on 05-27-2007 3:36 PM
Hi gurus,
Can anyone explain me the steps for outiler correction..
Thanks in advance,
sivaram
outlier correction is used to correct history by correcting values lying outside an expected range
since SCM 4.1 there are two ways of calculating outliers (pl see help file links for exact calculation and the activities needed to use them)-
1. median method - http://help.sap.com/saphelp_scm50/helpdata/en/cf/ab586782ab42b1989e4a44ba40119b/content.htm
2. expost method
http://help.sap.com/saphelp_scm50/helpdata/en/c5/eea7f4741c4e39aff1d6e4fce4b024/content.htm
in /SAPAPO/MC96B you should be able to choose the method for a given profile
Pl use the F1 there for more details on how to use it
"The Sigma factor fac controls outlier detection in the following way: An observed value y is declared to be an outlier if the difference to the forecast value e is greater than fac *s. s denotes the standard deviation of the residuals. "
"If you want to select the periods in which outliers should be corrected, set this indicator and use a set of historical value markings. You mark the historical values either in the statistical forecast view of interactive demand planning or in the univariate forecast profile."
"In the context of the forecast function, outliers in the historic values are defined by the Sigma factor. The greater the Sigma factor the more tolerant the system of atypical values, and the fewer outliers are determined"
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
You need to select Outlier correction in the univariate forecast profile, the system corrects the historical values that it determinesbased on the sigma factor and the method you choose
go to /SAPAPO/MC96B and choose the planning area and in the univariate profile tab you can choose the Outlier Correction in the Control Parameters block - you can choose between none and the methods mentioned
please read this help for some more details
http://help.sap.com/saphelp_scm50/helpdata/en/3a/e08841af99060de10000000a1550b0/content.htm
User | Count |
---|---|
7 | |
4 | |
3 | |
2 | |
2 | |
1 | |
1 | |
1 | |
1 | |
1 |
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.