What is Durbin-Watson in SAP SCM-APO-FCS - Demand Planning?

SAP Term: Durbin-Watson

• Component: SCM-APO-FCS

• Component Name: Demand Planning

• Description: A measure of first-order autocorrelation; that is, of autocorrelation in time series where independent variables are not lagged. The Durbin-Watson statistic lies in the range 0-4. A value of 2 or nearly 2 indicates that there is no first-order autocorrelation. An acceptable range is 1.50 - 2.50. Where successive error differences are small, Durbin-Watson is low less than 1.50; this indicates the presence of positive autocorrelation. Positive autocorrelation is very common. Where successive error differences are large, Durbin-Watson is high more than 2.50; this indicates the presence of negative autocorrelation. Negative autocorrelation is not particularly common. If the Durbin-Watson statistic is greater than R square, it is likely that autocorrelation exists. Autocorrelation indicates that the forecast model could be improved on. In time series with lagged variables, the Durbin-Watson statistic is unreliable as it tends toward a value of 2.0.

Smart SAP Assistant

• Key Concepts: 
  Durbin-Watson is a statistical test used to detect autocorrelation in a time series. It is used in SAP's SCM-APO-FCS Demand Planning component to measure the correlation between successive values in a time series. The test is based on the idea that if there is no autocorrelation, then the successive values should be independent of each other. 
  
  How to use it: 
  The Durbin-Watson test can be used to detect autocorrelation in a time series. To use it, the user must first calculate the autocorrelation coefficient for each pair of successive values in the time series. The user then calculates the Durbin-Watson statistic by summing up the squares of the autocorrelation coefficients and dividing by the sum of the squares of all the values in the time series. The result is a number between 0 and 4, with 0 indicating strong autocorrelation and 4 indicating no autocorrelation. 
  
  Tips & Tricks: 
  When using the Durbin-Watson test, it is important to remember that it only measures linear autocorrelation. If there is non-linear autocorrelation present, then the test may not be able to detect it. Additionally, it is important to remember that the test only measures correlation between successive values, so if there is correlation between non-successive values, then this will not be detected by the test. 
  
  Related Information: 
  The Durbin-Watson test is related to other tests such as the Breusch-Godfrey test and the Ljung-Box test, which are also used to detect autocorrelation in time series data. Additionally, it is related to other statistical tests such as regression analysis and correlation analysis, which can be used to measure relationships between variables.