Investigating the Impact of Unemployment Rate on the Romanian Shadow Economy. A Complex Approach Based on ARDL and SVAR Analysis

The paper aims to investigate the potential impact of unemployment rates (both recorded and ILO) on the Romanian shadow economy (SE) for quarterly data covering the period 2000-2013, using ARDL cointegration method in conjunction with the structural VAR (SVAR) analysis in order to provide evidence for both the long and short-run dynamics between the variables. The size of the shadow economy as % of official GDP was estimated previously using a special case of the structural equation models - the MIMIC model, recording the value of 40% at the beginning of 2000 and following a downward trend over the analyzed period. The results of ARDL approach pointed out that there is no long-run relation between unemployment rates and the Romanian shadow economy. The relationship between the two variables is further tested by imposing a long-run restriction in the Structural VAR model to analyze the effect in the size of the Romanian shadow economy to a temporary shock in unemployment rates. The impulse response function generated by the Structural VAR confirms that in the short run, a rise in the recorded unemployment rate will lead to an increase in the size of the shadow economy, meanwhile an increase in the ILO unemployment rate highlighted a decrease in the size of the shadow economy.