A Strategy to Improve the Survey of Professional Forecasters (SPF) Predictions Using Bias-Corrected-Accelerated (BCA) Bootstrap Forecast Intervals

Purpose – The purpose of the research is to find a suitable strategy to improve the SPF predictions for inflation. Design/methodology/approach – some alternative forecasts for the annual rate of change for the HICP for EU were developed, their accuracy was evaluated, using proper accuracy measures, and it was compared with the accuracy of Survey of Professional Forecasters (SPF) predictions. Findings – a synergy of strategies (combined forecasts, BCA bootstrap technique and the method of regression models) proved to be a good strategy to improve the forecasts accuracy on the horizon January 2010-May 2012. Practical implications – the proposed strategy to get more accurate predictions than SPF or naïve ones will help the government in improving the decisions at macroeconomic level and the economic agents in having a better planning activity. Research limitations – the proposed strategy of improving the forecasts accuracy is dependent by the particularities of the data series and it can not be recommended for all types of predictions Originality/ value – the proposed strategy is an original contribution of the author in literature, the BCA bootstrap intervals never being used in literature to get better predictions. The historical accuracy method used to construct new forecasts is also an original proposal of the author in literature that was also applied in this research.