Nonparanormal Adjusted Marginal Inference

2025-03-03

AI Summary

Covariate adjustment in clinical trials improves estimation precision but alters the interpretation of marginal effects—such as odds ratios (ORs) and hazard ratios (HRs)—in logistic or Cox regression, compromising cross-model comparability and violating non-collapsibility. Method: We propose the first nonparametric normalizing joint modeling framework whose native parameters are marginal effects (e.g., log-OR, log-HR, Cohen’s *d*). It integrates nonparametric normalizing transformations, joint maximum likelihood estimation, and marginal identification, implemented in the open-source R package *tram*. Contribution/Results: Theoretically justified and empirically validated, our framework preserves marginal interpretability while substantially enhancing estimation accuracy. Simulation studies and three real-world clinical studies demonstrate its ability to uniformly handle diverse outcome types (binary, survival, continuous), simultaneously report explained variance (e.g., *R*²) and prognostic strength measures for covariates, and outperform conventional adjustment approaches.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Nonmonotonic Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Treatment effects for assessing the efficacy of a novel therapy are typically defined as measures comparing the marginal outcome distributions observed in two or more study arms. Although one can estimate such effects from the observed outcome distributions obtained from proper randomisation, covariate adjustment is recommended to increase precision in randomised clinical trials. For important treatment effects, such as odds or hazard ratios, conditioning on covariates in binary logistic or proportional hazards models changes the interpretation of the treatment effect under noncollapsibility and conditioning on different sets of covariates renders the resulting effect estimates incomparable. We propose a novel nonparanormal model formulation for adjusted marginal inference. This model for the joint distribution of outcome and covariates directly features a marginally defined treatment effect parameter, such as a marginal odds or hazard ratio. Marginal distributions are modelled by transformation models allowing broad applicability to diverse outcome types. Joint maximum likelihood estimation of all model parameters is performed. From the parameters not only the marginal treatment effect of interest can be identified but also an overall coefficient of determination and covariate-specific measures of prognostic strength can be derived. A reference implementation of this novel method is available in R add-on package tram. For the special case of Cohen's standardised mean difference d, we theoretically show that adjusting for an informative prognostic variable improves the precision of this marginal, noncollapsible effect. Empirical results confirm this not only for Cohen's d but also for log-odds ratios and log-hazard ratios in simulations and three applications.

Problem

• Estimating treatment effects with covariate adjustment in clinical trials
• Addressing incomparability of effect estimates from different covariate sets
• Improving precision of marginal noncollapsible effects via prognostic variables

Innovation

• Nonparanormal model for adjusted marginal inference
• Directly features marginal treatment effect parameters
• Improves precision with informative prognostic variables