Nowcasting GDP of Bosnia and Herzegovina: A Comparison of Forecast Accuracy Models

Abstract

The paper explores the possibilities of creating an econometric model for making short-term forecasts of the Gross Domestic Product of Bosnia and Herzegovina (GDP of B&H). Its aim is to determine the most representative and most efficient model for forecasting the quarterly GDP of B&H. This is the first paper that simultaneously compares ARIMA models, bridge models and factor models in three different time periods. All variables are available for the period of 2006q1-2016q4. The final choice of the model for forecasting the quarterly GDP of B&H was selected on the basis of a comparative analysis of the predictive efficiency of the analysed models. Based on the obtained results, the most efficient model for forecasting quarterly GDP of B&H is the bridge model, which includes four variables as regressor: Retail sale of other goods, Total loans, Manufacturing and Manufacture of food products.

New Market Information Applications in East Africa: Three Essays on Mapping Trade Flows, Identifying Vulnerability in Food Commodity Networks, and Nowcasting Agricultural Prices in East Africa

“…Note that, for other data series, contemporaneous data relevant to the simulation date remains is kept in the simulation data. This simulates a real-world application, whereby price data are known for other marketplaces and products, but unknown for the marketplace commodity of interest.122 For comparative nowcasting method examples, seeSabu and Kumar 2020;Abdić et al 2020;Chernis and Sekkel 2018;Kuzin et al 2009;Giannone et al 2008. …”