Although previous empirical studies have analyzed the geographic effect of NAFTA on economic
activity in Mexico, they are limited by using state level data which masks the spatial distribution of
economic activity and severely restricts their number of observations. This paper offers the following
contributions. First, it uses municipal panel data to identify the relationship between trade and
regional patterns of growth. The use of municipal data also provides more observations that could
improve the precision of the estimated impact, since as the sample size grows the estimators converge
in probability to the quantity being estimated. Second, we include the latest economic census (2004)
to observe longer-term effects of NAFTA. Third, by separating economic activity into traded and
non-traded goods, we can better identify the specific effect of trade. Last, unlike previous papers,
we explicitly control for the spatial nature of our data, and use newly-developed spatial panel data
methods (Kapoor et al. 2007).