Latent Unbalancedness in Three-Way Gravity Models

TL;DR

This paper investigates latent unbalancedness in three-way gravity models, revealing how redundant uninformative observations in panel data exacerbate inference issues in pseudo-poisson estimation.

Contribution

It introduces the concept of latent unbalancedness and demonstrates its impact on inference problems in three-way gravity models using real data and simulations.

Findings

Latent unbalancedness amplifies inference problems.

Redundant uninformative observations affect estimation accuracy.

The phenomenon is demonstrated through empirical and simulated data.

Abstract

Many panel data sets used for pseudo-poisson estimation of three-way gravity models are implicitly unbalanced because uninformative observations are redundant for the estimation. We show with real data as well as simulations that this phenomenon, which we call latent unbalancedness, amplifies the inference problem recently studied by Weidner and Zylkin (2021).