Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting

• URL: http://arxiv.org/abs/2607.05806v1
• Date: Tue, 07 Jul 2026 03:59:46 GMT
• Title: Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting
• Abstract summary: Training data for machine learning is routinely collected by a selection process the model never sees.<n>Etonians solved the harder case in 1979: Heckman's two-equation model fits a probit selection equation and an outcome equation linked through correlated errors.<n>The Heckman correction restores coverage when the selection equation has an instrument -- a variable affecting selection but not the outcome -- and degrades measurably without one.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes only when a test was ordered. The standard fixes -- importance weighting, covariate-shift correction, MAR imputation -- assume selection is ignorable given observables. Econometrics solved the harder case in 1979: Heckman's two-equation model jointly fits a probit selection equation and an outcome equation linked through correlated errors, and the inverse-Mills-ratio term corrects for selection on unobservables, where importance weighting is structurally helpless. We instantiate this for deep epistemic uncertainty: a deep outcome network, a linear selection head, and a joint bivariate-normal likelihood over all units, ensembled for predictive variance. In a controlled generator where sampling probability depends on an unobservable correlated (rho up to 0.9) with the outcome noise, deep ensembles, MC dropout, and GP baselines are overconfident exactly where data was avoided: coverage of nominal-90% intervals falls to 64.4% at rho=0.9, and importance weighting with oracle propensities does not fix it (43.1%) -- reweighting corrects the covariate distribution, not the conditional bias E[y|x,selected] != E[y|x]. The Heckman correction restores coverage (88.9%) when the selection equation has an instrument -- a variable affecting selection but not the outcome -- and degrades measurably without one (40.3%); we chart this honesty curve rather than hide it. On real tabular data with induced MNAR selection, the corrected intervals are the best-calibrated (lowest region-ECE) non-oracle method in selected-against regions; baselines matching its raw coverage do so only by over-widening everywhere. Our estimators reproduce classic Stata output to seven digits. We state which identification regime a practitioner is in, and release the code.

Related papers

• Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset [8.271195591114806]
  Five UQ methods are compared on accuracy, calibration, uncertainty decomposition, and risk-coverage.<n>Even methods with narrow entropy rank the same samples as hard.<n>The choice of method matters more for calibration and uncertainty decomposition, where Deep Ensembles is the clear winner.
  arXiv  Detail & Related papers  (2026-08-14T14:14:13Z)
• Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification [1.547549252134621]
  We study a post-inference problem through cross-fitted residual utility and a primary-preserving cognitive decision policy.<n>A structured KAN-Fourier classifier supplies the default probability, while neural and non-neural candidates provide observable evidence.<n>On RMLA, RMLB, and HISAR, the complete system improves overall accuracy from 63.632% to 66.332%, 65.161% to 66.168%, and 77.769% to 79.867%.
  arXiv  Detail & Related papers  (2026-08-03T11:07:37Z)
• PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data [0.0]
  We introduce PAIR-CI, a nonparametric conditional independence (CI) test that restores calibration by integrating multiple imputation directly into the inferential procedure.<n>A provably consistent variance estimator jointly accounts for uncertainty arising from cross-validation and multiple imputation.
  arXiv  Detail & Related papers  (2026-05-06T12:34:37Z)
• A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning [10.891872788947298]
  Local CRPS variance provides a direct signal of single-seed estimation error.<n>Power-law fit quality and monotonicity together provide compact method-level summaries of trajectory regularity.
  arXiv  Detail & Related papers  (2026-04-25T02:52:33Z)
• Fixed-Horizon Self-Normalized Inference for Adaptive Experiments via Martingale AIPW/DML with Logged Propensities [0.0]
  Under adaptive assignment, propensities can keep changing, so the predictable quadratic variation of AIPW/DML increments may remain random.<n>We show that the Studentized statistic, with variance estimated by realized quadratic variation, is conditionally miscalibrated even without variance stabilization.
  arXiv  Detail & Related papers  (2026-02-17T13:12:31Z)
• Missing At Random as Covariate Shift: Correcting Bias in Iterative Imputation [5.51520342433892]
  We formulate missing data imputation as a risk minimisation problem.<n>We derive theoretically valid importance weights that correct for the induced distributional bias.<n>We propose a novel imputation algorithm that jointly estimates both the importance weights and imputation models.
  arXiv  Detail & Related papers  (2026-02-06T14:02:12Z)
• Regression-Based Estimation of Causal Effects in the Presence of Selection Bias and Confounding [52.1068936424622]
  We consider the problem of estimating the expected causal effect $E[Y|do(X)]$ for a target variable $Y$ when treatment $X$ is set by intervention.<n>In settings without selection bias or confounding, $E[Y|do(X)] = E[Y|X]$, which can be estimated using standard regression methods.<n>We propose a framework that incorporates both selection bias and confounding.
  arXiv  Detail & Related papers  (2025-03-26T13:43:37Z)
• Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression [102.24287051757469]
  We study self-supervised covariance estimation in deep heteroscedastic regression.<n>We derive an upper bound on the 2-Wasserstein distance between normal distributions.<n>Experiments over a wide range of synthetic and real datasets demonstrate that the proposed 2-Wasserstein bound coupled with pseudo label annotations results in a computationally cheaper yet accurate deep heteroscedastic regression.
  arXiv  Detail & Related papers  (2025-02-14T22:37:11Z)
• Revisiting the Dataset Bias Problem from a Statistical Perspective [72.94990819287551]
  We study the "dataset bias" problem from a statistical standpoint. We identify the main cause of the problem as the strong correlation between a class attribute u and a non-class attribute b. We propose to mitigate dataset bias via either weighting the objective of each sample n by frac1p(u_n|b_n) or sampling that sample with a weight proportional to frac1p(u_n|b_n).
  arXiv  Detail & Related papers  (2024-02-05T22:58:06Z)
• Selective Nonparametric Regression via Testing [54.20569354303575]
  We develop an abstention procedure via testing the hypothesis on the value of the conditional variance at a given point. Unlike existing methods, the proposed one allows to account not only for the value of the variance itself but also for the uncertainty of the corresponding variance predictor.
  arXiv  Detail & Related papers  (2023-09-28T13:04:11Z)
• Equivariance and Invariance Inductive Bias for Learning from Insufficient Data [65.42329520528223]
  We show why insufficient data renders the model more easily biased to the limited training environments that are usually different from testing. We propose a class-wise invariant risk minimization (IRM) that efficiently tackles the challenge of missing environmental annotation in conventional IRM.
  arXiv  Detail & Related papers  (2022-07-25T15:26:19Z)
• To Impute or not to Impute? -- Missing Data in Treatment Effect Estimation [84.76186111434818]
  We identify a new missingness mechanism, which we term mixed confounded missingness (MCM), where some missingness determines treatment selection and other missingness is determined by treatment selection. We show that naively imputing all data leads to poor performing treatment effects models, as the act of imputation effectively removes information necessary to provide unbiased estimates. Our solution is selective imputation, where we use insights from MCM to inform precisely which variables should be imputed and which should not.
  arXiv  Detail & Related papers  (2022-02-04T12:08:31Z)
• Decorrelated Clustering with Data Selection Bias [55.91842043124102]
  We propose a novel Decorrelation regularized K-Means algorithm (DCKM) for clustering with data selection bias. Our DCKM algorithm achieves significant performance gains, indicating the necessity of removing unexpected feature correlations induced by selection bias.
  arXiv  Detail & Related papers  (2020-06-29T08:55:50Z)

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.