| Abstract: | The objective of this paper is to introduce the Wiener-Kolmogorov (WK) method to business researchers and to applied workers who have an interest in spectral techniques. It is seen that the advantage of the WK method is that it provides better forecasts than autoregressive regression analysis when the order of the true autoregressive process is large. The paper outlines the steps involved in the WK method. Also discussed is a labor-saving feature to guide one at the outset as to whether the WK algorithm should be used. A numerical example is given to illustrate the application of the method in time-series forecasting. |
