Quantitative Project Risk Register

We start defining the elements that compose a quantitative risk register.

Consider events such as Delays due to abnormal weather, labor accidents during construction and spillages or damages to a neighboring construction site.

The frequency and severity segments of event risks is completed here to run a simulation.

Density curves and tornado charts generated after a simulation are analyzed before any mitigation plan is evaluated.

The RISKMAKEINPUT function synthesizes or integrates together the two effects FREQUENCY and SEVERITY into a single tornado graph bar per activity.

Many decision makers like this tornado chart because it can be expressed in the “currency” of the measured unit of the output variable.

Powerful and correct FREQUENCY and SEVERITY models can be easily created with this function.

Analyses of other tornado charts, once the compound function has slightly corrected the proper way on which multiple frequency events are dealt.

This graph shows the magnitudes of the bars scaled or "normalized" by the standard deviation of the output and the standard deviation of that input.

Correlation coefficients can be written directly through a statistic function on your worksheet.

This tornado graphs shows the amount of change in the output attributable to each input.

A spider graph shows how the value of the output statistic changes as the sampled input value changes.

In many situations, it is important to account for correlation between input variables.

It should be clear now that a correlation coefficient establishes between a pair of variables.

During this simulation, @RISK will now consider the presence of a simulation matrix.

The RiskSimTable function allows the analysis of multiple scenarios on the same simulation run.

We redefine the model to include the impact of applying mitigation strategies to key risks.

We stand to simulate 80 moving variables, 5,000 times, before and after mitigation strategies, and then evaluate results.

Which mitigation strategies are worth implementing considering that some of these risks may have correlated effects upon the others.

Now we define the Adjustable Cell Ranges section of the optimization.

With this command the user defines essentially how to run the optimization process.

We analyze the Watcher, responsible for regulating and reporting all RISKOptimizer activity.

We evaluate whether correlation plays a role on the optimized answer.

We compare four calculated optimization strategies. 

We have included a final tab named Comparison where risks are compared using both methodologies: quantitative versus qualitative risk analysis.