Alternative method to measure the VAT gap in the EU: Stochastic tax frontier model approach.

In this paper, we pursue an alternative method to measure the Value Added Tax gap in the European Union using the stochastic tax frontier model. We use the Value Added Tax total tax liability as the input to estimate the optimal frontier of the Value Added Tax, as well as to predict technical inefficiency. Using the latest innovations of the stochastic frontier approach, we aim to obtain the accurate size of the Value Added Tax gap in the EU-26 countries and contrast them with extant estimates. The obtained estimates of the Value Added Tax gap using the stochastic tax frontier model are different from the estimates produced by the top-down method to calculate the Value Added Tax gap in the EU. Moreover, the stochastic tax frontier approach allows us to disentangle the Value Added Tax gap, which is time dependent, from the persistent Value Added Tax gap, which is country specific. The stochastic tax frontier model allows us to test the effect of exogenous factors on the technical inefficiency of the Value Added Tax and propose appropriate policy recommendations.