Abstract:
This paper re‐examines the stochastic properties of U.S. state real per capita personal income, using new panel unit‐root procedures. The new developments incorporate non‐linearity, asymmetry, and cross‐sectional correlation within panel‐data estimation. Including nonlinearity and asymmetry finds that 43 states exhibit stationary real per capita personal income whereas including only nonlinearity produces 42 states that exhibit stationarity. Stated differently, we find that two states exhibit nonstationary real per capita personal income when considering nonlinearity, asymmetry, and cross‐sectional dependence.
