DETERMINATION OF CONFIDENTIAL INTERVALS AT FORECASTING TREND-PERIODIC ECONOMIC PROCESSES WITH HARMONIC ANALYSIS METHODS

Abstract

The purpose of the study was to develop a method for constructing an interval forecast of trend-periodic economic processes using harmonic analysis methods and EXCEL tools. The method involves constructing a time series model in the form of a multiple linear regression equation that includes a trend and only a few significant harmonics for the seasonal and cyclic components. This allows for the determination of confidence intervals to use the approach used for interval estimation of the forecast using the multiple linear regression equation. The method is implemented by the example of constructing point and interval forecasts for a time series including a trend, seasonal and cyclical fluctuations. The high predictive ability of the model in predicting trend-periodic processes is shown.