Honey, the Currency Union Effect on Trade hasn’t Blown Up

where I follow Nitsch in defining Tijt as the value of real bilateral trade between “countries” i and j at time t, CU is a dummy variable which is unity if i and j share the same currency at time t, Z is a vector of controls given by an augmented gravity model, γ are the associate nuisance coefficients, and ε is a (hopefully) well-behaved residual. My chief finding was that β was large and robust; my point estimate was β=1.2, implying that currency union is associated with a tripling (since exp(1.2)≈3) of trade. In his paper, Volker Nitsch provides three pieces of value-added. First he finds and corrects a number of data errors in my original data set. Second, he shows that adding extra controls to my empirical setup, dis-aggregating by currency unions, and adjusting for missing data affects the results. He concludes that the effect of currency union on trade is smaller than my original estimates, has not been reliably estimated, and may be zero.