- #1

Moose Winooski

- 2

- 0

- TL;DR Summary
- How to figure out the probability of multiple outcomes from a single event

Hello all!

I hope I have come to the right place, and I appreciate any help! My first disclaimer is that I am not a math professional of any sort, I am not bad at it but I just wanted to start with that so if I ask a stupid question, it's because I am ignorant mostly. What I work in is risk management, specifically health and safety.

My problem is this, I don't like and have never really felt comfortable with communicating risk from a 2-dimensional point of view (e.g. likelihood is between 1-2 years, and the consequence is a permanent disability). For those that are familiar with risk, your typical 5x5 heat map.

My issue with this is a "Risk Event" can have a range of possible outcomes. If you think of a car accident, the outcomes can range from minor bumps and bruises to death... and I would like to, in a visual way, represent the probability of many outcomes. (e.g. Bumps and bruises 22% chance, Hospitalisation 48% chance, Permanent disability 20%, Death 10%).

To add to my problem in many cases I probably won't have good external or internal data to already represent this... but I may have multiple "Risk Inputs" so if I go back to my car accident example there would be the inputs of speed, weather, road conditions, driver experience etc... that I could use as "dials" to shift the probability of the outcomes. I also assume that I would have to "weight" these inputs and that would add some subjectivity but I don't think I could be any more accurate?

So in a nutshell, is there a way I can visualise a Risk Event that shows a bunch of grouped outcomes and their probabilities while also having the ability to highlight that "if we increase the speed" then it shifts the numbers?

Cheers, M

I hope I have come to the right place, and I appreciate any help! My first disclaimer is that I am not a math professional of any sort, I am not bad at it but I just wanted to start with that so if I ask a stupid question, it's because I am ignorant mostly. What I work in is risk management, specifically health and safety.

My problem is this, I don't like and have never really felt comfortable with communicating risk from a 2-dimensional point of view (e.g. likelihood is between 1-2 years, and the consequence is a permanent disability). For those that are familiar with risk, your typical 5x5 heat map.

My issue with this is a "Risk Event" can have a range of possible outcomes. If you think of a car accident, the outcomes can range from minor bumps and bruises to death... and I would like to, in a visual way, represent the probability of many outcomes. (e.g. Bumps and bruises 22% chance, Hospitalisation 48% chance, Permanent disability 20%, Death 10%).

To add to my problem in many cases I probably won't have good external or internal data to already represent this... but I may have multiple "Risk Inputs" so if I go back to my car accident example there would be the inputs of speed, weather, road conditions, driver experience etc... that I could use as "dials" to shift the probability of the outcomes. I also assume that I would have to "weight" these inputs and that would add some subjectivity but I don't think I could be any more accurate?

So in a nutshell, is there a way I can visualise a Risk Event that shows a bunch of grouped outcomes and their probabilities while also having the ability to highlight that "if we increase the speed" then it shifts the numbers?

Cheers, M