This paper estimates a structural New Keynesian model to test whether globalization has changed the behavior of U.S. macroeconomic variables. Several key coefficients in the model--such as the slopes of the Phillips and IS curves, the sensitivities of domestic inflation and output to "global" output, and so forth--are allowed in the estimation to depend on the extent of globalization (modeled as the changing degree of openness to trade of the economy), and, therefore, they become time-varying. The empirical results indicate that globalization can explain only a small part of the reduction in the slope of the Phillips curve. The sensitivity of U.S. inflation to global measures of output may have increased over the sample, but it remains very small. The changes in the IS curve caused by globalization are similarly modest. Globalization does not seem to have led to an attenuation in the effects of monetary policy shocks. The nested closed economy specification still appears to provide a substantially better fit of U.S. data than various open economy specifications with time-varying degrees of openness. Some time variation in the model coefficients over the postwar sample exists, particularly in the volatilities of the shocks, but it is unlikely to be related to globalization.