Quantitative and Qualitative Forecasting

458 section 4 Srppr,r lNn L)ru,lNn Pt,,lxNrr,lr; ,rtn Corumor Using tlrcser lhclors. il' we cxpccte d dcnrancl lbr ncrt ycar to be I , 1(X) un its, we r.i,ou ld litre - cast the demand t0 occur as AVERAGE ExprcrEo S.{LEs FoR IJEu,rNo ron EecH Srr.soN NexrYeen (1.lO0l4) Srlsor'.rL[j tcrott NExr AR's Srrsorrt.ForEc'rst Spring Summer Fall Winter Total 275 275 ?75 0.8 1.1 1.2 0.6 220 330 165 x X x X Eiff;EIeas+; ffi- For a step-by-step walkthrough of this example, vi$it wwwmhhe.com/ iacobsl 4e_sbs_chl 8. r Jo; The seasonal factor may be pericldicerlly updated as new data are availablc. The following example shows the seasonal factor and multiplicative seasonal variation. EXAMPLE {8"4; Gomputing Trend and Seasanal Factor fronn a Linear Regression Line Obtained with Excel Forecast the demand for each quarter of the next year using trend and seasonal factors. Demand for the past two years is in the following table: Qr,r \RTE]{ A}fotiN'l QI_rAIr I LR .{M0UN I 1 2 4 300 2CA 224 530 5 6 / 8 523 420 400 700 s&L$J?i#ru First, we plot as in Exhibit 18.10 and then calculate the slope and intercept using Excel. For Excel the quarters are numbered i through 8. The 'known,]rs" are the amounts (300,200,220, etc.), and the "known,rs" are the quarter numbers (1,2,3, etc.). We obtain a slope : 52.3 (rounded), and intercept -- 116.1 (rounded). The equation for the line is Forecast Including Trend (FTI) : 116.1 + 52.3t Next we can derive a seasonal index by comparing the actual data with the trend line, as in Exhibit I 8. I 1. The seasonal faclor was developed by averaging the same quarters in each year.

We can compute the 2013 forccast including trend and seasonal factors (FITS) as follows: FITS,:FITXSeasonal I-2$13 FITS, : 1176.1 + 52.3(9)11.25 : 808 Itr-2013 FITS,' : [176.1 + 52.3(10)]0.79 : 552 III-2013 FITS,, : [176.1 + 52.3(11)]0.70: 526 IV-2013 FITS1, : [176.1 + 52.3{1?)11.28 : 1,029 Note, these numbers were calculated using Excel, so your numbers may differ slightly due to rounding.