# Current practice on covariate adjustment and stratified analysis —based on survey results by ASA oncology estimand working group conditional and marginal effect task force

## TL;DR

A survey of biostatisticians reveals gaps in understanding how to properly use covariate adjustment in clinical trials, especially with non-linear models and different estimands.

## Contribution

The paper provides insights into current practices and challenges in covariate adjustment and stratified analysis based on a global survey of biostatisticians.

## Key findings

- Survey results show gaps in understanding statistical models targeting different estimands for non-collapsable measures.
- Practitioners often add extra covariates in stratified analyses and pool small strata to avoid estimation issues.
- There is a need for more training and clarification on covariate adjustment practices.

## Abstract

The 2023 FDA's guidance on covariate adjustment encourages the judicious use of baseline covariates to enhance efficiency. However, when performing covariate adjustment in non-linear models, care must be taken on preserving estimation of the target estimand as introduced by the ICH E9(R1) addendum. To understand the current practices of covariate adjustment within the context of the estimands framework across various sectors and associated challenges, the conditional and marginal effect task force within the ASA Oncology Estimand working group conducted a survey.

The target participants of the survey were biostatisticians who support study designs and analyses in clinical trials in the drug development industry or in academia. A total of 19 questions were included in an online survey that was distributed between June and July 2023. The survey was disseminated via a shared online link to contacts from more than 50 organisations. The survey response and experience from the working group on challenges of covariate adjustment and stratified analysis are summarized and discussed in detail.

A total of 122 responses were received from 12 countries. The survey results suggest that there remain gaps in the understanding of different statistical analysis models which may target different estimands for non-collapsable measures, highlighting the need for further clarification and training on this topic. In terms of general practice, when performing the analysis under stratified randomization, additional covariates may be added in the analysis model beyond those used for stratifying randomization, and small strata may be pooled to avoid the estimation challenges.

This paper summarises the results from this survey and based on our findings, we provide some recommendations to establish consistency and clarifications on any widely misunderstood practices.

The online version contains supplementary material available at 10.1186/s12874-025-02670-7.