GDP Forecasting by Czech Institutions: An Empirical Evaluation

Abstract

This paper evaluates the accuracy of real GDP growth forecasts published in the period 1995-2013 by two Czech institutions: the Ministry of Finance (MF) and the Czech National Bank (CNB). A two-stepped approach is adopted: first a battery of forecasting errors (MAE, RMSE, MASE) is calculated, complementary to evaluation papers already available. Then statistical analysis is carried out by comparing both MF and CNB forecasts with OECD, European Commission and consensus benchmarks (Kruskal-Wallis test), assessing the presence of systemic bias (Wilcoxon test) and determining their incremental improvement (Page trend test). The results show that although some error patterns might suggest performance deficiencies (i.e. during the recession periods), the accuracy of forecasts prepared by both the MF and CNB does not differ significantly from the benchmark forecasts; MF and CNB predictions do not contain systemic bias and their accuracy improves as the horizon shortens. The paper also highlights several methodological shortcomings in the internal evaluations conducted by both institutions, indicating a potential for further improvement.

AR Model or Machine Learning for Forecasting GDP and Consumer Price for G7 Countries

“…Forni, Gambetti, Lippi, & Sala (2017) found that noise shocks cause hump-shaped responses of GDP, consumption and investment, and explain a large part of their prediction error variance in business cycles. Sindelar (2017) showed that although some error patterns might indicate performance deficiencies, the validity of forecasts made by the Ministry of Finance in Czech and Czech National Bank does not differ much from the benchmark forecasting.…”

The accuracy of state budget planning: case of the Czech Republic

“…Nepoměrně bohatšími poznatky nicméně na druhé straně disponujeme v oblasti makroekonomických prognóz, které jsou základem fiskálního plánování. Ať už jde o evaluace vlastního Ministerstva financí (MF, 2013a), výstupů Výboru pro rozpočtové prognózy (VRP, 2022), případně dalších autorů (Šindelář, 2017;Antal, Hlaváček a Horvath, 2008;Novotný a Raková, 2011;aj.). Valná většina těchto studií indikuje konkurenceschopnost predikcí MF vůči dalším institucím (z hlediska jejich přesnosti) a nepřítomnost systémových chyb.…”