Testing for the Proportionality of Hazards in Two Samples Against the Increasing Cumulative Hazard Ratio Alternative

D. Sengupta, A. Bhattacharjee, B. Rajeev

    Research output: Contribution to journalArticle

    18 Citations (Scopus)

    Abstract

    A number of tests of the proportional hazards hypothesis have been proposed in the past. In recent years, researchers have proposed tests geared specially for the alternative hypothesis of "increasing hazard ratio", keeping in mind the case of crossing hazards. This alternative may be too restrictive in many situations. In this paper we develop a test of the proportional hazards model for the weaker "increasing cumulative hazard ratio" alternative. The work is motivated by a data analytic example given by Gill & Schumacher (1987) where their test fails to reject the null hypothesis even though the faster ageing of one group is quite apparent from a plot. The normalized test statistic proposed here has an asymptotically normal distribution under either hypothesis. We also present two graphical methods related to our analytical test.
    Original languageEnglish
    Pages (from-to)637-647
    Number of pages11
    JournalScandinavian Journal of Statistics
    Volume25
    Issue number4
    DOIs
    Publication statusPublished - Dec 1998

    Fingerprint

    Hazard
    Testing
    Alternatives
    Proportional Hazards
    Graphical Methods
    Proportional Hazards Model
    Null hypothesis
    Test Statistic
    Gaussian distribution
    Proportionality

    Keywords

    • Counting process
    • Graphical method
    • Hazard ratio
    • Martingale convergence

    Cite this

    @article{b8ed38a60cf243dcacaea670572435ff,
    title = "Testing for the Proportionality of Hazards in Two Samples Against the Increasing Cumulative Hazard Ratio Alternative",
    abstract = "A number of tests of the proportional hazards hypothesis have been proposed in the past. In recent years, researchers have proposed tests geared specially for the alternative hypothesis of {"}increasing hazard ratio{"}, keeping in mind the case of crossing hazards. This alternative may be too restrictive in many situations. In this paper we develop a test of the proportional hazards model for the weaker {"}increasing cumulative hazard ratio{"} alternative. The work is motivated by a data analytic example given by Gill & Schumacher (1987) where their test fails to reject the null hypothesis even though the faster ageing of one group is quite apparent from a plot. The normalized test statistic proposed here has an asymptotically normal distribution under either hypothesis. We also present two graphical methods related to our analytical test.",
    keywords = "Counting process, Graphical method, Hazard ratio, Martingale convergence",
    author = "D. Sengupta and A. Bhattacharjee and B. Rajeev",
    note = "Copyright 2004 Elsevier Science B.V., Amsterdam. All rights reserved.",
    year = "1998",
    month = "12",
    doi = "10.1111/1467-9469.00126",
    language = "English",
    volume = "25",
    pages = "637--647",
    journal = "Scandinavian Journal of Statistics",
    issn = "0303-6898",
    publisher = "Wiley",
    number = "4",

    }

    Testing for the Proportionality of Hazards in Two Samples Against the Increasing Cumulative Hazard Ratio Alternative. / Sengupta, D.; Bhattacharjee, A.; Rajeev, B.

    In: Scandinavian Journal of Statistics, Vol. 25, No. 4, 12.1998, p. 637-647.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Testing for the Proportionality of Hazards in Two Samples Against the Increasing Cumulative Hazard Ratio Alternative

    AU - Sengupta, D.

    AU - Bhattacharjee, A.

    AU - Rajeev, B.

    N1 - Copyright 2004 Elsevier Science B.V., Amsterdam. All rights reserved.

    PY - 1998/12

    Y1 - 1998/12

    N2 - A number of tests of the proportional hazards hypothesis have been proposed in the past. In recent years, researchers have proposed tests geared specially for the alternative hypothesis of "increasing hazard ratio", keeping in mind the case of crossing hazards. This alternative may be too restrictive in many situations. In this paper we develop a test of the proportional hazards model for the weaker "increasing cumulative hazard ratio" alternative. The work is motivated by a data analytic example given by Gill & Schumacher (1987) where their test fails to reject the null hypothesis even though the faster ageing of one group is quite apparent from a plot. The normalized test statistic proposed here has an asymptotically normal distribution under either hypothesis. We also present two graphical methods related to our analytical test.

    AB - A number of tests of the proportional hazards hypothesis have been proposed in the past. In recent years, researchers have proposed tests geared specially for the alternative hypothesis of "increasing hazard ratio", keeping in mind the case of crossing hazards. This alternative may be too restrictive in many situations. In this paper we develop a test of the proportional hazards model for the weaker "increasing cumulative hazard ratio" alternative. The work is motivated by a data analytic example given by Gill & Schumacher (1987) where their test fails to reject the null hypothesis even though the faster ageing of one group is quite apparent from a plot. The normalized test statistic proposed here has an asymptotically normal distribution under either hypothesis. We also present two graphical methods related to our analytical test.

    KW - Counting process

    KW - Graphical method

    KW - Hazard ratio

    KW - Martingale convergence

    UR - http://www.scopus.com/inward/record.url?scp=0032352554&partnerID=8YFLogxK

    U2 - 10.1111/1467-9469.00126

    DO - 10.1111/1467-9469.00126

    M3 - Article

    VL - 25

    SP - 637

    EP - 647

    JO - Scandinavian Journal of Statistics

    JF - Scandinavian Journal of Statistics

    SN - 0303-6898

    IS - 4

    ER -