A Matched Pairs Analysis of State Growth Differences

The American states have provided a rich laboratory in which to examine influences on economic growth, physical capital, human capital, and a variety of policy variables. Existing studies typically use broad cross sections of all states or particular regional subsamples. Pairwise matching is an alternative design for better controlling of omitted variables. We estimate a growth model of U.S. states for 1997–2005 before and after applying different pairwise matching techniques. Our results indicate that sample estimates based on pairwise matching substantially improve the overall ability of the growth model to identify the growth‐enhancing effects of lower tax burdens in general and lower individual income‐tax rates in particular. These effects are more pronounced with narrower matching criteria