Abstract
Randomized controlled trials (RCTs) play a fundamental role in establishing evidence on benefits of diet changes in nutrition. There is, however, little literature on how to analyze data obtained from such trials. This tutorial provides a detailed introduction to the statistical analysis of parallel-arm RCTs in nutrition by means of modern statistical methodology, i.e., analysis of covariance and linear mixed models are informed using specific information about the trial design. Focus will be on understanding how the trial design and possibly other aspects of the trial influence the subsequent statistical analysis. All steps of the statistical analysis will be covered and a practical example is also provided.
This is a preview of subscription content, access via your institution
Access options
Subscribe to this journal
Receive 12 print issues and online access
$259.00 per year
only $21.58 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
Similar content being viewed by others
Code availability
In practice the specification of the above-mentioned statistical models depends on the statistical software used. A detailed example using the statistical environment R [42] is provided as online supplementary material (https://doi.org/10.5281/zenodo.3978040).
Change history
14 October 2020
In the original version of this article, the legends to Figs. 2, 3 and 4 were inadvertently swapped. This has now been corrected in the PDF and HTML versions of the article.
References
Boushey CJ, Harris J, Bruemmer B, Archer SL. Publishing nutrition research: a review of sampling, sample size, statistical analysis, and other key elements of manuscript preparation, Part 2. J Am Diet Assoc. 2008;108:679–88. https://doi.org/10.1016/j.jada.2008.01.002.
Harris JE, Sheean PM, Gleason PM, Bruemmer B, Boushey C. Publishing nutrition research: a review of multivariate techniques—Part 2: analysis of variance. J Acad Nutr Diet. 2012;112:90–98. https://doi.org/10.1016/j.jada.2011.09.037.
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;1:6. https://doi.org/10.1186/1471-2288-1-6.
Van Breukelen GJP. ANCOVA versus change from baseline had more power in randomized studies and more bias in nonrandomized studies. J Clin Epidemiol. 2006;59:920–5. https://doi.org/10.1016/j.jclinepi.2006.02.007.
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;14:49. https://doi.org/10.1186/1471-2288-14-49.
Bland JM, Altman DG. Best (but oft forgotten) practices: testing for treatment effects in randomized trials by separate analyses of changes from baseline in each group is a misleading approach. Am J Clin Nutr. 2015;102:991–4. https://doi.org/10.3945/ajcn.115.119768.
Allison DB, Antoine LH, George BJ. Incorrect statistical method in parallel-groups RCT led to unsubstantiated conclusions. Lipids Health Dis. 2016;15:77. https://doi.org/10.1186/s12944-016-0242-3.
Ten Have T, Normand S, Marcus S, Brown C, Lavori P, Duan N. Intent-to-treat vs. non-intent-to-treat analyses under treatment non-adherence in mental health randomized trials. Psychiatr Ann. 2008;38:772–83. https://doi.org/10.3928/00485713-20081201-10.
Mostazir M, Taylor RS, Henley W, Watkins E. An overview of statistical methods for handling nonadherence to intervention protocol in randomized control trials: a methodological review. J Clin Epidemiol. 2019;108:121–31. https://doi.org/10.1016/j.jclinepi.2018.12.002.
Rochon J. Supplementing the intent-to-treat analysis: accounting for covariates observed postrandomization in clinical trials. J Am Stat Assoc. 1995;90:292–300. https://doi.org/10.1080/01621459.1995.10476512.
Lee PH. Covariate adjustments in randomized controlled trials increased study power and reduced biasedness of effect size estimation. J Clin Epidemiol. 2016;76:137–46. https://doi.org/10.1016/j.jclinepi.2016.02.004.
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;15:139. https://doi.org/10.1186/1745-6215-15-139.
Raab GM, Day S, Jill Sales J. How to select covariates to include in the analysis of a clinical trial. Control Clin Trials. 2000;21:330–42. https://doi.org/10.1016/S0197-2456(00)00061-1.
Laursen RP, Larnkjær A, Ritz C, Hauger H, Michaelsen KF, Mølgaard C. Probiotics and child care absence due to infections: a randomized controlled trial. Pediatrics. 2017;140:e20170735. https://doi.org/10.1542/peds.2017-0735.
Lachin JM. Properties of simple randomization in clinical trials. Control Clin Trials. 1988;9:312–26. https://doi.org/10.1016/0197-2456(88)90046-3.
Matts JP, Lachin JM. Properties of permuted-block randomization in clinical trials. Control Clin Trials. 1988;9:327–44. https://doi.org/10.1016/0197-2456(88)90047-5.
Bell ML, Rabe BA. The mixed model for repeated measures for cluster randomized trials: a simulation study investigating bias and type I error with missing continuous data. Trials. 2020;21:148. https://doi.org/10.1186/s13063-020-4114-9.
Pals SL, Murray DM, Alfano CM, Shadish WR, Hannan PJ, Baker WL. Individually randomized group treatment trials: a critical appraisal of frequently used design and analytic approaches. Am J Public Health. 2008;98:1418–24. https://doi.org/10.2105/AJPH.2007.127027.
Kernan WN, Viscoli CM, Makuch RW, Brass LM, Horwitz RI. Stratified randomization for clinical trials. J Clin Epidemiol. 1999;52:19–26. https://doi.org/10.1016/S0895-4356(98)00138-3.
Kahan BC, Morris TP. Reporting and analysis of trials using stratified randomisation in leading medical journals: review and reanalysis. BMJ. 2012;345:e5840. https://doi.org/10.1136/bmj.e5840.
Kangas ST, Salpéteur C, Nikièma V, Talley L, Ritz C, Friis H, et al. Impact of reduced dose of ready-to-use therapeutic foods in children with uncomplicated severe acute malnutrition: a randomised non-inferiority trial in Burkina Faso. PLoS Med. 2019;16:e1002887. https://doi.org/10.1371/journal.pmed.1002887.
Geiker NRW, Ritz C, Pedersen SD, Larsen TM, Hill JO, Astrup A. A weight-loss program adapted to the menstrual cycle increases weight loss in healthy, overweight, premenopausal women: a 6-mo randomized controlled trial. Am J Clin Nutr. 2016;104:15–20. https://doi.org/10.3945/ajcn.115.126565.
Sedgwick P. Standard deviation versus standard error. BMJ. 2011;343:d8010. https://doi.org/10.1136/bmj.d8010.
Moher D, Sally Hopewell S, Schulz KF, Montori V, Götzsche PC, Devereaux PJ, et al. ConSoRT 2010 explanation and elaboration: updated guidelines for reporting parallel group randomised trials. BMJ. 2010;340:c869. https://doi.org/10.1136/bmj.c869.
Senn S. Testing for baseline balance in clinical trials. Stat Med. 1994;13:1715–26. https://doi.org/10.1002/sim.4780131703.
Roberts C, Torgerson DJ. Baseline imbalance in randomised controlled trials. BMJ. 1999;319:185. https://doi.org/10.1136/bmj.319.7203.185.
Kramer MS, Chalmers B, Hodnett ED, Sevkovskaya Z, Dzikovich I, Shapiro S, et al. Promotion of Breastfeeding Intervention Trial (PROBIT): a randomized trial in the Republic of Belarus. JAMA. 2001;285:413–20. https://doi.org/10.1001/jama.285.4.413.
Altman DG, Royston P. The cost of dichotomising continuous variables. BMJ. 2006;332:1080. https://doi.org/10.1136/bmj.332.7549.1080.
Van der Vaart AW. Asymptotic statistics. Cambridge: Cambridge University Press; 1998.
Weisberg S. Applied linear regression. 3rd ed. Hoboken: Wiley & Sons; 2005.
Senn S. Change from baseline and analysis of covariance revisited. Stat Med. 2006;25:2334–44. https://doi.org/10.1002/sim.2682.
Thompson DD, Lingsma HF, Whiteley WN, Murray GD, Steyerberg EW. Covariate adjustment had similar benefits in small and large randomized controlled trials. J Clin Epidemiol. 2015;68:1068–75. https://doi.org/10.1016/j.jclinepi.2014.11.001.
Tsiatis AA, Davidian M, Zhang M, Lu X. Covariate adjustment for two-sample treatment comparisons in randomized clinical trials: a principled yet flexible approach. Stat Med. 2008;27:4658–77. https://doi.org/10.1002/sim.3113.
Wang B, Ogburn EL, Rosenblum M. Analysis of covariance in randomized trials: more precision and valid confidence intervals, without model assumptions. Biometrics. 2019;75:1391–1400. https://doi.org/10.1111/biom.13062.
Bartlett JW. Robustness of ANCOVA in randomized trials with unequal randomization. Biometrics. 2020;76:1036–8. https://doi.org/10.1111/biom.13184.
Verbeke G, Lesaffre E. The effect of misspecifying the random-effects distribution in linear mixed models for longitudinal data. Comput Stat Data Anal. 1997;23:541–56. https://doi.org/10.1016/S0167-9473(96)00047-3.
Jiang J. REML estimation: asymptotic behavior and related topics. Ann Stat. 1996;24:255–86.
Fitzmaurice GM, Laird NM, Ware JH. Applied longitudinal analysis. 2nd ed. Hoboken: Wiley & Sons; 2011.
Liang K-Y, Zeger SL. Longitudinal data analysis of continuous and discrete responses for pre–post designs. Sankhya. 2000;62:134–48. https://doi.org/10.2307/25053123.
Liu GF, Lu K, Mogg R, Mallick M, Mehrotra DV. Should baseline be a covariate or dependent variable in analyses of change from baseline in clinical trials? Stat Med. 2009;28:2509–30. https://doi.org/10.1002/sim.3639.
Raziani F, Tholstrup T, Kristensen MD, Svanegaard ML, Ritz C, Astrup A, et al. High intake of regular-fat cheese compared with reduced-fat cheese does not affect LDL cholesterol or risk markers of the metabolic syndrome: a randomized controlled trial. Am J Clin Nutr. 2016;104:973–81. https://doi.org/10.3945/ajcn.116.134932.
R Core Team. R: a language and environment for statistical computing. Vienna: R Foundation for Statistical Computing; 2020.
Lenth RV. Least-squares means: the R package LSmeans. J Stat Softw. 2016;69:1–33. https://doi.org/10.18637/jss.v069.i01.
Duan N. Smearing estimate: a nonparametric retransformation method. J Am Stat Assoc. 1983;78:605–10. https://doi.org/10.2307/2288126.
Laursen R, Dalskov S, Damsgaard CT, Ritz C. Back-transformation of treatment differences—an approximate method. Eur J Clin Nutr. 2014;68:277–80. https://doi.org/10.1038/ejcn.2013.259.
Yilma D, Kæstel P, Olsen MF, Abdissa A, Tesfaye M, Girma T, et al. Change in serum 25-hydroxyvitamin D with antiretroviral treatment initiation and nutritional intervention in HIV-positive adults. Br J Nutr. 2016;116:1720–7. https://doi.org/10.1017/S0007114516003743.
Saquib N, Saquib J, Ioannidis JPA. Practices and impact of primary outcome adjustment in randomized controlled trials: meta-epidemiologic study. BMJ. 2013;347:f4313. https://doi.org/10.1136/bmj.f4313.
DeMets DL, Cook TD, Buhr KA. Guidelines for statistical analysis plans. JAMA. 2017;318:2301–3. https://doi.org/10.1001/jama.2017.18954.
Hothorn LA. The two-step approach—a significant ANOVA F-test before Dunnett’s comparisons against a control—is not recommended. Commun Stat—Theory Methods. 2016;45:3332–43. https://doi.org/10.1080/03610926.2014.902225.
Greenland S, Robins J, Pearl J. Confounding and collapsibility in causal inference. Stat Sci. 1999;14:29–46.
Twisk J, Bosman L, Hoekstra T, Rijnhart J, Welten M, Heymans M. Different ways to estimate treatment effects in randomised controlled trials. Contemp Clin Trials Commun. 2018;10:80–85. https://doi.org/10.1016/j.conctc.2018.03.008.
Harris JE, Raynor HA. Crossover designs in nutrition and dietetics research. J Acad Nutr Diet. 2017;117:1023–30. https://doi.org/10.1016/j.jand.2017.03.017.
Ritz C, Rønn B. Estimands: improving inference in randomized controlled trials in clinical nutrition in the presence of missing values. Eur J Clin Nutr. 2018;72:1291–5. https://doi.org/10.1038/s41430-018-0207-x.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author declares that he has no conflict of interest.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ritz, C. Statistical analysis of continuous outcomes from parallel-arm randomized controlled trials in nutrition—a tutorial. Eur J Clin Nutr 75, 160–171 (2021). https://doi.org/10.1038/s41430-020-00750-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41430-020-00750-z
This article is cited by
-
Multidimensional individualized nutritional therapy for individuals with severe chronic obstructive pulmonary disease: study protocol for a registry-based randomized controlled trial
Trials (2023)
-
Promoting work ability with a wearable activity tracker in working age individuals with hip and/or knee osteoarthritis: a randomized controlled trial
BMC Musculoskeletal Disorders (2022)
-
Metabotyping for Precision Nutrition and Weight Management: Hype or Hope?
Current Nutrition Reports (2022)