What determines unemployment in the long run? Band spectrum regression on ten countries

This paper presents an empirical analysis of the relation between unemployment and macroeconomic performance. A strong correlation has been pointed out before, but a crucial question is over what time-horizon this holds. To the best of our knowledge, no previous cross-country study has shown that there is a long-run relationship between unemployment and macroeconomic performance over a time-period that stretches before the 1960s. To address this issue, we use wavelet analysis to decompose the time series into short, medium and long-run variations, and band spectrum regressions on the relation between unemployment, GDP, investment, long-term interest rate and TFP, covering ten countries 1913-2016. This methodology has several advantages compared to standard econometrical methods and other tools for decomposition. Our results show that unemployment correlates negatively with the long-run components of investment. This suggests that aggregate demand and capital formation inuence long-term labor market outcomes. According to our estimates ca 17-percent of overall variations in unemployment and 29 percent of the long-run variations may be explained by long-run variations in capital formation.