Regression Discontinuity Designs for Functional Data and Random Objects in Geodesic Spaces

TL;DR

This paper extends regression discontinuity designs to complex, non-Euclidean outcomes in geodesic spaces, enabling causal inference in settings like networks and functional data with theoretical guarantees.

Contribution

It introduces a geodesic-based RDD framework for metric space-valued data, including a new bandwidth selection method and an extension to fuzzy designs, supported by convergence theory.

Findings

Applied to CO concentration curves after Taipei Metro introduction

Analyzed UK voting pattern shifts post-Conservative wins

Demonstrated competitive performance of the new bandwidth method

Abstract

Regression discontinuity designs have been widely used in observational studies to estimate causal effects of an intervention or treatment at a cutoff point. We propose a generalization of regression discontinuity designs to handle complex non-Euclidean outcomes, such as networks, compositional data, functional data, and other random objects residing in geodesic metric spaces. A key challenge in this setting is the absence of algebraic operations, which makes it difficult to define treatment effects using simple differences. To address this, we define the causal effect at the cutoff as a geodesic between the local Fr\'echet means of untreated and treated outcomes. This reduces to the classical average treatment effect in the scalar case. Estimation is carried out using local Fr\'echet regression, a nonparametric method for metric space-valued responses that generalizes local linear regression. We introduce a new bandwidth selection procedure tailored to regression discontinuity designs, which performs competitively even in classical scalar scenarios. The proposed geodesic regression discontinuity design method is supported by theory, including convergence rate guarantees, and is demonstrated in applications where causal inference is of interest in complex outcome spaces. These include changes in daily CO concentration curves following the introduction of the Taipei Metro, and shifts in UK voting patterns measured by vote share compositions after Conservative Party wins. We also develop an extension to fuzzy designs with non-Euclidean outcomes, broadening the scope of causal inference to settings that allow for imperfect compliance with the assignment rule.