Forecasting charge-off rates with a panel Tobit model: the role of uncertainty

Based on a large panel dataset of small commercial banks in the United States, this paper employs dynamic Tobit model to analyse role uncertainty forecasting charge-off rates loans for credit card (CC) and residential real estate (RRE). When compared other standard predictors, such as house prices unemployment rates, we find that effect changes is more pronounced. Furthermore, it evident including heteroscedasticity specification leads accurate forecasts.