Most people understand that @RISK and Monte Carlo simulation are designed to be an improvement on single-point estimates. In practice, however, I often see people using @RISK as a forecasting tool to get yet another single-point estimate, such as the 90th percentile, without putting it into the context of the potential range of outcomes.
This is probably the difference between a forecasting and a decision-making. The former tends to focus on historical or observed trends and developing specific scenarios (e.g. best, most likely, worse) based on expert opinion, while the latter is concerned with confidence ranges and likelihood.
Indeed, it’s not until you add probability, as with @RISK, that you start to measure the quality of your forecasts (i.e. your confidence level) and calculate the margin of error – something that’s crucial in all walks of life!
In my opinion, therefore, @RISK is much more of a decision-making tool than a forecasting tool. Both involve trying to predict the future but the addition of probability gives decision-makers vital insight to a problem.
Don’t you just love semantics!
Ian Wallace, ACMA
Palisade Training Team