Over time, the gravity model has been defined as the workhorse of international trade and its ability to correctly approximate bilateral trade flows makes it one of the most successful “empirical fact” in economics. With data increasingly available for developing, as well as developed countries, the gravity model has come to be the starting point for a wide variety of research questions with a policy component.
There are two fundamental problems related to gravity-based model to evaluate the eﬀect of trade policies: multilateral trade resistance and policy measurement.
The gravity model has more recently acquired a range of micro-founded theoretical bases, showing that the typical gravity equation should account for both “bilateral resistance” and the so-called “multilateral resistance” term (MTR). The need to control for the multilateral trade resistance is often implemented in the literature as the inclusion of importer and exporter fixed effects.
Another important issue refers to the measurement of the trade policies under evaluation. It is well known that gravity type models using policy dummies are misspecified and lead to erroneous economic inferences. The recent literature emphasizes the importance of expressing trade policies through continuous variables since they vary widely across products, importers and exporters, and at least in the case of tariffs detailed data are currently available.
This course intends to provide African-based researchers with knowledge of the latest developments regarding both theoretical general equilibrium foundations for the gravity equation for trade and empirical strategies leading to a more accurate estimation and interpretation of the policy impact of trade flows. After an overview of the theoretical foundation of gravity models, we will then turn to the discussion of advanced issues on gravity modelling such as how to handle zero-trade flows and how to account for Multilateral Resistance.
Equipped with these analytical tools, we will review the debate over the impact of the preferential policies on trade. This application will allow us to show the importance of a correct specification of the estimation equation for unbiased results, to explain to the reader how to interpret the results of a regression analysis (including inferences on trade diversion and trade creation) and to discuss a number of potential estimation problems such as endogeneity and heteroskedasticity. Finally, Montecarlo simulations will be performed to show to what extent the use of a full set of fixed effects to control for unobserved heterogeneity affects the possibility to capture the trade policy impact.
Participants will be provided a “hands-on” introduction to gravity modeling for applied policy researchers. The Stata code provided will give you several examples of hands-on estimation to familiarize themselves with the gravity equation methodological choices highlighted in the theoretical review. An illustrative dataset with alternative Stata codes presenting the different possible estimation strategies will be provided. Although some basic knowledge of Stata is required as a pre-requisite, more advanced commands and techniques are introduced in the course as necessary. Participants will be encouraged to use Stata to carry out estimations designed to familiarize themselves with the software and, more importantly, the gravity model. Once the basic techniques have been mastered, readers are encouraged to extend the results presented here using alternative specifications and methodologies.
The course will be organized into one-week. It will be divided into several modules focused on a particular strand of literature that is of current relevance for gravity modelling, and taught by leading academics in the field. In each module, the training will cover theoretical and empirical areas in that literature, apply that learning by replicating gravity estimations drawn from published papers. Finally, there will be a discussion of each participant’s research and how these techniques could be applied.
Participants to the training will be given access to relevant material (papers, datasets, Stata do files, and others), as well as encouraged to share experiences and information and to receive feedback on on-going work.
A tentative schedule is shown below:
- Brief introduction
- Overview of the workshop
- The gravity model: Data and measurement issues
- Participant presentations: on-going research
- The gravity model: theoretical issues
- Hands-on Stata session
- Specific examples of papers using gravity models
- Meta-analysis of the literature (hands-on component)
- Hands-on Stata session
- Measurement of preferential trade policies (hands-on component)
- Quantitative assessment of preferential policy impact
- Hands-on Stata session
- Discussion of participants on-going research
- The gravity model: current developments and future research
Knowledge of Stata required
In order to apply for this course, AGRODEP members must complete the following by August 17, 2015:
If you would like to practice using Stata before taking the proficiency test, please review the modules below. Information included covers Stata use for beginners, linear regressions, bivariate regressions, and panel data. You will need to know this information to successfully complete the test.
- Training Module 1: Introduction to Stata
- Training Module 2: Basic Data Management, Graphs, and Log-Files
- Training Module 3: Linear Regressions
- Training Module 4: Bivariate Regressions
- Training Module 5: Panel Data Regressions
Luca Salvatici received his Ph.D. from the University of California at Davis and is presently Professor of economic policy at the University of Roma Tre, Italy. He previously held positions at La Sapienza University of Roma and University of Molise, and was a consultant for the World Bank and the Food and Agriculture Organization. He is the author of several publications on the measurement of protection and on the EU policies.