Statistical Issues in Randomized Controlled Trials
An editorial
Keywords:
Biostatistics, Randomized controlled trials, Covariate adjustment, Analysis of covarianceAbstract
Randomization is the bedrock of randomized controlled trials, which ensures the elimination of selection bias and also to some extent the homogenous distribution of covariates between the intervention arms. Randomization does not always guarantee the baseline balance, and hence makes the statistical analysis more complex. Several published clinical trials have employed test of significance to compare baseline measures between the groups. However, such practice has been criticized by several authors and CONSORT statement also discourages it. This overview discusses various statistical designs that were employed in published trials. Post intervention data (follow up score) comparison between the arms was common practice in published RCTs. However, this approach fails to adjust baseline imbalance. Both Change score and Percentage change methods adjust the baseline imbalance. Both of the approaches give precise estimates when there is a high correlation between baseline and follow-up score. However, when correlation is low they both give biased and less precise estimates of treatment effect. Analysis of covariance (ANCOVA) is a regression method, which maintains high statistical power and gives less biased and more precise estimates of treatment effect regardless of correlation level. Understanding strengths and limitations of different statistical designs of RCTs will prevent statistical errors, which can yield an accurate estimate of treatment effect.
References
Sackett DL, Rosenberg WM, Gray JA, Haynes RB, Richardson WS. Evidence based medicine: what it is
and what it isn’t. BMJ. 1996; 312(7023): 71–2. doi: 10.1136/bmj.312.7023.71. PMID: 8555924, PMCID:
PMC2349778.
Kent DM, Trikalinos TA, Hill MD. Are unadjusted analyses of clinical trials inappropriately biased toward
the null? Stroke. 2009; 40(3): 672–3. doi: 10.1161/STROKEAHA.108.532051. PMID: 19164784, PMCID:
PMC2693723.
Egbewale BE, Lewis M, Sim J. Bias, precision and statistical power of analysis of covariance in the
analysis of randomized trials with baseline imbalance: A simulation study. BMC Med Res Methodol. 2014;
(1). doi: 10.1186/1471-2288-14-49. PMID: 24712304, PMCID: PMC3986434.
Gray LJ, Bath PMW, Collier T. Should stroke trials adjust functional outcome for baseline prognostic
factors? Stroke [Internet]. 2009;40(3):888–94. doi: 10.1161/STROKEAHA.108.519207.PMID: 19164798.
Hauck WW, Anderson S, Marcus SM. Should we adjust for covariates in nonlinear regression analyses of
randomized trials? Control Clin Trials. 1998; 19(3): 249–56. doi: 10.1016/S0197-2456(97)00147-5.
Hernández AV, Steyerberg EW, Habbema JDF. Covariate adjustment in randomized controlled trials with
dichotomous outcomes increases statistical power and reduces sample size requirements. J Clin Epidemiol.
; 57(5): 454–60. doi: 10.1016/j.jclinepi.2003.09.014. PMID: 15196615.
Random Allocation - National Library of Medicine - PubMed Health. Available from:
https://www.ncbi.nlm.nih.gov/pubmedhealth/PMHT0025810/.
Barnett AG, van der Pols JC, Dobson AJ. Regression to the mean: What it is and how to deal with it. Int J
Epidemiol. 2005; 34(1): 215–20. doi: 10.1093/ije/dyh299. PMID: 15333621.
Covariate. In: Encyclopedia of Research Design. Thousand Oaks California 91320 United States: SAGE
Publications; 2018.
Senn S. Testing for baseline balance in clinical trials. Stat Med. 1994; 13(17): 1715–26. doi:
1002/sim.4780131703. PMID: 7997705.
Elkins MR. Assessing baseline comparability in randomised trials. J Physiother. 2015; 61(4): 228-30. doi:
1016/j.jphys.2015.07.005. PMID: 26364088.
Abel U, Koch A. The role of randomization in clinical studies: Myths and beliefs. J Clin Epidemiol. 1999;
(6): 487-97. PMID: 10408986.
Peterson RL, Tran M, Koffel J, Stovitz SD. Statistical testing of baseline differences in sports medicine
RCTs: a systematic evaluation. BMJ open Sport Exerc Med. 2017; 3(1): e000228.
Knol MJ, Groenwold RHH, Grobbee DE. P-values in baseline tables of randomised controlled trials are
inappropriate but still common in high impact journals. Eur J Prev Cardiol. 2012; 19(2): 231–2. PMID:
Austin PC, Manca A, Zwarenstein M, Juurlink DN, Stanbrook MB. A substantial and confusing variation
exists in handling of baseline covariates in randomized controlled trials: a review of trials published in
leading medical journals. J Clin Epidemiol. 2010; 63(2): 142–53. doi: 10.1016/j.jclinepi.2009.06.002.
PMID: 19716262.
Altman DG. Comparability of Randomised Groups. Stat. 1985; 34(1): 125.
de Boer MR, Waterlander WE, Kuijper L, Steenhuis I, Twisk J. Testing for baseline differences in
randomized controlled trials: an unhealthy research behavior that is hard to eradicate. Int J Behav Nutr Phys
Act. 2015; 12(1): 4. doi: 10.1186/s12966-015-0162-z. PMID: 25616598, PMCID: PMC4310023.
Moher D, Hopewell S, Schulz KF, Montori V, Gøtzsche PC, Devereaux PJ, et al. CONSORT 2010
explanation and elaboration: Updated guidelines for reporting parallel group randomised trials. Int J Surg.
; 10(1): 28–55. doi: 10.1016/j.ijsu.2011.10.001. PMID: 22036893.
Ciolino JD, Martin RH, Zhao W, Hill MD, Jauch EC, Palesch YY. Measuring continuous baseline
covariate imbalances in clinical trial data. Stat Methods Med Res. 2015; 24(2): 255–72. doi:
1177/0962280211416038. PMID: 21865270, PMCID: PMC4280338.
Senn S. Seven myths of randomisation in clinical trials. Stat Med. 2013; 32(9): 1439–50. doi:
1002/sim.5713. PMID: 23255195.
Bland JM, Altman DG. Comparisons within randomised groups can be very misleading. BMJ. 2011; 342.
doi: 10.1136/bmj.d561.
Nash R, Bunce C, Freemantle N, Doré CJ, Rogers CA. Ophthalmic statistics note 4: Analysing data from
randomised controlled trials with baseline and follow-up measurements. Br J Ophthalmol. 2014; 98(11):
–9. doi: 10.1136/bjophthalmol-2014-305614. PMID: 25107901, PMCID: PMC4215292.
Bland JM, Altman DG. Regression towards the mean. BMJ. 1994; 308(6942): 1499. doi:
1136/bmj.308.6942.1499. PMID: 8019287, PMCID: PMC2540330.
Bland JM, Altman DG. Comparisons against baseline within randomised groups are often used and can be
highly misleading. Trials. 2011; 12: 264. doi: 10.1186/1745-6215-12-264. PMID: 22192231, PMCID:
PMC3286439.
Altman DG, Doré CJ. Randomisation and baseline comparisons in clinical trials. Lancet. 1990; 335(8682):
–53. doi: 10.1016/0140-6736(90)90014-V.
Vollenweider D, Boyd CM, Puhan MA. High prevalence of potential biases threatens the interpretation of
trials in patients with chronic disease. BMC Med. 2011; 9. doi: 10.1186/1741-7015-9-73.
Zhang S, Paul J, Nantha-Aree M, Buckley N, Shahzad U, Cheng J, et al. Empirical comparison of four
baseline covariate adjustment methods in analysis of continuous outcomes in randomized controlled trials.
Clin Epidemiol. 2014; 6(1): 227–35. doi: 10.2147/CLEP.S56554. PMID: 25053894, PMCID:
PMC4105274.
Overall JE, Magee KN. Directional Baseline Differences And Type I Error Probabilities In Randomized
Clinical Trials. J Biopharm Stat. 1992; 2(2): 189–203. doi: 10.1080/10543409208835039. PMID: 1300213.
Kahan BC, Jairath V, Doré CJ, Morris TP. The risks and rewards of covariate adjustment in randomized
trials: An assessment of 12 outcomes from 8 studies. Trials. 2014; 15(1). doi: 10.1186/1745-6215-15-139.
Vickers AJ, Altman DG. Statistics Notes: Analysing controlled trials with baseline and follow up
measurements. BMJ. 2001; 323(7321): 1123–4. doi: 10.1136/bmj.323.7321.1123. PMID: 11701584,
PMCID: PMC1121605.
Törnqvist L, Vartia P, Vartia YO. How should relative changes be measured? Am Stat. 1985; 39(1): 43–6.
Stridbeck R, Zhang L, Han K. How to Analyze Change from Baseline: Absolute or Percentage Change？
How to Analyze Change from Baseline: Absolute or Percentage Change? Högskolan Dalarna. 2009; 1–17.
Vickers AJ. The use of percentage change from baseline as an outcome in a controlled trial is statistically
inefficient: A simulation study. BMC Med Res Methodol. 2001; 1: 1–4. doi: 10.1186/1471-2288-1-6.
PMID: 11459516, PMCID: PMC34605.
Downloads
Published
Issue
Section
License
Copyright (c) 2020 KNOWLEDGE KINGDOM PUBLISHING
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
