On Robustness of Individualized Decision Rules
From MaRDI portal
Abstract: With the emergence of precision medicine, estimating optimal individualized decision rules (IDRs) has attracted tremendous attention in many scientific areas. Most existing literature has focused on finding optimal IDRs that can maximize the expected outcome for each individual. Motivated by complex individualized decision making procedures and the popular conditional value at risk (CVaR) measure, we propose a new robust criterion to estimate optimal IDRs in order to control the average lower tail of the individuals' outcomes. In addition to improving the individualized expected outcome, our proposed criterion takes risks into consideration, and thus the resulting IDRs can prevent adverse events. The optimal IDR under our criterion can be interpreted as the decision rule that maximizes the ``worst-case" scenario of the individualized outcome when the underlying distribution is perturbed within a constrained set. An efficient non-convex optimization algorithm is proposed with convergence guarantees. We investigate theoretical properties for our estimated optimal IDRs under the proposed criterion such as consistency and finite sample error bounds. Simulation studies and a real data application are used to further demonstrate the robust performance of our methods. Several extensions of the proposed method are also discussed.
Cites work
- scientific article; zbMATH DE number 3465097 (Why is no real title available?)
- scientific article; zbMATH DE number 6542809 (Why is no real title available?)
- A Sparse Random Projection-Based Test for Overall Qualitative Treatment Effects
- A generalization error for Q-learning
- A robust method for estimating optimal treatment regimes
- A simple method for estimating interactions between a treatment and a large number of covariates
- Adaptive contrast weighted learning for multi-stage multi-treatment decision-making
- Asymptotics for statistical treatment rules
- Coherent measures of risk
- Computing B-stationary points of nonsmooth DC programs
- Concordance-assisted learning for estimating optimal individualized treatment regimes
- D-learning to estimate optimal individual treatment rules
- Doubly robust learning for estimating individualized treatment with censored data
- Estimating individualized treatment rules for ordinal treatments
- Estimating individualized treatment rules using outcome weighted learning
- Estimation of individualized decision rules based on an optimized covariate-dependent equivalent of random outcomes
- Expected Utility, Penalty Functions, and Duality in Stochastic Nonlinear Programming
- Fast rates for support vector machines using Gaussian kernels
- High-dimensional \(A\)-learning for optimal dynamic treatment regimes
- Inferring welfare maximizing treatment assignment under budget constraints
- Learning optimal distributionally robust individualized treatment rules
- Minimax regret treatment choice with finite samples
- Modern nonconvex nondifferentiable optimization
- Multi-Armed Angle-Based Direct Learning for Estimating Optimal Individualized Treatment Rules With Various Outcomes
- Multicategory outcome weighted margin-based learning for estimating individualized treatment rules
- Optimal Dynamic Treatment Regimes
- Performance guarantees for individualized treatment rules
- Policy learning with observational data
- Quantile-optimal treatment regimes
- Risk-constrained reinforcement learning with percentile risk criteria
- Some remarks on the value-at-risk and the conditional value-at-risk
- Statistical treatment choice based on asymmetric minimax regret criteria
- Statistical treatment rules for heterogeneous populations.
- The Oxford handbook of Bayesian econometrics
- The Theory of Statistical Decision
- Tree based weighted learning for estimating individualized treatment rules with censored data
- Tree-based methods for individualized treatment regimes
- Using decision lists to construct interpretable and parsimonious treatment regimes
- When is ATE enough? Risk aversion and inequality aversion in evaluating training programs
- Who should be treated? Empirical welfare maximization methods for treatment choice
- Q- and A-learning methods for estimating optimal dynamic treatment regimes
Cited in
(8)- Federated learning of robust individualized decision rules with application to heterogeneous multihospital sepsis population
- Estimating expectile-optimal treatment regimes
- Optimal Individualized Decision Rules Using Instrumental Variable Methods
- scientific article; zbMATH DE number 3869018 (Why is no real title available?)
- scientific article; zbMATH DE number 773974 (Why is no real title available?)
- Online statistical inference in decision-making with matrix context
- Treatment learning with Gini constraints by Heaviside composite optimization and a progressive method
- scientific article; zbMATH DE number 773964 (Why is no real title available?)
This page was built for publication: On Robustness of Individualized Decision Rules
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6077600)
