Modelling Corruption Perceptions Through Latent Class Models: Evidence from Eastern Europe and Central Asian Countries

Abstract

This work proposes a multidimensional framework, based on a Latent Class model, to identify various types of corruption and their importance. A dataset of Eastern European and Central Asian countries is used to identify four groups of corrupt activities, which go beyond the usual classification of corruption into administrative and political. Estimates are validated by means of a direct administrative corruption index derived from the same dataset and comparison of corruption perception rankings published by Transparency International. The potential of the proposed approach is illustrated with an application to the relationship between firms' competitiveness and the latent classes of corruption identified.