The objective of this manuscript is to serve as a practical guide for estimations with the structural gravity model. After a brief review of the theoretical foundations, we summarize the main challenges with gravity estimations and we review the solutions to address those challenges. Then, we...

Then, we integrate the latest developments in the empirical gravity literature and we offer six recommendations to obtain reliable partial equilibrium estimates of the effects of bilateral and non-discriminatory trade policies within the same comprehensive, and theoretically-consistent...

In this paper we show that the relationship between trade liberalization and fi rm productivity is sensitive to the method used to estimate the production function. We estimate the productivity of Colombian manufacturing plants using the methods of Levinsohn and Petrin (2003), Ackerberg, Caves...

The objective of this manuscript is to serve as a practical guide for estimations with the structural gravity model. After a brief review of the theoretical foundations, we summarize the main challenges with gravity estimations and we review the solutions to address those challenges. Then, we...

This paper introduces the Granular Trade and Production Activities (GRANTPA) database, which covers international trade flows for 3,124 products and 247 countries over the period 1995-2019 as well as domestic trade flows and production data for the same number of products and years for a subset...

We propose a simple and flexible reduced-form econometric approach to estimate gravity models in the short and the long run. The theoretical lens for interpreting our methods amends the canonical Lucas-Prescott adjustment formulation to allow for time-interval-varying...

Using a new administrative dataset, we provide fresh micro-level evidence on firms’ returns to scale (RTS). We employ a new administrative database, iBACH, which contains extensive high-quality annual balance sheet, financial, and demographic information on more than two million non-financial...

Disregarding spatial dependence can invalidate methods for analyzing cross-sectional and panel data. We discuss ongoing work on developing methods that allow for, test for, or estimate, spatial dependence. Much of the stress is on nonparametric and semiparametric methods

The central limit theorem for nonparametric kernel estimates of a smooth trend, with linearly-generated errors, indicates asymptotic independence and homoscedasticity across fixed points, irrespective of whether disturbances have short memory, long memory, or antipersistence. However, the...