Propensity Score Propagation: A General Framework for Design-Based Inference with Unknown Propensity Scores

Abstract

Design-based inference, also known as randomization-based or finite-population inference, provides a principled framework for trustworthy statistical inference. It attributes randomness solely to the design mechanism, such as treatment assignment, survey sampling, or missingness, without imposing super-population distributional or modeling assumptions on the outcome data. From the seminal work of Fisher and Neyman to its recent resurgence, design-based inference has played a central role in causal inference, survey sampling, and missing data analysis. However, its use in many modern applications has been limited by a fundamental obstacle: existing design-based inference methods typically assume that propensity scores (i.e., design probabilities) are known, whereas in observational studies, real-world surveys, missing data problems, and many other settings, propensity scores are usually unknown and must be estimated from data. We propose propensity score propagation, a general framework for valid design-based inference with unknown propensity scores. The framework uses a regeneration-and-union procedure to propagate uncertainty from propensity score estimation into downstream design-based inference without introducing super-population assumptions about the outcomes. It accommodates both parametric and nonparametric propensity score estimation, supports flexible machine learning estimators, integrates seamlessly with existing design-based inference methods developed for settings with known propensity scores, and applies broadly across design-based problems. Theoretical and simulation results show that the proposed framework achieves nominal coverage, even when existing approaches exhibit substantial under-coverage.