Abstract
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 paper groups states into regions based on the similarities in their business cycles. We applied k-means cluster analysis to the cyclical components of Stock-Watson-type indices estimated at the state level to group the 48 contiguous states into eight regions with similar cycles. We then compare the cohesion of the regions so defined with the cohesion of the BEA regions. Finally, we examine how that definition affects the results of some recent regional business cycle analysis. © 2005 President and Fellows of Harvard College and the Massachusetts Institute of Technology.