Turkish bank efficiency: Bayesian estimation with undesirable outputs

This paper analyzes the productivity and efficiency of Turkish banks from 2002 to 2010. We obtained estimates of efficiency, productivity growth and efficiency growth using a Bayesian stochastic frontier approach and focused on accounting for Non-Performing Loans (NPLs) for use in our model. Specifically, we introduce NPLs as a bad output in an input distance function, and estimate a system of non-linear equations subject to endogeneity. We confirm that the productivity growth of Turkish banks was positive over the period of this study, which was mainly due to the improvement in technology, while efficiency growth continued to be negative over the same period. Methodologically, we also prove that not accounting for NPLs in estimating the frontier model might seriously distort the efficiency and productivity results. The study also provides measures of shadow prices for NPL and discusses the results in terms of several interesting trends in Turkish banking. Finally, the paper provides efficiency and productivity comparisons between domestic and foreign banks.