Dennis Novy | Searcharxiv

arXiv2025

Transitivity in International Trade: Evidence from Colombia-U.S. Firm Relationships

A large literature has documented transitivity as a key feature of social networks: individuals are more likely connected with each other if they share common connections with other individuals. We take this idea to trading relationships between firms: firms are more likely to trade with each other if they share common trading partners. Transitivity leads to a clustered pattern of relationship formation and break-up. It is therefore important for understanding how firms meet and how shocks propagate through firm networks. We describe a method for detecting and quantifying transitivity in firm-to-firm transactions, based on systematic deviations from conditional independence across firm-to-firm relationships. We apply the method to Colombia-U.S. exporter-importer data and show in counterfactuals that transitivity is a significant and economically meaningful factor in how firm networks adjust to cost shocks.

econ.GN↗

arXiv2025

Out-of-sample gravity predictions and trade policy counterfactuals

Gravity equations are often used to evaluate the effects of trade policies, such as regional trade agreements. We argue that their suitability for this purpose critically depends on their ability to produce unbiased out-of-sample predictions. We propose a methodology to evaluate the out-of-sample predictions obtained with gravity equations and with machine learning methods. We find that the 3-way gravity model is difficult to beat when the purpose is to evaluate policy interventions, further cementing its position as the predominant tool for applied trade policy analysis. However, when the goal is to predict individual flows, machine learning methods can be preferable.

econ.GN↗