Adjusting for Covariates in Randomized Clinical Trials

The FDA has issued a new guidance together with a Guidance Snapshot which describes the agency's current thinking regarding adjusting for covariates in the statistical analysis of randomized clinical trials. Sponsors should adjust for baseline covariates that are strongly associated with an outcome in a clinical trial population. According to the agency, the new guidance is consistent with the ICH guidance E9(R1) Statistical Principles for Clinical Trials: Addendum: Estimands and Sensitivity Analysis in Clinical Trials.

Linear and Nonlinear Models

Covariate adjustment means the use of information measured on a subject before the time of randomization for estimating and testing treatment effects between randomized groups. "It is desirable to study a population in clinical trials that reflects the variability of the target population but doing so may make it harder to detect a treatment effect. Covariate adjustment allows for incorporation of prespecified prognostic factors, or factors that predict the likely outcome of a disease or ailment, in the statistical analysis and can result in narrower confidence intervals and a greater statistical power to detect treatment effects", the guideline says.

The FDA guidance discusses general recommendations for performing covariate adjustment using linear and nonlinear models. Covariate adjustment using these models can be used to improve statistical efficiency.

  • In linear models, adjustment for prognostic baseline covariates often leads to improved precision by reducing residual variance.
  • When adjusting for covariates based on nonlinear regression models there are additional considerations that arise because inclusion of baseline covariates in a regression model can change the treatment effect that is being estimated.

The guideline finalizes the draft guidance of the same title issued on 21 May 2021. Changes from the draft to the final guidance include updated and clarified recommendations on computing standard errors, stratified randomization, treatment by covariate interactions, and additional methods.

More information is provided in FDA's Guidance Adjusting for Covariates in Randomized Clinical Trials for Drugs and Biological Products.

Go back


Stay informed with the GMP Newsletters from ECA

GMP Newsletter

The ECA offers various free of charge GMP newsletters for which you can subscribe to according to your needs.

To subscribe, please click here.