Munich Personal RePEc Archive

The Poisson quasi-maximum likelihood estimator: A solution to the “adding up” problem in gravity models

Arvis, Jean-Francois and Shepherd, Ben (2011): The Poisson quasi-maximum likelihood estimator: A solution to the “adding up” problem in gravity models.

[img]
Preview
PDF
MPRA_paper_34334.pdf

Download (815Kb) | Preview

Abstract

This paper shows that the Poisson quasi-maximum likelihood estimator applied to the gravity model produces estimates in which, summing across all partners, actual and estimated total trade flows are identical. Other methods such as OLS do not have this desirable property. Indeed, Poisson is the only quasi-maximum likelihood estimator that preserves total trade flows. This result is an additional reason for preferring Poisson as a workhorse gravity model estimator.

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.