Recovering latent linkage structures and spillover effects with structural breaks in panel data models

TL;DR

This paper develops a novel framework for analyzing time-varying spillover effects in panel data with latent linkages and structural breaks, using penalized estimation and double machine learning for high-dimensional parameters.

Contribution

It introduces a new method to estimate unknown breakpoints, linkage structures, and spillover effects in high-dimensional panel data models with structural breaks.

Findings

R&D spillovers become sparser after the financial crisis

The breakpoint estimator is super-consistent

The method effectively captures time-varying spillover effects

Abstract

This paper introduces a framework to analyze time-varying spillover effects in panel data. We consider panel models where a unit's outcome depends not only on its own characteristics (private effects) but also on the characteristics of other units (spillover effects). The linkage of units is allowed to be latent and may shift at an unknown breakpoint. We propose a novel procedure to estimate the breakpoint, linkage structure, spillover and private effects. We address the high-dimensionality of spillover effect parameters using penalized estimation, and estimate the breakpoint with refinement. We establish the super-consistency of the breakpoint estimator, ensuring that inferences about other parameters can proceed as if the breakpoint were known. The private effect parameters are estimated using a double machine learning method. The proposed method is applied to estimate the cross-country R&D spillovers, and we find that the R&D spillovers become sparser after the financial crisis.