Detecting and Mitigating Group Bias in Heterogeneous Treatment Effects

• URL: http://arxiv.org/abs/2602.20383v1
• Date: Mon, 23 Feb 2026 21:47:01 GMT
• Title: Detecting and Mitigating Group Bias in Heterogeneous Treatment Effects
• Authors: Joel Persson, Jurriën Bakker, Dennis Bohle, Stefan Feuerriegel, Florian von Wangenheim,
• Abstract summary: We develop a statistical framework to detect and mitigate group bias in randomized experiments.<n>For mitigation, we propose a shrinkage-based bias-correction, and show that the theoretically optimal and empirically feasible solutions have closed-form expressions.<n>We analyze the economic implications of mitigating detected group bias for profit-maximizing personalized targeting.
• Score: 28.4891545570248
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Heterogeneous treatment effects (HTEs) are increasingly estimated using machine learning models that produce highly personalized predictions of treatment effects. In practice, however, predicted treatment effects are rarely interpreted, reported, or audited at the individual level but, instead, are often aggregated to broader subgroups, such as demographic segments, risk strata, or markets. We show that such aggregation can induce systematic bias of the group-level causal effect: even when models for predicting the individual-level conditional average treatment effect (CATE) are correctly specified and trained on data from randomized experiments, aggregating the predicted CATEs up to the group level does not, in general, recover the corresponding group average treatment effect (GATE). We develop a unified statistical framework to detect and mitigate this form of group bias in randomized experiments. We first define group bias as the discrepancy between the model-implied and experimentally identified GATEs, derive an asymptotically normal estimator, and then provide a simple-to-implement statistical test. For mitigation, we propose a shrinkage-based bias-correction, and show that the theoretically optimal and empirically feasible solutions have closed-form expressions. The framework is fully general, imposes minimal assumptions, and only requires computing sample moments. We analyze the economic implications of mitigating detected group bias for profit-maximizing personalized targeting, thereby characterizing when bias correction alters targeting decisions and profits, and the trade-offs involved. Applications to large-scale experimental data at major digital platforms validate our theoretical results and demonstrate empirical performance.

Related papers

• Measuring Model Performance in the Presence of an Intervention [11.381587523287495]
  In many AI for social impact applications, the presence of an intervention that affects the outcome can bias the evaluation.<n>RCTs randomly assign interventions, allowing data from the control group to be used for unbiased model evaluation.<n>We propose nuisance parameter weighting (NPW), an unbiased model evaluation approach that reweights data from the treatment group to mimic the distributions of samples that would or would not experience the outcome.
  arXiv  Detail & Related papers  (2025-11-08T02:24:16Z)
• Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data [4.777323087050061]
  We propose the QR-learner, a model-agnostic learner that estimates conditional average treatment effects (CATE) within a trial population.<n>It can reduce the mean squared error relative to a trial-only CATE learner, and is guaranteed to recover the true CATE even when the external data are not aligned with the trial.
  arXiv  Detail & Related papers  (2025-07-04T16:01:05Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Causality and Independence Enhancement for Biased Node Classification [56.38828085943763]
  We propose a novel Causality and Independence Enhancement (CIE) framework, applicable to various graph neural networks (GNNs) Our approach estimates causal and spurious features at the node representation level and mitigates the influence of spurious correlations. Our approach CIE not only significantly enhances the performance of GNNs but outperforms state-of-the-art debiased node classification methods.
  arXiv  Detail & Related papers  (2023-10-14T13:56:24Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Systematic Evaluation of Predictive Fairness [60.0947291284978]
  Mitigating bias in training on biased datasets is an important open problem. We examine the performance of various debiasing methods across multiple tasks. We find that data conditions have a strong influence on relative model performance.
  arXiv  Detail & Related papers  (2022-10-17T05:40:13Z)
• Falsification before Extrapolation in Causal Effect Estimation [6.715453431174765]
  Causal effects in populations are often estimated using observational datasets. We propose a meta-algorithm that attempts to reject observational estimates that are biased.
  arXiv  Detail & Related papers  (2022-09-27T21:47:23Z)
• Robust and Agnostic Learning of Conditional Distributional Treatment Effects [44.31792000298105]
  We provide a new robust and model-agnostic methodology for learning the conditional DTE (CDTE) for a class of problems.<n>Our method is model-agnostic in that it can provide the best projection of CDTE onto the regression model class.<n>We investigate the behavior of our proposal in simulations, as well as in a case study of 401(k) eligibility effects on wealth.
  arXiv  Detail & Related papers  (2022-05-23T17:40:31Z)
• Two-Stage TMLE to Reduce Bias and Improve Efficiency in Cluster Randomized Trials [0.0]
  Cluster randomized trials (CRTs) randomly assign an intervention to groups of individuals, and measure outcomes on individuals in those groups. Findings are often missing for some individuals within clusters. CRTs often randomize limited numbers of clusters, resulting in chance imbalances on baseline outcome predictors between arms.
  arXiv  Detail & Related papers  (2021-06-29T21:47:30Z)
• Increasing the efficiency of randomized trial estimates via linear adjustment for a prognostic score [59.75318183140857]
  Estimating causal effects from randomized experiments is central to clinical research. Most methods for historical borrowing achieve reductions in variance by sacrificing strict type-I error rate control.
  arXiv  Detail & Related papers  (2020-12-17T21:10:10Z)
• Double machine learning for sample selection models [0.12891210250935145]
  This paper considers the evaluation of discretely distributed treatments when outcomes are only observed for a subpopulation due to sample selection or outcome attrition. We make use of (a) Neyman-orthogonal, doubly robust, and efficient score functions, which imply the robustness of treatment effect estimation to moderate regularization biases in the machine learning-based estimation of the outcome, treatment, or sample selection models and (b) sample splitting (or cross-fitting) to prevent overfitting bias.
  arXiv  Detail & Related papers  (2020-11-30T19:40:21Z)
• Enabling Counterfactual Survival Analysis with Balanced Representations [64.17342727357618]
  Survival data are frequently encountered across diverse medical applications, i.e., drug development, risk profiling, and clinical trials. We propose a theoretically grounded unified framework for counterfactual inference applicable to survival outcomes.
  arXiv  Detail & Related papers  (2020-06-14T01:15:00Z)
• Performance metrics for intervention-triggering prediction models do not reflect an expected reduction in outcomes from using the model [71.9860741092209]
  Clinical researchers often select among and evaluate risk prediction models. Standard metrics calculated from retrospective data are only related to model utility under certain assumptions. When predictions are delivered repeatedly throughout time, the relationship between standard metrics and utility is further complicated.
  arXiv  Detail & Related papers  (2020-06-02T16:26:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.