Introduction
Quantitative risk assessment is one approach to measuring risk. It involves measuring both consequences and likelihoods using numerical scales. These can be expressed as ranges or distributions.
Alternative measurement approaches are qualitative and semi-quantitative risk assessment.
Examples
Quantitative risk assessment techniques need to be carried out using the appropriate units for the risk being measured. For example, the expected frequency of car accidents per thousand kilometres travelled by a driver.
Other examples include the mean time to failure of a piece of equipment, expected values of financial returns over a financial year, or cost of repairs per thousand duty cycles.
The consequence of risks can also be expressed as a probability distribution, for example, the variance of returns on a financial investment. Another quantitative measure is calculating the value which has a certain probability of occurring for a particular risk. For example, the number of litres which have a 50 per cent chance of leaking out of a particular water pipe over a year.
Quantitative methods can also express consequence-based measures such as the probable maximum loss from an investment. These are usually used when there is not enough data to estimate likelihood, or there is uncertainty over which project controls will fail.
Risk aggregation
Quantitative risk assessment can be used to aggregate values for a group of like risks into a single value as long as they share a single consequence and common units, such as Australian dollars or failures per hour.
However, this reduces the amount of data available about each individual risk, which may cause problems in complex systems.
Correlations between probability distributions also need to be taken into account to avoid misleading results. For a reliable result, tools such as Monte Carlo simulation should be used to combine distributions.
Sources:
The content on this page was primarily sourced from:
- IEC 31010:2019 Risk Management – Risk Assessment Techniques (6.3.5.4)
Edited by Nadine Cranenburgh
Recommended Comments
There are no comments to display.
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.