Working Paper: CEPR ID: DP10428
Authors: Peter Egger; Kevin E. Staub
Abstract: Many empirical gravity models are now based on generalized linear models (GLM), of which the Poisson pseudo-maximum likelihood estimator is a prominent example and the most-frequently used estimator. Previous literature on the performance of these estimators has primarily focussed on the role of the variance function for the estimators? behavior. We add to this literature by studying the small-sample performance of estimators in a data-generating process that is fully consistent with general equilibrium economic models of international trade. Economic theory suggests that (i) importer- and exporter-specific effects need to be accounted for in estimation, and (ii) that they are correlated with bilateral trade costs through general-equilibrium (or balance-of-payments) restrictions. We compare the performance of structural estimators, fixed effects estimators, and quasi-differences estimators in such settings, using the GLM approach as a unifying framework.
Keywords: Fixed Effects; Generalized Linear Models; Gravity Models
JEL Codes: C23; F14
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| omitting importer and exporter-specific effects (ei, mj) (F14) | biased estimates of trade flows (F14) |
| specification of the model (C51) | reliability of the estimators (C51) |
| choice of estimator (C51) | accuracy of trade flow predictions (F17) |
| incidental parameters problem (C20) | biased variance estimates of fixed effects estimators (C51) |
| importer and exporter-specific effects (ei, mj) (F14) | bilateral trade costs (tij) (F14) |