Computation - Operations Management/Industrial Engineering

Computation

Forecasting

Compare

	Forecasting
	- Compare

The comparison option is for the comparison of different forecasting methods on a single time series. The purpose is to illustrate the differences between the methods and allow experimentation in the choice of parameters.

The dialog allows selection of a name, time horizon, history and number of extra columns. The check boxes at the bottom select one or more forecasting methods. The fields to the right of the check boxes indicate how many forecasts of each type are to placed on the worksheet

The compare option creates a worksheet with the same name as the forecast. The results for a simulated example are shown below with both moving average and regression forecasts. This particular data had a trend in the mean demand with a value of 1.

As expected the regression forecast does much better at estimating the future because it includes a trend estimate. The error for the moving average has a positive bias because the estimate always lags behind the data. The estimate for the trend for the regression forecast varies about its true value of 1 and the mean error is small.