Outlier Tolerant Parameter Estimation

Publikation: Beitrag in Buch/Bericht/KonferenzbandSonstiger Beitrag in Buch/Bericht/KonferenzbandForschung

Abstract

Real world does not only provide noisy instead of perfect data. Every experimentalist has now and then to deal with outliers. The situation is simple if isolated points stick out of the general trend by a large amount. Arguments can then usually be found why such a point should be disregarded. The situation becomes critical if the outliers are not that obvious. This is usually the case for parameter space dimensions ≥ 3. We present a Bayesian solution to the outlier problem which assumes that the uncertainties assigned to the experimental data are only estimates of the true error variances.
Originalspracheenglisch
TitelMaximum Entropy and Bayesian Methods Garching, Germany 1998
Redakteure/-innenWolfgang von der Linden, Volker Dose, Rainer Fischer, Roland Preuss
Herausgeber (Verlag)Springer Netherlands
Seiten47-56
Seitenumfang10
ISBN (Print)978-94-010-5982-4 978-94-011-4710-1
PublikationsstatusVeröffentlicht - 1999

Publikationsreihe

NameFundamental Theories of Physics
Herausgeber (Verlag)Springer Netherlands

Fingerprint

Parameter estimation
Uncertainty

Schlagwörter

    Dies zitieren

    Dose, V., & Linden, W. V. D. (1999). Outlier Tolerant Parameter Estimation. in W. V. D. Linden, V. Dose, R. Fischer, & R. Preuss (Hrsg.), Maximum Entropy and Bayesian Methods Garching, Germany 1998 (S. 47-56). (Fundamental Theories of Physics). Springer Netherlands.

    Outlier Tolerant Parameter Estimation. / Dose, V.; Linden, W. Von Der.

    Maximum Entropy and Bayesian Methods Garching, Germany 1998. Hrsg. / Wolfgang von der Linden; Volker Dose; Rainer Fischer; Roland Preuss. Springer Netherlands, 1999. S. 47-56 (Fundamental Theories of Physics).

    Publikation: Beitrag in Buch/Bericht/KonferenzbandSonstiger Beitrag in Buch/Bericht/KonferenzbandForschung

    Dose, V & Linden, WVD 1999, Outlier Tolerant Parameter Estimation. in WVD Linden, V Dose, R Fischer & R Preuss (Hrsg.), Maximum Entropy and Bayesian Methods Garching, Germany 1998. Fundamental Theories of Physics, Springer Netherlands, S. 47-56.
    Dose V, Linden WVD. Outlier Tolerant Parameter Estimation. in Linden WVD, Dose V, Fischer R, Preuss R, Hrsg., Maximum Entropy and Bayesian Methods Garching, Germany 1998. Springer Netherlands. 1999. S. 47-56. (Fundamental Theories of Physics).
    Dose, V. ; Linden, W. Von Der. / Outlier Tolerant Parameter Estimation. Maximum Entropy and Bayesian Methods Garching, Germany 1998. Hrsg. / Wolfgang von der Linden ; Volker Dose ; Rainer Fischer ; Roland Preuss. Springer Netherlands, 1999. S. 47-56 (Fundamental Theories of Physics).
    @inbook{7c74b6712f1243758dde82bb6d0cb9ef,
    title = "Outlier Tolerant Parameter Estimation",
    abstract = "Real world does not only provide noisy instead of perfect data. Every experimentalist has now and then to deal with outliers. The situation is simple if isolated points stick out of the general trend by a large amount. Arguments can then usually be found why such a point should be disregarded. The situation becomes critical if the outliers are not that obvious. This is usually the case for parameter space dimensions ≥ 3. We present a Bayesian solution to the outlier problem which assumes that the uncertainties assigned to the experimental data are only estimates of the true error variances.",
    keywords = "Artificial Intelligence (incl. Robotics), Coding and Information Theory, Discrete Mathematics in Computer Science, duff data, Outlier, parameter estimation, Probability Theory and Stochastic Processes, Statistics, general",
    author = "V. Dose and Linden, {W. Von Der}",
    note = "DOI: 10.1007/978-94-011-4710-14",
    year = "1999",
    language = "English",
    isbn = "978-94-010-5982-4 978-94-011-4710-1",
    series = "Fundamental Theories of Physics",
    publisher = "Springer Netherlands",
    pages = "47--56",
    editor = "Linden, {Wolfgang von der} and Volker Dose and Rainer Fischer and Roland Preuss",
    booktitle = "Maximum Entropy and Bayesian Methods Garching, Germany 1998",
    address = "Netherlands",

    }

    TY - CHAP

    T1 - Outlier Tolerant Parameter Estimation

    AU - Dose, V.

    AU - Linden, W. Von Der

    N1 - DOI: 10.1007/978-94-011-4710-14

    PY - 1999

    Y1 - 1999

    N2 - Real world does not only provide noisy instead of perfect data. Every experimentalist has now and then to deal with outliers. The situation is simple if isolated points stick out of the general trend by a large amount. Arguments can then usually be found why such a point should be disregarded. The situation becomes critical if the outliers are not that obvious. This is usually the case for parameter space dimensions ≥ 3. We present a Bayesian solution to the outlier problem which assumes that the uncertainties assigned to the experimental data are only estimates of the true error variances.

    AB - Real world does not only provide noisy instead of perfect data. Every experimentalist has now and then to deal with outliers. The situation is simple if isolated points stick out of the general trend by a large amount. Arguments can then usually be found why such a point should be disregarded. The situation becomes critical if the outliers are not that obvious. This is usually the case for parameter space dimensions ≥ 3. We present a Bayesian solution to the outlier problem which assumes that the uncertainties assigned to the experimental data are only estimates of the true error variances.

    KW - Artificial Intelligence (incl. Robotics), Coding and Information Theory, Discrete Mathematics in Computer Science, duff data, Outlier, parameter estimation, Probability Theory and Stochastic Processes, Statistics, general

    M3 - Other chapter contribution

    SN - 978-94-010-5982-4 978-94-011-4710-1

    T3 - Fundamental Theories of Physics

    SP - 47

    EP - 56

    BT - Maximum Entropy and Bayesian Methods Garching, Germany 1998

    A2 - Linden, Wolfgang von der

    A2 - Dose, Volker

    A2 - Fischer, Rainer

    A2 - Preuss, Roland

    PB - Springer Netherlands

    ER -