## Quantitative risk management

**Quantitative risk management **

Risk management can be summarised as knowing and controlling the probability and effect of threats to quality and costs. Quantitative risk management is calculating with probabilities and effects, taking variability and uncertainty into account. It is common in many industries: aviation, spaceflight, (petro)chemical, finance and the nuclear industry. To many people, quantitative risk management seems to be only for ‘rocket scientists’ and ‘whiz kids’. However, the methods are successfully applied in an increasing number of industries and disciplines. With some training and affordable software the base techniques are easier, more effective and more efficient than ever.

**What are the benefits?**

· A quantitative estimate of risks, including variability of risk.

· Best-case and worst-case scenarios, with a more realistic estimate of their probabilities.

· A quantitative relation between factors that determine quality.

· Objective, quantitatively supported priorities:

o Where will control measures be most effective?

o Is there a need for more data (research) and if so, where would this be most effective?

· Interaction of disciplines controlling processes, resulting in an even better cooperation!

**How to achieve this? I can explain this to you in a (web/phone) meeting or teach you this during a training:**

1. Start simple. Make an outline flow chart of the process and indicate relations.

2. With specialists of disciplines concerned, translate relations into (simple) quantitative formulas.

3. Describe the known or estimated variation of process variables (probability distributions).

4. Calculate the formulas in Excel. With a dedicated add-in you can calculate with the entire variation, not just with one fixed value, such as the mean, minimum or maximum value.

5. Let the add-in calculate automatically what variables have the most effect on the process. These variables receive objective priority for:

a. Control measures, when the uncertainty about the values of that variable is acceptable.

b. Collecting (better) data and knowledge, when the uncertainty is too large. Optimise the formulas (step 2) and/or the values of the variables (step 3) and calculate again (step 4).

6. When changing the process: calculate the effect of this change, preferably before the change.