Applies to: @RISK 5.x and Up

Error:

"The correlation matrix ... has multiple inputs assigned to the same matrix position. Instances can be used to correlate multiple sets of inputs with the same matrix. Continue the simulation anyway?"

 

Background:

Correlation is specified by RiskCorrmat property functions within the @RISK distributions. 

• If you have two or more groups of inputs to be correlated using the same matrix, your RiskCorrmat functions need a third argument, called an instance. 

 

Solutions:

We recommend you click No when you see this prompt and edit your workbook.

• Please see Same Correlation Coefficients for Several Groups of Inputs for more details

If you are using this correlation to create a correlated time series:

• Please see Correlation of Time Series
• You need the Industrial Edition of @RISK 6.0 and above to use time series.

If you click Yes and let the simulation proceed

• Please download the attached example SameMatrixPosition.xls

Using the Example:

If you apply the same 2×2 correlation matrix to both A16:A17 and B16:B17 without specifying instances, @RISK will correlate A16 with A17 and B16 with B17 as intended.

However, because the same matrix is used for both groups, @RISK must rely on the same underlying random numbers for each pair. As a result, A16 and B16 will be perfectly correlated (correlation = 1), and the same will occur for A17 and B17—almost certainly an unintended outcome.

In contrast, using the same setup with instances for D16:D17 and E16:E17 correctly applies the correlations within each group while preventing unwanted correlations between groups.

Attachments:
KB144 MeanOutputs.xlsx