Calculates the statistical variance of the specified data set (expList). The calculation is based upon a sample of a population. Variance is a measure of the dispersion of a set of data points around their mean (average) value.
Syntax
@VARIANCE (SKIPNONE | SKIPMISSING | SKIPZERO | SKIPBOTH, expList)
Parameter | Description |
---|---|
SKIPNONE | Includes all cells specified in expList, regardless of their content, during calculation of the variance. |
SKIPMISSING | Excludes all #MISSING values from expList during calculation of the variance. |
SKIPZERO | Excludes all zero (0) values from expList during calculation of the variance. |
SKIPBOTH | Excludes all zero (0) values and #MISSING values from expList during calculation of the variance. |
expList | Comma-delimited list of member specifications, variable names, functions, or numeric expressions. expList provides a list of numeric values across which the variance is calculated. |
Notes
@VARIANCE is different from @VAR, which calculates the variance (difference) between two members.
@VARIANCE assumes that expList represents a sample of the population. If you want expList to represent the entire population, use @VARIANCEP.
@VARIANCE is calculated with the "unbiased" or "n-1" method.
@VARIANCE uses the following formula:
Example
The following example is based on the Sample Basic database. Assume that the Measures dimension contains an additional member, Sales Var. This example uses the @RANGE function to generate expList, and calculates the variance of the sales values for a product family.
FIX (Product) "Sales Var" = @VARIANCE(SKIPBOTH,@RANGE(Sales,@CHILDREN(Product))); ENDFIX
This example produces the following report:
Jan New York Actual Budget ====== ====== Sales Colas 678 640 Root Beer 551 530 Cream Soda 663 510 Fruit Soda 587 620 Diet Drinks #MI #MI Product 2479 2300 Sales Var Product 3687.58 4166.67
See Also