Example 12.3: Forecasting Petroleum Sales

The FORECAST Procedure

Example 12.3: Forecasting Petroleum Sales

This example uses the double exponential smoothing method to forecast the monthly U.S. sales of petroleum and related products series (PETROL) from the data set SASHELP.USECON. These data are taken from Business Statistics, published by the U.S. Bureau of Economic Analysis.

The following statements plot the PETROL series:


   title1 "Sales of Petroleum and Related Products";
   
   symbol1 i=spline v=circle;
   axis2 label=( a=-90 r=90 "Petroleum and Coal Products");
   proc gplot data=sashelp.usecon;
      plot petrol * date = 1 /
           haxis= '1jan80'd to '1jan92'd by year
           vaxis=axis2;
      where date >= '1jan80'd;
      format date year4.;
   run;

The plot is shown in Output 12.3.1.

Output 12.3.1: Sales of Petroleum and Related Products

The following statements produce the forecast:


   proc forecast data=sashelp.usecon interval=month
                 method=expo trend=2 lead=12
                 out=out outfull outest=est;
      id date;
      var petrol;
      where date >= '1jan80'd;
   run;

The following statements print the OUTEST= data set:


   title2 'OUTEST= Data Set: EXPO Method';
   proc print data=est;
   run;

The PROC PRINT listing of the output data set is shown in Output 12.3.2.

Output 12.3.2: The OUTEST= Data Set Produced by PROC FORECAST

OUTEST= Data Set: EXPO Method

Obs	_TYPE_	DATE	PETROL
1	N	DEC91	144
2	NRESID	DEC91	144
3	DF	DEC91	142
4	WEIGHT	DEC91	0.1055728
5	S1	DEC91	14165.259
6	S2	DEC91	13933.435
7	SIGMA	DEC91	1281.0945
8	CONSTANT	DEC91	14397.084
9	LINEAR	DEC91	27.363164
10	SST	DEC91	1.17001E9
11	SSE	DEC91	233050838
12	MSE	DEC91	1641203.1
13	RMSE	DEC91	1281.0945
14	MAPE	DEC91	6.5514467
15	MPE	DEC91	-0.147168
16	MAE	DEC91	891.04243
17	ME	DEC91	8.2148584
18	RSQUARE	DEC91	0.8008122

The plot of the forecast is shown in Output 12.3.3.

Output 12.3.3: Forecast of Petroleum and Related Products

Chapter Contents
Previous
Next
Top