Identifying Banking Crises Dates

This paper identifies banking crises dates based on market information embedded in banking stocks. Specifically, we estimate returns on banking indices around the world using a Markov Switching Autoregressive (MS-AR) model to capture regime shift behaviour in both the mean and variance from 1995 to 2010 with the sample of 77 countries. Overall, we find evidence of three regimes (bull/bear/crisis) and identify banking crisis dates in the majority of countries examined. The crisis regime is characterized by higher volatility and lower stock returns. Finally, our MS-AR modelling offers an alternative ex-ante method of crisis dates identification and our identified crisis dates are, in general, consistent with the IMF's ex-post crisis date classification