Related Experiment Video
Updated: Aug 6, 2026

Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Should We Adjust for Baseline Covariates in Randomized Clinical Trials?
1Department of Biostatistics, Yale University School of Public Health, New Haven, Connecticut.
Introduction:
The primary goal in randomized clinical trials (RCTs) is to estimate the causal effects of interventions. Since prognostic factors can also affect outcomes, RCTs often employ covariate-adjusted analyses. It is important to review reasons for adjustment, advantages and disadvantages of adjustments, and reiterate best practices.
Methods:
We reviewed guidelines and recommendations for covariate adjustment from authoritative sources, including the European Medicines Agency and the US Food and Drug Administration, as well as recent studies and meta-analyses.
Results:
While post hoc adjustments for baseline covariates may lead to bias, unadjusted analyses and prespecified adjusted analyses are valid approaches for RCTs. Adjustment for highly prognostic variables can enhance precision and power. Direct adjustment methods and more complex methods, such as inverse probability of treatment weighting, can be applied.
Conclusions:
Covariate adjustments should be prespecified, theoretically justified, and transparently reported. This approach aligns with the CONSORT 2025 guidelines, emphasizing methodological rigor and transparency.
Related Concept Videos
Randomized Experiments
Simple randomization
Simple...
Blinding
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Bias in Epidemiological Studies
Confounding in Epidemiological Studies