Nothing is more hair raising than exposure to risk without a sense of the level of that exposure. This is especially true in capital investment decisions.
Monte Carlo simulations perform risk analysis by building models of possible results by substituting a range of values—a probability distribution—for any factor that has inherent uncertainty and significant impact on the final result.
By using probability distributions, variables can have different probabilities of different outcomes occurring. Probability distributions are a much more realistic way of describing uncertainty in variables of a risk analysis and improve the quality of sensitivity analysis.
During a Monte Carlo simulation, values are sampled at random from input probability distributions. This is done hundreds or thousands of times, and results in a probability distribution of possible outcomes. It provides a much more comprehensive view of what may happen.
Advantages over deterministic, or “single-point estimate” analysis include:
- Probabilistic Results. Showing how likely each outcome is.
- Clearer Graphical Results. Visual presentation of probabilities.
- Improved Sensitivity Analysis. Sharper sensitivity analysis to show what counts.
- Scenario Analysis: Model repeated variations in combinations of factors to show which scenarios need further investigation.
- Correlation of Inputs. Represent how, in reality, when some factors goes up, others go up or down accordingly.
Done poorly or with low quality input data, the results can be potentially misleading – producing a level of certainty on the basis of some very uncertain assumptions.
Lytton Advisory holds an @Risk software licence which enable us to provide this type of probabilistic analysis to clients, helping them make better informed decisions. Examples of how we have applied this for clients include:
- Estimating financial costs of schedule delay on a major metropolitan public transport project.
- Assessing probability of breaching a cost contingency levels on a +$500 million infrastructure program.
- Building probabilistic NPV profiles in cost benefit analyses given uncertainty about key economic inputs.
Contact us today to find out how we might be able to help you.
Red tape reduction remains on the Government’s agenda in Queensland. Significant work has been done on a social and human services blueprint by the Department of Communities, Child Safety and Disability Services. See:
I am pleased to have played a small part in this. See:
How do you find out what an economic cost benefit analysis should contain?
Reference materials run to hundreds of pages, with detailed explanations depending on the nature and purpose of the investigation and the field under consideration.
I thought a simple introduction would help explain what is involved and prepared Intro to CBA for my clients.
Suppose you are given a cost benefit analysis. Without an economics degree, how do you know it has been properly completed?
Economic CBAs are a decision support tool used to determine the net benefit to an economy of a proposed course of action, a policy or a project. A ‘do something’ case is typically compared to a ‘business as usual’ case to identify incremental changes in benefits and costs, explicitly recognising that not doing a project has implications as well. Costs and benefits occur in different time periods and values are brought to the present to enable comparison of net economic benefits.
If you are wading through one of these reports here is a cheat sheet with questions you can ask the analyst to pierce the veil of certainty these reports often convey. It is based on longstanding advice the Commonwealth Government has given its own agencies when confronted with this kind of economic analysis.
Ask the following questions:
- What questions does the study attempt to answer?
- What alternative strategies are considered?
- Do you have any comments on the way the choices could have been set out?
- Are there other choices that could/should have been considered at the same time?
- Are you happy with the cost estimates made?
- Are the methods of evaluation satisfactory?
- Are any relevant costs omitted?
- Is the study based on reliable evidence?
- What further information would you require?
- Is such information available and, if so, where and from whom?
- Are you happy with the methods of benefit measurement employed in the study?
- If not, what method or approach would you propose?
- If yes, are you content with the values derived?
- Does the study allow for:
- Uncertainty (or errors) in the expected costs and benefits?
- The differential timing of costs and benefits?
- Finally, assuming you were advising the decision makers, what would be your recommendation?
Any analyst should have no problems or hesitancy answering these. If they do, the report probably needs more work.
The absence of a publicly available cost benefit analysis for the proposed Bus and Train (BAT) Tunnel project in Brisbane raises a couple of obvious questions. The first is the simplest.
The previous Cross River Rail (CRR) proposal was expected to cost around $6.4 billion to construct. At this stage the BAT Tunnel is expected to cost around $5 billion. Queenslanders save $1.4 billion right?
Financially they do. But without a full CBA we cannot know what benefits are being left on the table. If more than $1.4 billion in benefits under CRR are not realised in the BAT Tunnel we are actually reducing the net economic benefit of getting a decent public transport solution.
How would we know?