8320

    IS - 1

    ER -