Pharmacometric covariate analyses support both mechanistic understanding and clinical decision-making, that is, two different objectives which require different analysis targets. Adopting the ICH E9(R1) estimand framework clarifies this distinction, reconciling mechanistic modeling (conditional covariate effects) with regulatory and clinical needs (unconditional covariate effects), clarifying that estimand definition, i.e. the objective, and not the estimator, is the first choice to make in covariate modeling. This structured approach optimizes quantitative evidence for communicating clinical impact and patient care.
Jonsson et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: