Time series dynamics of US State unemployment rates

This paper examines the time series properties of state and national unempl oyment rates. Based upon unit root, variance ratio, and cointegration tests , as well as Granger-causality and error-correction model results, several important conclusions can be made. First, forecasting models that include o nly levels of unemployment rates may produce spurious regression results. S econd, in the vast majority of cases, there is no long run co-movement betw een the aggregate US unemployment rate and individual state unemployment ra tes. Third, models that are specified in first-differences generally yield reliable insights into state-national unemployment relationships.