Design-based theory for causal inference

2025-11-27

AI Summary

Causal inference confronts practical challenges including high-dimensional covariates, individual noncompliance, and network interference; conventional model-based approaches often rely on strong parametric or functional-form assumptions. This paper systematically reviews design-driven advances in causal inference, focusing on covariate-balancing designs (e.g., stratified randomization, rerandomization), regression adjustment, and network-aware inference—grounded in the Fisher randomization test and Neyman asymptotic frameworks. Its key contribution lies in developing a robust, model-agnostic framework for randomization design and inference under weak assumptions, substantially enhancing identification power and statistical efficiency in high-dimensional, noncompliant, and network-interfered settings. The proposed methodology provides theoretically rigorous yet practically implementable tools for causal analysis in medicine, social sciences, and related domains. It further identifies promising future directions, including multi-scenario integration and co-design of algorithms and experimental protocols.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Causal inference, as a major research area in statistics and data science, plays a central role across diverse fields such as medicine, economics, education, and the social sciences. Design-based causal inference begins with randomized experiments and emphasizes conducting statistical inference by leveraging the known randomization mechanism, thereby enabling identification and estimation of causal effects under weak model dependence. Grounded in the seminal works of Fisher and Neyman, this paradigm has evolved to include various design strategies, such as stratified randomization and rerandomization, and analytical methods including Fisher randomization tests, Neyman-style asymptotic inference, and regression adjustment. In recent years, with the emergence of complex settings involving high-dimensional data, individual noncompliance, and network interference, design-based causal inference has witnessed remarkable theoretical and methodological advances. This paper provides a systematic review of recent progress in this field, focusing on covariate-balanced randomization designs, design-based statistical inference methods, and their extensions to high-dimensional, noncompliance, and network interference scenarios. It concludes with a comprehensive perspective on future directions for the theoretical development and practical applications of causal inference.

Problem

• Reviews recent advances in design-based causal inference methods
• Focuses on covariate-balanced randomization and statistical inference techniques
• Extends methods to high-dimensional, noncompliance, and network interference scenarios

Innovation

• Design-based inference using known randomization mechanisms
• Covariate-balanced randomization designs for complex settings
• Extensions to high-dimensional, noncompliance, and network scenarios