An alternative definition of economic regions in the U.S. based on similarities in state business cycles

Since the 1950s the Bureau of Economic analysis (BEA) has grouped the states into eight regions based primarily on cross-sectional similarities in their socioeconomic characteristics. This is the most frequently used grouping of states in the U.S. for economic analysis. Since several recent studies concentrate on similarities and differences in regional business cycles, this paper groups states into regions based not on a broad set of socioeconomic characteristics but on the similarities in their business cycles. The analysis makes use of a consistent set of coincident indexes estimated from a Stock and Watson-type model. The author applies k-means cluster analysis to the cyclical components of these indexes to group the 48 contiguous states into eight regions with similar cycles. Having grouped the states into regions, the author determines the relative strength of cohesion among the states in the various regions. Finally, the author compares the regions defined in this paper with the BEA regions.