The export‐led growth hypothesis is tested using monthly time series data for Shanghai (one of the major exporting provinces in China) using the Granger no‐causality procedure developed by Toda and Yamamoto (1995) in a vector autoregresion (VAR) model. This paper builds on the existing literature in three distinct ways. This is the first study of the export‐led growth hypothesis which employs a regional dataset (Shanghai). Second, the paper follows Riezman et al. (1996) in controlling for the growth of imports to avoid a spurious causality result; and finally, the use of the methodology by Toda and Yamamoto is expected to improve the standard F‐statistics in the causality test process. The research finds one‐way Granger causality running from GDP to exports