Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2401.10867

Learning Optimal Dynamic Treatment Regimes from Longitudinal Data

Nicholas T. Williams·Katherine L. Hoffman Iván Díaz·Kara E. Rudolph
View original source ↗Read source document ↗Export metadata ↓

Abstract

Studies often report estimates of the average treatment effect. While the ATE summarizes the effect of a treatment on average, it does not provide any information about the effect of treatment within any individual. A treatment strategy that uses an individual's information to tailor treatment to maximize benefit is known as an optimal dynamic treatment rule. Treatment, however, is typically not limited to a single point in time; consequently, learning an optimal rule for a time-varying treatment may involve not just learning the extent to which the comparative treatments' benefits vary across the characteristics of individuals, but also learning the extent to which the comparative treatments' benefits vary as relevant circumstances evolve within an individual. The goal of this paper is to provide a tutorial for estimating ODTR from longitudinal observational and clinical trial data for applied researchers. We describe an approach that uses a doubly-robust unbiased transformation of the conditional average treatment effect. We then learn a time-varying ODTR for when to increase buprenorphine-naloxone dose to minimize return-to-regular-opioid-use among patients with opioid use disorder. Our analysis highlights the utility of ODTRs in the context of sequential decision making: the learned ODTR outperforms a clinically defined strategy.

Explore related subjects

stat.ME

Keep this discovery

BibTeXRIS

Nicholas T. Williams, Katherine L. Hoffman Iván Díaz, Kara E. Rudolph. 2024-01-19. Learning Optimal Dynamic Treatment Regimes from Longitudinal Data. https://doi.org/10.1093/aje%2Fkwae122

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Surprise Reduction and Nullification in Bayesian and Inverse Bayesian Inference under Ambiguous Prediction-Error Attribution

In non-stationary environments, prediction errors may signal environmental change or transient outliers, and adaptive systems must track such changes without overreacting to outliers. We distinguish surprise reduction, which updates beliefs to fit observations, from surprise nullification, which weakens constraints imposed by the predictive structure, and formalize both within Bayesian and inverse Bayesian (BIB) inference. Belief and likelihood updates are derived from variational objectives sharing a nullification strength, determined endogenously by minimizing surprise under the candidate post-update predictive distribution. In the Gaussian case, nullification expands belief and likelihood variances by a common factor relative to standard Bayesian updating, leaving the ratio unchanged. BIB thus defers attribution of the prediction error, committing to neither latent-state change nor observation-process uncertainty. The nullification strength is carried over as a candidate and is maintained or released according to the predictive surprise of the next observation. In a mean estimation task with outliers and changepoints, no scanned parameter setting of a Sage-Husa-type adaptive Kalman filter, fixed-strength BIB variant, or belief-forgetting-only variant outperforms BIB in both changepoint tracking and post-outlier stability. An oracle-informed reduced Bayesian model tracks changepoints better but is less stable after outliers. Although BIB maintains no explicit hypotheses about changepoints or outliers, it generates event-dependent dynamics. The learning rate increases after changepoints, whereas after outliers, nullification is released, and this increase is suppressed. Deferring attribution and letting subsequent observations differentiate the responses may constitute a principle of adaptive inference in non-stationary environments.

stat.ME↗
arXiv2026

Generalized Ridge Refitting for the Lasso and Prediction Improvement Bounds

We study a class of Lasso based estimators obtained by applying a quadratic correction on the Lasso equicorrelation set. The penalty matrix determines both the magnitude and geometry of the correction and contains, among other cases, the isotropic Lasso--Ridge correction, least squares refitting, Gram proportional interpolation between the Lasso and least squares, and coordinate specific penalties. We first derive a closed form representation and isolate the positive gain component of the resulting prediction improvement. We then control the remaining stochastic linear term in expectation by localizing the random signed equicorrelation model around a deterministic reference support. This yields a finite sample expectation bound that explicitly accounts for the randomness induced by Lasso model selection. The resulting decomposition provides a unified framework for understanding when Lasso based quadratic corrections can improve prediction.

stat.ME↗
arXiv2026

Discretization in covariate-adaptive randomization: gains and losses

Covariate-adaptive randomization(CAR) is widely implemented in clinical trials to balance prognostic covariates across treatment arms. Continuous covariates are often discretized into strata in practice, yet their consequences are not clearly understood. This paper provides a comprehensive study of the impact of discretization on both the CAR design process and the inferential results thereafter. We establish the asymptotic properties of both imbalance measures and treatment effect estimators under discretized and non-discretized settings. Practical recommendations are given on when and how discretization should be employed. We show that discretization in design is generally recommended, as it enhances robustness against model misspecification. However, if the true model is known, the most efficient strategy is to balance covariates according to that model in the design. The theoretical results are corroborated by extensive simulation studies and an empirical application to a diabetes trial dataset. Together, the results clarify the gains and losses of discretization in CAR and pave the way for learning impact of discretization to other designs and beyond.

stat.ME↗