Analysis of Covariance (ANCOVA): Optimal Method for Analyzing Pre-post Data with Repeated Measures Two Groups under Experimental Design in Health Science Research
Article Sidebar
Main Article Content
Abstract
In health science research, measuring for two groups of pre-post data with repeated measures can be found in an experimental design, including randomized and quasi-experiments. Most of the aim was to evaluate and compare the interesting outcome that was affected differently between the intervention and control groups. Numbers of statistical methods have been adopted for analyzing these kinds of research, but most researchers are still confused about utilizing information to make decisions about choosing the optimal method. This may cause misunderstandings that affect the accuracy and certainty of the results. Therefore, the objective of this article is to introduce and synthesize the six statistical methods for analyzing pre-post data with repeated measures in two groups, including (1) comparing of pre-post data with a t-test, (2) one-way analysis of variance (one-way ANOVA) with post-outcome, (3) one-way ANOVA with change score, (4) one-way ANOVA with percent changes, (5) repeated measures ANOVA, and (6) analysis of covariance (ANCOVA). The results found that ANCOVA is a simple and efficient approach for analyzing pre-post data with repeated measures in two groups compared with other methods, especially in randomized design. In a quasi-experimental design, the cluster or hierarchy distribution of the characteristics is an issue that should be considered before being allocated to the group. However, there it is still necessary to report of the results of each assumption examination and comprehensively reporting of study results consistent with research questions.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
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. Clinical Epidemiology 2014; 6: 227-235.
Pocock SJ, Assmann SE, Enos LE, Kasten LE. Subgroup analysis, covariate adjustment and baseline comparisons in clinical trial reporting: current practice and problems. Stat Med 2002; 21(19): 2917-30.
Wan F. Statistical analysis of two arm randomized pre-post designs with one post-treatment measurement. BMC Medical Research Methodology 2021; 21(1): 150.
Clifton L, Clifton DA. The correlation between baseline score and post-intervention score, and its implications for statistical analysis. Trials 2019; 20(1): 43.
Brocklehurst P, Hoare Z. How to design a randomised controlled trial. British Dental Journal 2017; 222(9): 721-726.
Harris AD, McGregor JC, Perencevich EN, Furuno JP, Zhu J, Peterson DE, et al. The use and interpretation of quasi-experimental studies in medical informatics. Journal of the American Medical Informatics Association 2006; 13(1): 16-23.
Chidambaram AG, Josephson M. Clinical research study designs: The essentials. Pediatric Investigation 2019; 3(4): 245-252.
McLeod C, Norman R, Litton E, Saville BR, Webb S, Snelling TL. Choosing primary endpoints for clinical trials of health care interventions. Contemporary Clinical Trials Communications 2019; 16: 100486-100486.
Wei L, Zhang J. Analysis of Data with Imbalance in the Baseline Outcome Variable for Randomized Clinical Trials. Drug Information Journal / Drug Information Association 2001; 35(4): 1201-1214.
Breukelen V, Gerard JP. ANCOVA versus change from baseline: more power in randomized studies, more bias in nonrandomized studies [corrected]. J Clin Epidemiol 2006; 59(9): 920-5.
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(5): 991-4.
Groenwold RHH, Goeman JJ, Cessie SL, Dekkers OM. Multiple testing: when is many too much? European Journal of Endocrinology 2021; 184(3): E11-E14.
Vickers AJ, Altman DG, Analysing controlled trials with baseline and follow up measurements. BMJ 2001; 323(7321): 1123.
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 Medical Research Methodology 2014; 14(1): 49.
Dimitrov DM, Rumrill PD Jr. Pretest-posttest designs and measurement of change. Work 2003; 20(2): 159-65.
Jennings M, Cribbie R. Comparing Pre-Post Change Across Groups: Guidelines for Choosing between Difference Scores, ANCOVA, and Residual Change Scores. Journal of Data Science 2021; 14: 205-230.
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.
Lee U, Garcia TP, Carroll RJ, Gilbreath KR, Wu G. Analysis of repeated measures data in nutrition research. Front Biosci (Landmark Ed) 2019; 24(8): 1377-1389.
Curran-Everett D, Williams CL. Explorations in statistics: the analysis of change. Advances in Physiology Education 2015; 39(2): 49-54.
Khammar A, Yarahmadi M, Madadizadeh F. What Is Analysis of Covariance (ANCOVA) and How to Correctly Report Its Results in Medical Research? Iranian Journal of Public Health 2020; 49(5): 1016-1017.
Breukelen V, Gerard JP. ANCOVA Versus CHANGE From Baseline in Nonrandomized Studies: The Difference. Multivariate Behavioral Research 2013; 48(6): 895-922.
Lord FM. A paradox in the interpretation of group comparisons. Psychol Bull 1967; 68(5): 304-5.