• The use of percentage change from baseline as an outcome in a controlled trial is statistically inefficient: a simulation study

    Type Journal Article
    Author A. J. Vickers
    URL http://www.biomedcentral.com/1471-2288/1/6
    Volume 1
    Pages 6
    Publication BMC Med Res Methodol
    Date 2001
    Extra Citation Key: vic01use tex.citeulike-article-id= 13265731 tex.citeulike-linkout-0= http://dx.doi.org/10.1186/1471-2288-1-6 tex.citeulike-linkout-1= http://www.biomedcentral.com/1471-2288/1/6 tex.posted-at= 2014-07-14 14:10:03 tex.priority= 0
    DOI 10.1186/1471-2288-1-6
    Abstract BACKGROUND:Many randomized trials involve measuring a continuous outcome - such as pain, body weight or blood pressure - at baseline and after treatment. In this paper, I compare four possibilities for how such trials can be analyzed: post-treatment; change between baseline and post-treatment; percentage change between baseline and post-treatment and analysis of covariance (ANCOVA) with baseline score as a covariate. The statistical power of each method was determined for a hypothetical randomized trial under a range of correlations between baseline and post-treatment scores.RESULTS:ANCOVA has the highest statistical power. Change from baseline has acceptable power when correlation between baseline and post-treatment scores is high;when correlation is low, analyzing only post-treatment scores has reasonable power. Percentage change from baseline has the lowest statistical power and was highly sensitive to changes in variance. Theoretical considerations suggest that percentage change from baseline will also fail to protect from bias in the case of baseline imbalance and will lead to an excess of trials with non-normally distributed outcome data.CONCLUSIONS:Percentage change from baseline should not be used in statistical analysis. Trialists wishing to report this statistic should use another method, such as ANCOVA, and convert the results to a percentage change by using mean baseline scores.
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • change
    • change-from-baseline
    • change-score
    • measuring-change
    • methodology
    • percent-change
    • percentage-change
    • statistics

  • Regression models for the analysis of pretest/posttest data

    Type Journal Article
    Author Julio M. Singer
    Author Dalton F. Andrade
    URL http://dx.doi.org/10.2307/2533973
    Volume 53
    Pages 729-735
    Publication Biometrics
    Date 1997
    Extra Citation Key: sin97reg tex.citeulike-article-id= 13264865 tex.citeulike-linkout-0= http://dx.doi.org/10.2307/2533973 tex.posted-at= 2014-07-14 14:09:44 tex.priority= 0
    DOI 10.2307/2533973
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • serial-data
    • teaching-mds
    • repeated-measures
    • change
    • analysis-of-change
    • baseline-measurement-as-covariable
    • multiplicative-model
    • pretest-posttest

    Notes:

    • problems with using baseline measurement as covariate

  • How should relative changes be measured?

    Type Journal Article
    Author L. Törnqvist
    Author P. Vartia
    Author Y. O. Vartia
    URL http://dx.doi.org/10.1080/00031305.1985.10479385
    Volume 39
    Pages 43-46
    Publication Am Statistician
    Date 1985
    Extra Citation Key: tor85how tex.citeulike-article-id= 13264968 tex.citeulike-linkout-0= http://dx.doi.org/10.1080/00031305.1985.10479385 tex.posted-at= 2014-07-14 14:09:46 tex.priority= 0
    DOI 10.1080/00031305.1985.10479385
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • change
    • measuring-change
    • percent-change
    • one-sample-problem

  • Models and the use of signed rank tests

    Type Journal Article
    Author J. S. Maritz
    URL http://dx.doi.org/10.1002/sim.4780040205
    Volume 4
    Pages 145-153
    Publication Stat Med
    Date 1985
    Extra Citation Key: mar85mod tex.citeulike-article-id= 13264569 tex.citeulike-linkout-0= http://dx.doi.org/10.1002/sim.4780040205 tex.posted-at= 2014-07-14 14:09:38 tex.priority= 0
    DOI 10.1002/sim.4780040205
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • change
    • measuring-change
    • percent-change
    • one-sample-problem
    • signed-rank-test

  • Adjusting for baseline: Change or percentage change?

    Type Journal Article
    Author Lee Kaiser
    URL http://dx.doi.org/10.1002/sim.4780081002
    Volume 8
    Pages 1183-1190
    Publication Stat Med
    Date 1989
    Extra Citation Key: kai89 tex.citeulike-article-id= 13264376 tex.citeulike-linkout-0= http://dx.doi.org/10.1002/sim.4780081002 tex.posted-at= 2014-07-14 14:09:34 tex.priority= 0
    DOI 10.1002/sim.4780081002
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • miscellaneous
    • measurement
    • research-methods
    • teaching-mds
    • change
    • measuring-change
    • percent-change
    • one-sample-problem

  • Sympercents: symmetric percentage differences on the 100 log e scale simplify the presentation of log transformed data

    Type Journal Article
    Author T. J. Cole
    Volume 19
    Pages 3109-3125
    Publication Stat Med
    Date 2000
    Extra Citation Key: col00sym tex.citeulike-article-id= 13265161 tex.posted-at= 2014-07-14 14:09:50 tex.priority= 0
    Date Added 7/7/2018, 1:38:33 PM
    Modified 11/8/2019, 8:01:59 AM

    Tags:

    • teaching-mds
    • change
    • measuring-change
    • quantifying-change