Influence Diagram

[Salim]

Hello I am working on a Risk assessment with influence diagram.
The scenario is, the decision node contains all risk factors and is acting as a parent node.
The decision node then connect to other child nodes.however some risks effect 1 child node, not all the risks.
In this case how to give probabilities for the risks which won't be effected in the specific child node. I tried giving equal probabilities to the non effective ones but then the result converges to medium only.
Kindly advise

[Salim]

In other words, how can we put a node between decision node and child node to work as filter node? To prevent some data from coming to the child node

[marek [BayesFusion]]

Hi Salim,

I will be happy to help you but need to understand better what you want. Would you be willing to create and post the simplest possible influence diagram that does what you want? In general, uniform probabilities do not sound like a good idea in this case. I would keep the probabilities that the nodes would have without the decision node as parent and then just duplicate these distributions, i.e., indicate that the decision does not matter for those nodes. Please do keep in mind that I may have misunderstood what you want and posting a simple ID will help me to be more precise.
Cheers,

Marek

[Salim]

I have attached a simple case for your refrence. the problem i am facing in equal probabilities for the ineffective states of Decision node in the child nodes is that as model propagates the decision node results converges to mostly medium.
I also thought of putting a filter node (noisy or) inbetween the two to limit the unnessary states of the parent node but not successful yet.

Thanks alot of your support

[marek [BayesFusion]]

Hi Salim,

The screen shots are not originating from GeNIe and are confusing. My original advice is still standing. You should change the uniform probabilities into the probability distributions that will be there when the node Risks has no effect on the children nodes.
Cheers,

Marek