Is infrastructure capital really productive? Nonparametric modeling and data-driven model selection in a cross-sectionally dependent panel framework

Abstract

This paper examines the contribution of infrastructure to aggregate productivity. We address some complex and relevant issues, namely functional form, nonstationary variables and cross-sectional dependence. We adopt the CCE framework and consider both parametric and nonparametric specifications, thus allowing for different degrees of flexibility. We also employ a data-driven model selection procedure based on moving block bootstrap to choose among alternative specifications. It is found that nonparametric specifications provide the best predictive performance and that CCE models always overperform with respect to traditional panel data methods. Furthermore, we find a lack of significance of the infrastructure index, with an estimated elasticity very close to zero for all estimates.

Keywords

JEL codes

Replaces

Antonio Musolesi, Giada Andrea Prete, and Michel Simioni, “Is infrastructure capital really productive? Non-parametric modeling and data-driven model selection in a cross-sectionally dependent panel framework”, TSE Working Paper, n. 22-1335, May 2022.

Reference

Antonio Musolesi, Giada Andrea Prete, and Michel Simioni, “Is infrastructure capital really productive? Nonparametric modeling and data-driven model selection in a cross-sectionally dependent panel framework”, Journal of Productivity Analysis, September 2025.