Bregman projection for calibration estimation

TL;DR

This paper introduces a unified Bregman divergence-based framework for calibration estimation in survey sampling, offering geometric insights, efficiency improvements, and extensions to high-dimensional and unknown inclusion probability settings.

Contribution

It develops a general Bregman projection framework for calibration, unifies classical methods, and introduces optimal divergence choices and regularization for high-dimensional data.

Findings

Bregman calibration estimators are asymptotically equivalent to debiased regression estimators.

Optimal divergence minimizes asymptotic variance under Poisson sampling.

Proposed methods perform well in simulations and real data applications.

Abstract

Calibration weighting is a fundamental technique in survey sampling and data integration for incorporating auxiliary information and improving efficiency of estimators. Classical calibration methods are typically formulated through distance functions applied to weight ratios relative to design weights. In this paper we develop a unified framework for calibration estimation based on Bregman divergence defined directly on the weight vector. We show that calibration estimators obtained from Bregman divergence admit a dual representation that depends only on the dimension of the auxiliary variables and can be interpreted as a Bregman projection onto the calibration constraint set. This geometric structure leads to a general asymptotic representation showing that calibration estimators are equivalent to debiased regression estimators whose regression coefficient depends on the choice of the Bregman generator. The result provides a unifying perspective on classical calibration methods such as quadratic calibration and exponential tilting, and reveals how the choice of divergence influences efficiency. Under Poisson sampling we further characterize the generator that minimizes the asymptotic variance of the calibration estimator and obtain an optimal contrast entropy divergence. The framework also extends naturally to settings where inclusion probabilities are unknown and must be estimated, yielding cross-fitted estimators that remain root-n consistent under mild conditions. Finally, we develop a regularized calibration estimator suitable for high-dimensional auxiliary variables. Simulation studies and a real data application illustrate the practical advantages of the proposed approach.