Hi!
I populated the CPTs of my Bayesian decision network with judgment elicited from the experts. I used 3 experts for each node. Now I would like to study the variability of the output (the value nodes) arising from changes in the CPTs, according to the positions of the different experts (e.g.: different runs. In each run I randomly chose for each node the judgment expressed by an expert, eg. node 1 = expert 2, node 2 = expert 3 etc).
Is it possible to introduce in the Genie sw this kind of Monte-Carlo simulation, obtaining a spreadsheet with the results of the different runs?
thank you very much!!!
Monte-Carlo
-
shooltz[BayesFusion]
- Site Admin
- Posts: 1417
- Joined: Mon Nov 26, 2007 5:51 pm
Re: Monte-Carlo
We don't plan to implement such feature at the moment. We usually encourage users to write some code using core SMILE or one of the wrappers to perform user-specific tasks.mic wrote:Is it possible to introduce in the Genie sw this kind of Monte-Carlo simulation, obtaining a spreadsheet with the results of the different runs?