We present non-linear models to capture the turning points in global economic activity as well as in advanced and emerging economies from 1980 to 2017. We first estimate Markov Switching models within a univariate framework. These models support the relevance of three business cycle regimes (recessions, low growth and high growth) for economic activity at the global level and in advanced and emerging economies. In a second part, we find that the regimes of the Markov Switching models can be well explained with activity, survey and commodity price variables within a discrete choice framework, specifically multinomial logit models, therefore reinforcing the economic interpretation of the regimes.
Global GDP Markov Switching multinomial logit turning points