Messages

1

HUGIN GUI Discussion / HUGIN EXPERT 8.5 - Export Beliefs issue

« on: January 26, 2024, 15:33:11  »

As a happy user of a rather old 8.5 version, I found that GUI command Export Beliefs visualizes and also exports to .csv file nodes belief data rounded to 0 if figure is bellow about 0.001 % (1e-5) and rounds to 1 of above about 0.99999. That is problem for my models (low probability events) if exporting final results and do a post processing. Is this a bug, or? Any workaround?
Was that solved in later versions?

2

General Discussion / Re: Discrete Boolean nodes with beliefs as data distributions?

« on: March 01, 2015, 18:41:40  »

Specifically, the boolean's variable true wold be represented by a log-normal distribution, e.g., using mean and error-factor (=sqrt of 95 and 5 percentiles quotient), or other "input" data.

3

General Discussion / Re: Discrete Boolean nodes with beliefs as data distributions?

« on: February 09, 2015, 14:51:30  »

The point is simple.
Instead of using point values for Boolean type of variables, I would like to use distributions, where normal or log-normal are of practical interest.
That would add information on the confidence intervals for states od interest. This is usually practiced in engineering risk assessments, like using methods of fault tree and event tree analysis. Needless to say, we are mainly interested in failures becoming realized = true.

4

General Discussion / Discrete Boolean nodes with beliefs as data distributions?

« on: January 05, 2015, 17:04:32  »

As a novice Hugin user and oriented to risk modelling applications, I am interested in using Boolean variables/nodes, however, the point values specified for parents for true and false states seem dull. Is it possible somehow to use "simple" distribution data (e.g, log-normal) for true state(s) and rest to 1 is set to false state?
Had read the Expressions chapter in Manual, and Distrubution () function as permitted for Boolean nodes is not clear enough for me.