Business cycle asymmetries in Turkey: an application of Markov-switching autoregressions

This paper examines business cycle characteristics of the Turkish economy in the liberalization (post-1980) period using a Markov-switching Autoregressive (MSAR) model framework. The importance of the model selection process is emphasized in an extensive search for the appropriate MS model. The business cycle properties are found to be very sensitive to the state dimension, the choice of the MS model (classified according to regime-dependent parameters) and the autoregressive lag order. The chosen two-regime MS model suggests four recessionary and five expansionary phases in the post-1980 period. Business cycle phases are found to be asymmetric with the probability of switching from a recession to expansion exceeding the probability of switching from expansion to recession. The paper also provides evidence on the usefulness of a non-linear model as compared with a linear alternative in the context of business cycle research in an emerging economy using various parametric and non-parametric tests. Non-linear and linear models are compared and evaluated using kernel density and conditional expectation estimates by simulating data from respective models.