BAMIFun provides Bayesian multiple imputation for functional data via low-rank penalized spline models, achieving accurate imputation and improved coverage in simulations and real datasets compared to single-imputation FPCA methods.
Double debiased machine learning nonparametric inference with continuous treatments
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
Presents the first kernel framework for distributional treatment effect inference from adaptively collected data, using doubly robust RKHS scores, cross-fold witness functions, and sequentially normalized statistics with valid type-I error.
SHIFT combines cross-fit DML with kernel-local Welsch loss optimized via Graduated Non-Convexity and a MAD-scaled defensive OLS refit to achieve robust average dose-response estimation under localized heavy-tailed contamination while recovering outlier masks.
Introduces partial identification bounds and a double-robust SurvB-learner meta-learner for estimating robust CATE in survival analysis under informative censoring.
Derives closed-form optimal batch sampling probabilities to minimize asymptotic variance of doubly robust ATE estimator with missing outcomes, achieving lower MSE and matching full-sample precision with 75% fewer labels on simulated and real data.
Develops m-th order estimators for dose-response functions based on higher-order influence functions that attain the fastest known convergence rates under stated conditions.
New ADRF estimator jointly outputs tail shape, deep-tail quantities, and mean effect with an explicit refusal mechanism, claiming 11-25.5% MAE reductions on heavy-tailed data and correct refusal on insurance claims.
citing papers explorer
-
BAMIFun: Bayesian Multiple Imputation for Functional Data
BAMIFun provides Bayesian multiple imputation for functional data via low-rank penalized spline models, achieving accurate imputation and improved coverage in simulations and real datasets compared to single-imputation FPCA methods.
-
Kernel Treatment Effects with Adaptively Collected Data
Presents the first kernel framework for distributional treatment effect inference from adaptively collected data, using doubly robust RKHS scores, cross-fold witness functions, and sequentially normalized statistics with valid type-I error.
-
SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination
SHIFT combines cross-fit DML with kernel-local Welsch loss optimized via Graduated Non-Convexity and a MAD-scaled defensive OLS refit to achieve robust average dose-response estimation under localized heavy-tailed contamination while recovering outlier masks.
-
Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
Introduces partial identification bounds and a double-robust SurvB-learner meta-learner for estimating robust CATE in survival analysis under informative censoring.
-
Batch-Adaptive Causal Annotations
Derives closed-form optimal batch sampling probabilities to minimize asymptotic variance of doubly robust ATE estimator with missing outcomes, achieving lower MSE and matching full-sample precision with 75% fewer labels on simulated and real data.
-
Fast convergence rates for dose-response estimation
Develops m-th order estimators for dose-response functions based on higher-order influence functions that attain the fastest known convergence rates under stated conditions.
-
Stop Suppressing the Tail: Causal Inference for Extreme Events
New ADRF estimator jointly outputs tail shape, deep-tail quantities, and mean effect with an explicit refusal mechanism, claiming 11-25.5% MAE reductions on heavy-tailed data and correct refusal on insurance claims.