When doing risk analysis simulation modeling, it’s critical to represent the fact that many variables are related. Very rarely are all variables completely independent of one another. For example, when interest rates are low, housing starts tend to go up. This relationship is represented by a correlation coefficient, a number between -1 and 1. -1 means the two variables are perfectly negatively correlated; that is, when interest rates go up 1 unit, housing starts go down 1 unit. A coefficient of 1 is exactly the opposite, and 0 means there is no relationship between the variables at all. Typical coefficients are between these extremes. This correlation between input variables can and must be captured in your financial risk analysis models. Even if you are using expert opinion, estimating these relationships is better than ignoring them completely.
@RISK provides an easy way to define correlation coefficients. Through the use of a slider bar, you can dynamically update coefficients between variables as well as scatter plots representing those variables. This helps you visualize and more easily define these relationships.
For a quick video demonstrating this, see: