Description
This guidance describes FDA’s current recommendations regarding adjusting for covariates in the statistical analysis of randomized clinical trials in drug development programs. This guidance provides recommendations for the use of covariates in the analysis of randomized, parallel group clinical trials that are applicable to both superiority trials and noninferiority trials. The main focus of the guidance is on the use of prognostic baseline covariates to improve statistical efficiency for estimating and testing treatment effects. This guidance does not address use of covariates to control for confounding variables in non-randomized trials, the use of covariates in models to account for missing outcome data (National Research Council 2010), the use of covariate adjustment for analyzing longitudinal repeated measures data, the use of Bayesian methods for covariate adjustment, or the use of machine learning methods for covariate adjustment.
Key Topics
Terms and concepts identified from this document
Scope & Applicability
Product Classes
2Clinical investigations of drugs, including human drugs and biological products
Requires analytical comparability per ICH Q5E
Stakeholders
3Entity responsible for submitting applications under section 524B
Sponsors should consult regarding hybrid or augmented data approaches
Assist sponsors in the nonclinical evaluation
Regulatory Context
Regulatory Activities
1statistical analysis of randomized clinical trials in drug development programs
Document Types
2Document for protocol execution; The sponsor should develop a statistical analysis plan that is consistent with the trial protocol; Deviations from this plan must be justified
Defines the standard of veterinary practice and limits for anesthetic regimens
Attributes
8sponsors should include confidence intervals on all reported results
Leveraging Prognostic Baseline Variables to Gain Precision
improve statistical efficiency for estimating and testing treatment effects
Linear model is an acceptable method for estimating the average treatment effect
The average treatment effect is an example of an unconditional treatment effect
subgroup-specific conditional treatment effect can differ from the unconditional treatment effect
This is termed non-collapsibility, which is distinct from confounding
computing standard errors in stratified randomization
Technical Details
Testing Methods
10use of baseline covariate measurements for estimating and testing population-level treatment effects
adjustment for prognostic baseline covariates often leads to improved precision
includes generalized linear models with nonlinear link functions
used in studies with binary outcomes; Nonlinear models such as logistic regression are commonly used; Randomization Does Not Justify Logistic Regression
Covariate adjustment through a linear model is an acceptable method for estimating the average treatment effect
Covariate adjustment with nonlinear models is often used when the primary outcome is not continuous
the model is estimated using ordinary least squares
Agency recommends use of a robust standard error method such as the Huber-White sandwich standard error
An appropriate nonparametric bootstrap procedure can also be used
Cochran-Mantel-Haenszel methods are acceptable for the analysis of clinical trial data with binary endpoints
Processes
1Sponsors can adjust for baseline covariates in the analyses of efficacy endpoints in randomized clinical trials
Clinical Concepts
6baseline covariates that are likely to be associated with the primary endpoint
minimal impact on bias or the Type I error rate
Sponsors can adjust for baseline covariates in the analyses of efficacy endpoints
analysis of clinical trial data with binary endpoints
In trials with time-to-event outcomes, the hazard ratio can also be non-collapsible
The Prevention and Treatment of Missing Data in Clinical Trials
ICH References (2)
Statistical Principles for Clinical Trials; Discourages deterministic procedures due to high risk of bias; Notes that the use of Bayesian methods in clinical trials may be considered.
Statistical Principles for Clinical Trials: Addendum: Estimands and Sensitivity Analysis in Clinical Trials
Related MFDS Guidelines
Korean regulatory guidelines covering similar topics
See Also (8)
- E11A Pediatric Extrapolation
- M15 General Principles for Model-Informed Drug Development
- Clinical Pharmacology Data to Support a Demonstration of Biosimilarity to a Reference Product
- Q6A Specifications: Test Procedures and Acceptance Criteria for New Drug Substances and New Drug Products: Chemical Substances
- Rare Diseases: Considerations for the Development of Drugs and Biological Products
- Q3C Impurities: Residual Solvents_2011
- Providing Regulatory Submissions in Electronic Format --Content of the Risk Evaluation and Mitigation Strategies Document Using Structured Product Labeling: Guidance for Industry
- Q4B Annex 5: Disintegration Test General Chapter