Arithmetic average, geometric average, and ranking: application to incoherent scatter radar data processing

Q. H. Zhou, Q. N. Zhou, John David Mathews

    Research output: Contribution to journalArticle

    5 Citations (Scopus)

    Abstract

    We examine the statistical characteristics of three commonly used estimators, arithmetic average, geometric average, and ranking as applied to incoherent scatter radar observations in the presence of interference. While the arithmetic average is effective in reducing the statistical error, it is very sensitive to 'outlier' contamination, such as meteor returns. The ranking method is robust in removing outliers but is not effective in reducing the statistical variance. On the other hand, triple ranking and the geometric average are almost as effective as the arithmetic average in reducing the statistical error. If the data contain only outlier contamination, the geometric average is a better choice than either simple arithmetic average or the single ranking method. In dealing with complex interference from radars and various communication systems, one can use the triple ranking method or a combination of the arithmetic average and the single ranking method. In addition, the processes of ranking and geometric average, like those of the arithmetic average, also converge to a Gaussian function when the number of samples is large. We also show that the central limit theorem can be used to obtain interesting approximations.

    Original languageEnglish (US)
    Pages (from-to)1227-1237
    Number of pages11
    JournalRadio Science
    Volume34
    Issue number5
    DOIs
    StatePublished - Jan 1 1999

    Fingerprint

    incoherent scatter radar
    ranking
    radar data
    Radar
    Contamination
    radar
    outlier
    Communication systems
    contamination
    meteor
    interference
    radar tracking
    meteoroids
    estimators
    telecommunication
    method
    theorems

    All Science Journal Classification (ASJC) codes

    • Condensed Matter Physics
    • Earth and Planetary Sciences(all)
    • Electrical and Electronic Engineering

    Cite this

    Zhou, Q. H. ; Zhou, Q. N. ; Mathews, John David. / Arithmetic average, geometric average, and ranking : application to incoherent scatter radar data processing. In: Radio Science. 1999 ; Vol. 34, No. 5. pp. 1227-1237.
    @article{0fb17d0063d146ada0e0de0a0851e1dc,
    title = "Arithmetic average, geometric average, and ranking: application to incoherent scatter radar data processing",
    abstract = "We examine the statistical characteristics of three commonly used estimators, arithmetic average, geometric average, and ranking as applied to incoherent scatter radar observations in the presence of interference. While the arithmetic average is effective in reducing the statistical error, it is very sensitive to 'outlier' contamination, such as meteor returns. The ranking method is robust in removing outliers but is not effective in reducing the statistical variance. On the other hand, triple ranking and the geometric average are almost as effective as the arithmetic average in reducing the statistical error. If the data contain only outlier contamination, the geometric average is a better choice than either simple arithmetic average or the single ranking method. In dealing with complex interference from radars and various communication systems, one can use the triple ranking method or a combination of the arithmetic average and the single ranking method. In addition, the processes of ranking and geometric average, like those of the arithmetic average, also converge to a Gaussian function when the number of samples is large. We also show that the central limit theorem can be used to obtain interesting approximations.",
    author = "Zhou, {Q. H.} and Zhou, {Q. N.} and Mathews, {John David}",
    year = "1999",
    month = "1",
    day = "1",
    doi = "10.1029/1999RS900062",
    language = "English (US)",
    volume = "34",
    pages = "1227--1237",
    journal = "Radio Science",
    issn = "0048-6604",
    publisher = "American Geophysical Union",
    number = "5",

    }

    Arithmetic average, geometric average, and ranking : application to incoherent scatter radar data processing. / Zhou, Q. H.; Zhou, Q. N.; Mathews, John David.

    In: Radio Science, Vol. 34, No. 5, 01.01.1999, p. 1227-1237.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Arithmetic average, geometric average, and ranking

    T2 - application to incoherent scatter radar data processing

    AU - Zhou, Q. H.

    AU - Zhou, Q. N.

    AU - Mathews, John David

    PY - 1999/1/1

    Y1 - 1999/1/1

    N2 - We examine the statistical characteristics of three commonly used estimators, arithmetic average, geometric average, and ranking as applied to incoherent scatter radar observations in the presence of interference. While the arithmetic average is effective in reducing the statistical error, it is very sensitive to 'outlier' contamination, such as meteor returns. The ranking method is robust in removing outliers but is not effective in reducing the statistical variance. On the other hand, triple ranking and the geometric average are almost as effective as the arithmetic average in reducing the statistical error. If the data contain only outlier contamination, the geometric average is a better choice than either simple arithmetic average or the single ranking method. In dealing with complex interference from radars and various communication systems, one can use the triple ranking method or a combination of the arithmetic average and the single ranking method. In addition, the processes of ranking and geometric average, like those of the arithmetic average, also converge to a Gaussian function when the number of samples is large. We also show that the central limit theorem can be used to obtain interesting approximations.

    AB - We examine the statistical characteristics of three commonly used estimators, arithmetic average, geometric average, and ranking as applied to incoherent scatter radar observations in the presence of interference. While the arithmetic average is effective in reducing the statistical error, it is very sensitive to 'outlier' contamination, such as meteor returns. The ranking method is robust in removing outliers but is not effective in reducing the statistical variance. On the other hand, triple ranking and the geometric average are almost as effective as the arithmetic average in reducing the statistical error. If the data contain only outlier contamination, the geometric average is a better choice than either simple arithmetic average or the single ranking method. In dealing with complex interference from radars and various communication systems, one can use the triple ranking method or a combination of the arithmetic average and the single ranking method. In addition, the processes of ranking and geometric average, like those of the arithmetic average, also converge to a Gaussian function when the number of samples is large. We also show that the central limit theorem can be used to obtain interesting approximations.

    UR - http://www.scopus.com/inward/record.url?scp=0033317419&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0033317419&partnerID=8YFLogxK

    U2 - 10.1029/1999RS900062

    DO - 10.1029/1999RS900062

    M3 - Article

    AN - SCOPUS:0033317419

    VL - 34

    SP - 1227

    EP - 1237

    JO - Radio Science

    JF - Radio Science

    SN - 0048-6604

    IS - 5

    ER -