Gross domestic product (GDP) serves as the predominant metric utilised for quantifying economic activity within a country and is therefore considered a crucial element in both economic policy formulation and private sector decision-making processes.

Organized by the Institute of Public Finance and the Croatian National Bank, Mateo Ljubišić, a Research Economist – Associate in the Economic Analysis Department of the CNB, presented on 13 November 2025 an article published in the journal Public Sector Economics, in which he analyses various models for forecasting economic activity in Croatia.

The paper seeks to identify the model that most accurately captures short-term movements in GDP, taking into account the specific context and characteristics of a small and open economy that is a member of a monetary union. The use of both domestic and foreign indicators proved particularly important for enhancing the model’s ability to predict outcomes. Simpler models, such as the principal component method, often outperform more sophisticated dynamic models.

The results show that, despite the availability of more advanced methods, extracting factors from two or three groups of indicators, combined with a simple principal component method, yields the best results. The insights obtained improve the speed and accuracy of GDP forecasts, thereby enabling timely planning and implementation of fiscal policy, which is especially important in the context of a monetary union.

The lecture was moderated by Luka Draganić, a researcher at the Institute of Public Finance.

Photo: CNB