Pitt Logo LinkContact Us

Simulation of meta-analysis for assessing the impact of study variability on parameter estimates for survival data

Karpova, Irina (2006) Simulation of meta-analysis for assessing the impact of study variability on parameter estimates for survival data. Master's Thesis, University of Pittsburgh.

[img]
Preview
PDF - Primary Text
Download (215Kb) | Preview

    Abstract

    Meta-analysis is a statistical method of public health relevance that is used to combine the results of individual studies which evaluate the same treatment effect. A test that is commonly used to decide whether the results are homogeneous, and determines model choice for meta-analysis, is called Cochran's Q-test. A major drawback of the Q-test, when the outcomes are normally distributed, is its low power when the number of studies is small, and excessive power when the number of studies is large. In this thesis, we propose a Cochran's Q--test for survival analysis data. Usingsimulations, we examine how the power of Cochran's test changes with different numbers of studies, different weight allocations per study, and the amount of censored observations. We show that the power increases with the increasing number of studies, but lowers with the increasing number of censored observations, and whenever one study comprises a large proportion of the total weight. We conclude that the test of heterogeneity should not be considered as the only determinant of the model choice for meta-analysis. Other methods such as graphical exploration, stratified analysis, or regression modeling should be used in conjunction with the formal statistical test.


    Share

    Citation/Export:
    Social Networking:

    Details

    Item Type: University of Pittsburgh ETD
    Creators/Authors:
    CreatorsEmailORCID
    Karpova, Irinaikn53@yahoo.com
    ETD Committee:
    ETD Committee TypeCommittee MemberEmailORCID
    Committee ChairAnderson, Stewart Jsja@pitt.edu
    Committee MemberJeong, Jong-Heyonjeong@nsabp.pitt.edu
    Committee MemberKip, Kevin Ekipk@edc.pitt.edu
    Title: Simulation of meta-analysis for assessing the impact of study variability on parameter estimates for survival data
    Status: Unpublished
    Abstract: Meta-analysis is a statistical method of public health relevance that is used to combine the results of individual studies which evaluate the same treatment effect. A test that is commonly used to decide whether the results are homogeneous, and determines model choice for meta-analysis, is called Cochran's Q-test. A major drawback of the Q-test, when the outcomes are normally distributed, is its low power when the number of studies is small, and excessive power when the number of studies is large. In this thesis, we propose a Cochran's Q--test for survival analysis data. Usingsimulations, we examine how the power of Cochran's test changes with different numbers of studies, different weight allocations per study, and the amount of censored observations. We show that the power increases with the increasing number of studies, but lowers with the increasing number of censored observations, and whenever one study comprises a large proportion of the total weight. We conclude that the test of heterogeneity should not be considered as the only determinant of the model choice for meta-analysis. Other methods such as graphical exploration, stratified analysis, or regression modeling should be used in conjunction with the formal statistical test.
    Date: 01 June 2006
    Date Type: Completion
    Defense Date: 10 April 2006
    Approval Date: 01 June 2006
    Submission Date: 12 April 2006
    Access Restriction: No restriction; The work is available for access worldwide immediately.
    Patent pending: No
    Institution: University of Pittsburgh
    Thesis Type: Master's Thesis
    Refereed: Yes
    Degree: MS - Master of Science
    URN: etd-04122006-125729
    Uncontrolled Keywords: Cochran's test
    Schools and Programs: Graduate School of Public Health > Biostatistics
    Date Deposited: 10 Nov 2011 14:36
    Last Modified: 27 Apr 2012 13:49
    Other ID: http://etd.library.pitt.edu/ETD/available/etd-04122006-125729/, etd-04122006-125729

    Actions (login required)

    View Item

    Document Downloads