 Risk Analysis Tip (a sample ModelAssist topic)
Presenting your Risk Analysis Model and Results (1 of 3)
The following Risk Analysis Tip has been drawn from material in ModelAssistT. ModelAssist users can consult the ModelAssist-references (in the form of Mxxx) for additional information. To read more About ModelAssist and get a free download of the demo version, click here.
Introduction
For a lot of areas of business and government, risk analysis is still a relatively new field. Complex Monte Carl models, probability distributions and statistics can leave the reader of a risk analysis report or attendant of a presentation thoroughly confused. The reader may have little understanding of the methods employed in risk analysis or of how to interpret and make decisions from its results. The goal of risk analysis is however to support decisions and thus it is essential that a risk analysis report or presentation guides the reader through the assumptions, results and conclusions in a manner that is transparent, efficient and interesting. This Risk Analysis Tip will give you an introduction to how to best explain your risk analysis assumptions. In the next two Risk Analysis Tips, we will discuss how to best present your risk analysis results.
Be explicit!
The key to gaining acceptance to a model's results is very often the acceptance of the model's structure and assumptions. We recommend that you are very explicit about your assumptions. Being explicit about any assumptions made in your model will build trust and give people the ability to challenge and improve assumptions. The beauty of a Monte Carlo simulation model is that you don't have to use just one number in each of your assumptions as it has the ability to include uncertainty about your. You can even combine difference in expert opinions (M0229).
We also advise you to make a summary of all your assumptions in a prominent place in your report rather than just have them scattered through the report.
.and use pictorial representations
A risk analysis model will often have a fairly complex structure and you will need to find ways of explaining the model dynamics and structure that can quickly be checked. A useful first step is usually to draw up a schematic diagram of the structure of the model. The type of schematic diagram will obviously depend on the problem being modeled: GANTT charts, site plans with phases, work breakdown structure, flow diagrams, event trees etc. Pictorial representations that convey the required information often greatly help in explaining the structure of your risk analysis model.
The next step is to show the key quantitative assumptions that are made for the model's variables.
How to present distributions and correlations?
Using the parameters of a probability distribution (e.g. mean, 10% and 90% percentiles) to explain how a model variable has been characterized will often be informative when explaining your model's logic. In addition, showing a sketch of the distributions that are used, such as the Poisson distribution below, is much more informative than knowing that a Poisson distribution with lambda = 7 was used.
Sketches are also very useful when you want to explain partial or intermediate model results. For example, a summary plot as shown below is useful for demonstrating the numbers that come out of what could be a complex time series model.
Also, scatter plots are very useful for giving an overview of complicated correlation structures between two or more variables. For example, when you used a rank order correlation coefficient in your model to correlate two variables, it is often very difficult to imagine what a certain value of the correlation coefficient 'r' actually means. This difficulty is compounded by the fact that the same degree of correlation will look quite different on scatter plots for different distribution types, e.g. two Lognormals with a 0.7 correlation will produce a different scatter pattern than two Uniform distributions with the same correlation (see M0389). Presenting a scatter plot of the two correlated variables is therefore useful and will give reviewers a feeling of what the r mean in terms of a correlation's pattern.
Finally, we encourage you to have someone who has not been involved in your project proofread your report or review your presentation. Remember that the goal of your risk analysis is to support decisions and therefore making sure that the decisionmakers understand your model in order to accept its results is critically important!
What's next?
After today's tip on how to present your Risk Analysis model, we will discuss how to present your Risk Analysis results in the next two Risk Analysis Results. In addition, ModelAssist gives you a more complete list of good practices on how to present your risk analysis model and its results.
ModelAssist
- The material within this 'Risk Analysis Tip' comes from one of over 500 risk analysis topics available in ModelAssist, which gives a more detailed explanation of the above methods and any risk analysis techniques involved.
> Learn more about ModelAssist
top |
