Optimal subgroup selection
From MaRDI portal
Abstract: In clinical trials and other applications, we often see regions of the feature space that appear to exhibit interesting behaviour, but it is unclear whether these observed phenomena are reflected at the population level. Focusing on a regression setting, we consider the subgroup selection challenge of identifying a region of the feature space on which the regression function exceeds a pre-determined threshold. We formulate the problem as one of constrained optimisation, where we seek a low-complexity, data-dependent selection set on which, with a guaranteed probability, the regression function is uniformly at least as large as the threshold; subject to this constraint, we would like the region to contain as much mass under the marginal feature distribution as possible. This leads to a natural notion of regret, and our main contribution is to determine the minimax optimal rate for this regret in both the sample size and the Type I error probability. The rate involves a delicate interplay between parameters that control the smoothness of the regression function, as well as exponents that quantify the extent to which the optimal selection set at the population level can be approximated by families of well-behaved subsets. Finally, we expand the scope of our previous results by illustrating how they may be generalised to a treatment and control setting, where interest lies in the heterogeneous treatment effect.
Recommendations
- Inference on Selected Subgroups in Clinical Trials
- Maximin projection learning for optimal treatment decision with heterogeneous individualized treatment effects
- Exploratory subgroup analysis in clinical trials by model selection
- Subgroup identification and variable selection for treatment decision making
- A General Framework for Subgroup Detection via One-Step Value Difference Estimation
Cites work
- A constrained risk inequality with applications to nonparametric functional estimation
- A Neyman–Pearson Approach to Statistical Learning
- Adaptive confidence interval for pointwise curve estimation.
- Adaptive transfer learning
- Asymptotic normality of plug-in level set estimates
- Asymptotics and optimal bandwidth for nonparametric estimation of density level sets
- Asymptotics and optimal bandwidth selection for highest density region estimation
- Bandwidth selection for kernel density estimators of multivariate level sets and highest density regions
- Confidence bands in density estimation
- Confidence regions for level sets
- Design and analysis of subgroups with biopharmaceutical applications
- Exact asymptotic limit for kernel estimation of regression level sets
- Fast learning rates for plug-in classifiers
- High-dimensional probability. An introduction with applications in data science
- Honest adaptive confidence bands and self-similar functions
- scientific article; zbMATH DE number 3624650 (Why is no real title available?)
- Intentional control of type I error over unconscious data distortion: a Neyman-Pearson approach to text classification
- Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
- Nonparametric confidence regions for level sets: statistical properties and geometry
- Nonparametric Estimation of Regression Level Sets
- Nonparametric estimation of regression level sets using kernel plug-in estimator
- On nonparametric estimation of density level sets
- Regression Level Set Estimation Via Cost-Sensitive Classification
- Responder identification in clinical trials with censored data
- Smoothness-Adaptive Contextual Bandits
- Understanding machine learning. From theory to algorithms
Cited in
(6)- Selection Algorithms with Small Groups
- Enhancing Target Group Selection Using Belief Functions
- Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data
- Exact two-sided confidence sets for a level set in simple linear regression
- Isotonic subgroup selection
- Non-splitting Neyman-Pearson classifiers
This page was built for publication: Optimal subgroup selection
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6183867)
