Focused median bias reduction
Abstract
Median bias reduction of maximum likelihood estimators can substantially improve estimation and inference. Existing generally applicable methods are, however, implicit, requiring the solution of nonlinear systems of estimating equations for a specified parameterization. Their application to parameter transformations often involves tedious algebra and bespoke implementations. We develop an explicit median bias-corrected estimator for focus parameters that are smooth scalar transformations of a chosen reference parameterization. The estimator results from solving an equation derived from the Cornish-Fisher expansion of the centred and scaled maximum likelihood estimator of the focus parameter, and requires only the ML or an asymptotically equivalent estimator at the reference parameterization, the gradient and Hessian of the transformation, and expectations of products of log-likelihood derivatives. These expectations are available for many models in the bias reduction literature and can also be estimated by Monte Carlo simulation. The resulting estimators are third-order median unbiased and provide one-step approximations to estimators from implicit median bias reduction when the reference parameterization includes the focus parameter. The method can improve standard asymptotic inference and enables hull-based confidence procedures to produce intervals with near nominal finite-sample coverage under median bias control. We illustrate the framework through post-selection inference using the Focused Information Criterion, Mahalanobis distances, quantiles, and scalar focus parameters in regression, stratified, circular, and multiple-mediator models.
Related
- Invariant Measures as Estimators: Second-Order Stochastic Expansions and Bias Reduction
- D3MI: an efficient and powerful federated imputation method for bias reduction in the analysis of distributed incomplete data by accounting for within-site correlation and between-site heterogeneity.
- Adjusting for Many Covariates in Randomized Clinical Trials with GLMs: Bias Reduction by Jackknife and Practical Guidance
- CRANDALL-PAZY RIGIDITY FOR LOWER SEMICONTINUOUS CONVEX FUNCTIONS: A BALANCED MEDIAN-FLOW ARGUMENT
- CRANDALL-PAZY RIGIDITY FOR C 1 CONVEX FUNCTIONS: A FIRST-ORDER MEDIAN-FLOW ARGUMENT
BibTeX
@misc{benussi2026focused,
title = {{Focused median bias reduction}},
author = {Davide Benussi and Ioannis Kosmidis and Alessandra Salvan and Nicola Sartori},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.28597},
eprint = {2606.28597},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.28597},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Focused median bias reduction
AU - Davide Benussi
AU - Ioannis Kosmidis
AU - Alessandra Salvan
AU - Nicola Sartori
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2606.28597
UR - https://arxiv.org/abs/2606.28597
AB - Median bias reduction of maximum likelihood estimators can substantially improve estimation and inference. Existing generally applicable methods are, however, implicit, requiring the solution of nonlinear systems of estimating equations for a specified parameterization. Their application to parameter transformations often involves tedious algebra and bespoke implementations. We develop an explicit median bias-corrected estimator for focus parameters that are smooth scalar transformations of a chosen reference parameterization. The estimator results from solving an equation derived from the Cornish-Fisher expansion of the centred and scaled maximum likelihood estimator of the focus parameter, and requires only the ML or an asymptotically equivalent estimator at the reference parameterization, the gradient and Hessian of the transformation, and expectations of products of log-likelihood derivatives. These expectations are available for many models in the bias reduction literature and can also be estimated by Monte Carlo simulation. The resulting estimators are third-order median unbiased and provide one-step approximations to estimators from implicit median bias reduction when the reference parameterization includes the focus parameter. The method can improve standard asymptotic inference and enables hull-based confidence procedures to produce intervals with near nominal finite-sample coverage under median bias control. We illustrate the framework through post-selection inference using the Focused Information Criterion, Mahalanobis distances, quantiles, and scalar focus parameters in regression, stratified, circular, and multiple-mediator models.
ER -