Imputing missing quality of life data as covariate in survival analysis of the International Breast Cancer Study Group Trials VI and VII

Procter, Marion and Robertson, Charles (2017) Imputing missing quality of life data as covariate in survival analysis of the International Breast Cancer Study Group Trials VI and VII. Communications in Statistics - Simulation and Computation. pp. 1-11. ISSN 0361-0918 (https://doi.org/10.1080/03610918.2017.1390123)

[thumbnail of Procter-Robertson-CSSC2017-Imputing-missing-quality-of-life-data-as-covariate-in-survival]
Preview
 Text. Filename: Procter_Robertson_CSSC2017_Imputing_missing_quality_of_life_data_as_covariate_in_survival.pdf
Accepted Author Manuscript
Download (501kB)| Preview

Abstract

Quality of life (QoL) was an important endpoint in the adjuvant breast cancer trials International Breast Cancer Study Group (IBCSG) Trial VI and VII. Here, QoL was considered as a time-dependent effect. The hypothesis explored is that poorer QoL throughout the trial is associated with poorer disease-free survival (DFS) and vice-versa. Potential bias in the parameter estimates is an important concern associated with missing observations. Standard simple and multiple imputation methods were applied to missing QoL assessments before analysis in a time-dependent Cox model. There was no evidence that the patient's QoL is related to the patient's DFS.

ORCID iDs

Procter, Marion ORCID logoORCID: https://orcid.org/0000-0002-1997-4417 and Robertson, Charles;
  • Item type:Article
    ID code:64932
    Dates:
    Date
    Event
    15 December 2017
    Published
    30 October 2017
    Published Online
    3 October 2017
    Accepted
    Notes:This is an Accepted Manuscript of an article published by Taylor & Francis in Communications in Statistics - Simulation and Computation on 30th October 2017, available online: http://www.tandfonline.com/10.1080/03610918.2017.1390123.
    Keywords:informative missing data, multiple imputation, potential bias, qualify of life, simple imputation, time-dependent Cox model, Neoplasms. Tumors. Oncology (including Cancer), Modelling and Simulation, Statistics and Probability
    Subjects:Medicine > Internal medicine > Neoplasms. Tumors. Oncology (including Cancer)
    Department:Faculty of Science > Mathematics and Statistics
    Depositing user: Pure Administrator
    Date deposited:30 Jul 2018 09:25
    Last modified:06 Feb 2023 14:22
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/64932
CORE (COnnecting REpositories)