The Statistics and History Correction Parameters page provides a summary of the parameters set for History Correction. You can edit the values at product-customer level. 

Before you start

You can select the customer from the context selector in the top-right of the page. There are options for all levels of customer hierarchy, but you must select a customer account as promotion plans are specific to a customer. Select a customer from the list at the top right of the page, or manually enter the required value using the search function.

Parameters

ParametersValues
Correct From

Specifies the baseline for correction. In the cases of From Mean or From Trend Line, the values are calculated using periodic data starting from the product’s effective date and ending with the last effective period. 

  • Off: Selecting this option prevents the application from calculating outliers for correction. 
  • From Mean: Selecting this option enables the application to calculate outliers based on values being greater than x standard deviations from the Mean. 
  • From Trend: Selecting this option enables the application to calculate outliers based on values being greater than x standard deviations from the Trend line. 
  • From Trend Seasonal: Selecting this option enables the application to calculate outliers based on values greater than x standard deviations from the Trend Seasonal line. 
Correct What

Specifies which of the outlier's history correction should be applied to, controlled by options available in the drop-down list: 

  • Off: Selecting this option prevents the application from calculating outliers for correction. 
  • Spikes: Selecting this option corrects outliers that are above the upper limit. 
  • Dips: Selecting this option corrects outliers that are below the lower limit. 
  • Both: Selecting this option corrects outliers that are above the upper limit or that are below the lower limit. 
Outlier MagnitudeThis parameter specifies the number of standard deviations from the mean (or standard errors from the trend line) that should determine an outlier. A value of two highlights any data points that are more than two standard deviations from the mean (or standard errors from the trendline) as outliers. 
Correct To

If an outlier is to be corrected, this parameter determines the value that it should be corrected to. The parameter setting is selected from the below options: 

  • To Limit: Corrects outliers to the upper or lower limit.  
  • To Mean: Corrects outliers to the Mean.  
  • To Trend: Corrects outliers to the Trend Line. 
  • To Prior Correction: Selecting this option corrects the outliers to the value in the previous period for System Corrected History (U).  In the first period of the system calendar, no correction will occur for this method.   
Period by PeriodSelecting this checkbox forces the system to identify all outliers but enables the user to manually select which outliers should be corrected. If set to No, then all outliers will be automatically corrected as per the Correct To parameter.  When set to Yes, then each outlier period can be reviewed on its own, and a decision taken as to whether to correct. 
EF Correct From, EF Correct What, EF Outlier Magnitude, EF Correct To, and EF Period by PeriodThe values displayed in these columns confirm the data inputs to History Correction. These parameters are managed at the global level in D1000 Global Demand Parameters > 1120: History Correction Parameters or at the product level as explained above.