A striking feature of the structural change literature is that, even though the U.S. economy is often used as a benchmark for calibration, the traditional models cannot account for the steep decline in manufacturing and rise in services in the U.S. since the late 1970s (Buera and Kaboski, 2009). In order to solve this puzzle, this paper develops a three-sector model to evaluate various factors that could have contributed to the structural transformation process from 1950 to 2005. The results show that, in addition to traditional explanations, such as non-homothetic preference and sector-biased productivity progress, international trade is another major source of structural change and is able to explain about 35.5% of the overall employment share decrease in American manufacturing. The quantitative calibration estimates that the inter-sector trade makes a moderate contribution, while trade imbalances dominate the recent contraction of manufacturing employment share. Our results suggest that calibrated models based on U.S. data have to be adjusted by trade factors.