Introducing Monte Carlo Analysis
Please respond to the following questions. NOTE: DO NOT WRITE STUDENT NAME AND PROFESSOR NAME OR ANY OTHER INFORMATION ON THE PAGE (that’s a separate page), I can take care of that. Q1. Using the information presented in “Common Influences on Risk Perception” Figure 6-3 (Hillson & Simon text), see attachment , determine the conscious factors, subconscious factors, and affective factors for this project. Examine how awareness of such factors influences the decision to hire outside vendors. In addition, analyze how the stated factors help improve the overall facilitation and effectiveness of the risk management. Q2. Review the Monte Carlo Analysis method presented in Chapter 15 of the Hillson & Simon text. Then, determine whether you would recommend to a project manager the use of this methodology for a large, complex project. Include an example to support your response. If you would not recommend the use of a method such as Monte Carlo, explain what you would recommend as an alternative tool that would allow the project manager to make informed decisions. Provide a rationale for your recommendation.
Monte Carlo analysis is based on the generation of random numbers, allowing the random sampling of a range of possibilities from predefined input data in a risk model. The input data must reflect the degree of uncertainty in the project, based on the risks exposed in the risk process. A single analysis is formed from many iterations, each of which runs through the risk model once to produce one outcome calculated from a randomly chosen sample drawn from the input data. An analysis can calculate thousands of outcomes that reflect the range of what is possible, based on the uncertainties reflected in the input data, and these will include the best and worst possible outcomes and all values in between. The results from a Monte Carlo analysis are typically presented in two forms:
- A histogram that shows the range of possible outcomes and the number of times a particular outcome was achieved
- An S-curve, which plots the range of possible outcomes against the cumulative probability of achieving a given value.
Figure 15-1 shows a histogram from a quantitative risk analysis with the number of occurrences for each outturn value plotted against the left-hand y-axis. This is overlaid with the cumulative S-curve from the same data, plotted against the right-hand y-axis. To apply quantitative risk analysis to a project effectively, a number of key steps must be applied. These are summarized below and explained in more detail later in this chapter.
Define the purpose of the analysis. The overall project objectives have already been determined during the Initiation step of the generic ATOM process and documented in the Risk Management Plan. Using this information, the particular emphasis and purpose of the quantitative analysis can be determined. The scope of the analysis might only cover schedule risk or cost risk, or an integrated view may be needed. Quantitative analysis can also be applied to other objectives, such as internal rate of return (IRR) or net present value (NPV).
Figure 15-1 Example Monte Carlo Histogram and S-Curve
Develop the risk model or models. For a schedule risk analysis, it is typical to base the risk model on the critical path network for the project. A cost risk analysis model is usually based on the cost breakdown structure (CBS), which is often set out in a spreadsheet. A single integrated risk model can be created for analysis of both schedule and cost risk by using the critical path network and ensuring that all project costs are included within the schedule.
Generate input data and build analysis models. Once the initial model has been developed, the data required for the analysis can be derived and input. This must reflect all relevant risks, including threats and opportunities, and can include both variability (presented as ranges of values) and the possibility of alternative options (modeled using stochastic branches—see below).
Initial analysis—run model and validate initial results. The completed model is then analyzed by running a large number of iterations. An initial view of the model’s robustness should be taken in order to check that no errors were made in inputting data and that nothing illogical has been included. Any errors should be corrected before proceeding further.
Secondary analysis—run model including risk responses. The risk model is adjusted following further data gathering to include the effects of risk responses and actions. Repeating the analysis assists in understanding the effectiveness of planned responses.
Produce and interpret analytical outputs. The final outputs from the analysis present the range of possible outcomes, allowing assessment of the likelihood of achieving project objectives and exposing the main risk drivers. Decide on appropriate course of action and report results. The outputs produced should be carefully considered and the need for any resulting actions decided upon. Actions could include anything from completely restrategizing the project to making minor adjustments to the logical sequence of the project’s activities. As a final step in the process, a report is produced detailing the analysis, including the results obtained and any resultant decisions or recommended changes.
The post Introducing Monte Carlo Analysis appeared first on Smashing Essays.
Looking for a Similar Assignment? Order now and Get 10% Discount! Use Coupon Code "Newclient"
