This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Forecast Errors In using the word error, we are referring to the difference between the forecast vaIUC
and what actually occurred. In statistics, these errors are called residuals. As long as
the forecast value is within the conﬁdence limits, as we discuss later in “Measurement
of Error,” this is not really an error. But common usage refers to the difference as an
error. \ Demand for a product is generated through the interaction of a number of factors
too complex to describe accurately in a model. Therefore, all forecasts certainly FQREQAST ERRoRs (p. 323) 2 Types
— Bias  when mistake is made, eg. wrong variables, or relationships, etc random — cannot be explained W MAD: é \AVFA ’ Use  standard error (6) “  variances (62)
 Mean absolute deviation (MAD)  errors generally normally distributed, thus,
1 MAD = 0.8 SD's Tr kin i nal T  measures whether f/c average is keeping pace
with real changes in demand TS = Running sum of fie errors
MAD (see Exh. 7.9) 8.1 Computing the Mean Absolute Deviation (MAD), the Running Sum of Forecast Errors (RSFE). ‘E X hi1? l t 13.9 ' and the Tracking Signal (TS) from Forecast and Actual Data (ﬁghts—{D A A’F 37"" lA'Fl ilA’Fl *zlA‘Fl _RSFE*~ Month Domead Forecast Actual Deviation RSFE Abs. Dev. Sum of Abs. Dev. MAD* TS — W
1 1,000 950 —50 —50 50 50 50 —1
2 1,000 1,070 +70 +20 70 120 60 .33
3 1,000 1.100 +100 +120 100 220 73.3 1.64
4 1.000 960 —40 +80 40 260 65 1.2
5 1,000 1,090 +90 + 170 ’ 90 350 70 2.4
6 1,000 1,050 +50 #2205 50 499 @ 3.3 *For Month 6. MAD = 400 + 6 =66?) ,, RSFE 220
For Month 6, TS = —— = — = 3.3 MADs.
MAD 66.7 A Plot of the Tracking Actual _
exceeds Signals Calculated In
forecast Exhibit 13.9
Tracking
signal
‘ Actual is
less than forecast ...
View Full
Document
 Fall '11
 bhole

Click to edit the document details