摘要：The aim of this paper is to determine whether the existing leading indicators system CROLEI (CROatian Leading Economic Indicators) and its derivative, the CROLEI forecasting index, predict overall Croatian economic activity reliably. The need to evaluate the CROLEI system and the index stems from the modification of the barometric method on which the system and the index are founded on in its application in Croatia. The evaluation of the forecasting power involved the construction of six alternative forecasting indices, which not only challenge the original CROLEI index, but also enable comparisons of forecasting power. The construction of the alternative forecasting indices is also based on the barometric method. The authors then proceed to adjust more complex measurements i.e. forecasting power evaluation matrix, in order to obtain credible forecasting power estimates. Forecasting power is also estimated using two regression models that allow for the forecasting of reference series and yield measurements of forecasting power. The results of both approaches indicate not only that the original CROLEI has by far the greatest forecasting power, but also that it is able to predict the turning points in the economic cycle with the highest probability.
