Monte Carlo Appraisals of Gravity Model Specifications

30 Pages Posted: 24 May 2004

See all articles by Michael A. Anderson

Michael A. Anderson

Washington and Lee University - Department of Economics

Michael J. Ferrantino

Trade Policy Research Forum

Kurt C. Schaefer

Calvin College

Date Written: May 21, 2004

Abstract

Many improvements have been proposed for the basic gravity model specification, most of which are confirmed by standard statistical tests due to the large number of observations often used to estimate such models. We use Monte Carlo experiments to examine situations in which features of models may be found statistically significant (or insignificant) when it is known ex ante that they are absent (or present) in the underlying data process. Erroneous assumptions about the presence or absence of lagged dependent variables, fixed effects, free-trade associations and customs unions are shown to introduce economically important bias in estimates of the coefficients of interest, and in some cases to be confirmed spuriously. Policy effects, such as for free trade associations and currency unions, can also be confirmed spuriously when they do not exist in the data-generating process.

Keywords: Gravity model, Monte Carlo, econometrics, replication, international trade, specification

JEL Classification: F10, F15, F17, C15, C52

Suggested Citation

Anderson, Michael A. and Ferrantino, Michael J. and Schaefer, Kurt C., Monte Carlo Appraisals of Gravity Model Specifications (May 21, 2004). Available at SSRN: https://ssrn.com/abstract=549301 or http://dx.doi.org/10.2139/ssrn.549301

Michael A. Anderson

Washington and Lee University - Department of Economics ( email )

Lexington, VA 24450
United States

Michael J. Ferrantino

Trade Policy Research Forum ( email )

13 Yucca Drive
Fredericksburg, VA Virginia 22405
United States

Kurt C. Schaefer (Contact Author)

Calvin College ( email )

Grand Rapids, MI 49546
United States
616-526-6298 (Phone)
616-526-8410 (Fax)