The Relationship between Shadow Economy and Unemployment Rate. A ARDL Causality Analysis for the Case Of Romania

The paper aims to investigate the nature of the relationship between the shadow economy (SE) and unemployment rates (both registered and ILO) for the case of Romania using Pesaran et al.(2001) bounds tests approach for cointegration. The study uses quarterly data covering the period 2000-2010. The size of Romanian shadow economy is estimated using the currency demand approach based on VECM models, stating that its size is decreasing over the analyzed period, from 36.5% at the end of 2000 to about 31.5% of real GDP at the middle of 2010. To investigate the long-run causal linkages and short-run dynamics between shadow economy and unemployment rate, ARDL cointegration approach is applied. Cointegration test results shows that in short-run both ILO and registered unemployment rate has a negative and statistically significant effect on the size of the shadow economy, while in the long-run the unemployment rates have a positive effect on shadow economy. The ARDL causality results revealed the existence of a long-run unidirectional causality that runs from unemployment rates (registered or ILO) to shadow economy. In addition, the CUSUM and CUSUMSQ tests confirm the stability of the both causal relationships.