A multivariate regression algorithm which identifies dependencies between a specific value and other values.
In its simplest form, the linear regression algorithm models data by using a straight line. A response variable, Y, is modeled as a linear function of a predictor variable, X.
A more complex form, multivariate linear regression, models a response variable that is based on several predictors by fitting a hyperplane into the data. Coefficients generated by the model are the Y-intercept of the line or plane and slope of the line or plane. The multivariate linear regression algorithm uses the least squares method to calculate the regression coefficients.
In the apply phase, the model coefficients predict the target from input predictor vectors.
This algorithm predicts the value of a dependent (target) variable, based on the value of independent (predictor) variables.
For example, given the number of televisions, DVD players, and VCRs sold during the first quarter in the East region, how many cameras were sold during the same period in the same region? Restrict sales data to prior year actuals.
Mining Wizard presents information to Data Mining Framework by using a set of predictor and target MDX expressions that you supply:
Table 12. Predictor Expressions
Member Expression | Example |
|---|---|
Predictor.Predictor specifies member or member set to use for the predictor domain. | {[Fruit].Children}) |
Predictor.Sequence defines the sequence to be traversed for the predictor, generally a time dimension range. | {[Jan 1].Level.Members} |
Predictor.External (optional) defines the scope of the predictor. | {[East].Children} |
Predictor.Anchor (optional) specifies additional restrictions from other dimensions. | {([2001], [Actual], [Sales])} |
Table 13. Target Expressions
Target Expression | Example |
|---|---|
Target.Target specifies the single member to use as the target domain. | {[Camera]} |
Target.Sequence defines the sequence to be traversed for the target, generally a time dimension range. | {[Jan 1].Level.Members} |
Target.External (optional) defines the scope of the target. | {[East].Children} |
Target.Anchor (optional) specifies additional restrictions from other dimensions. | {([2001], [Actual], [Sales])} |
If you leave optional dimensions blank, information is taken from the root of the dimension.
This information will be made available at a later release.
This information will be made available at a later release.