Forecasting GDP at the Regional Level with Many Predictors

In this paper, we assess the accuracy of macroeconomic forecasts at the regional level using a large data set at quarterly frequency. We forecast gross domestic product (GDP) for two German states (Free State of Saxony and Baden-Württemberg) and Eastern Germany. We overcome the problem of a ?data-poor environment? at the sub-national level by complementing various regional indicators with more than 200 national and international ones. We calculate single?indicator, multi?indicator, pooled and factor forecasts in a pseudo real?time setting. Our results show that we can significantly increase forecast accuracy compared to an autoregressive benchmark model, both for short and long term predictions. Furthermore, regional indicators play a crucial role for forecasting regional GDP. Keywords: regional forecasting, forecast combination, factor models, model confidence set, data?rich environment JEL Code: C32, C52, C53, E37, R11