Jorge: My question is about knowledge engineering (eliciting probability models from a domain expert's knowledge or mental model ) rather than data mining (extracting a probabilistic model from data).
Bob. ----- Original Message ----- From: "Jorge Moraleda" <[EMAIL PROTECTED]> To: "Bob Welch" <[EMAIL PROTECTED]> Sent: Saturday, July 06, 2002 1:21 PM Subject: Re: [UAI] human comprehension of bayesian networks > Bob, > > I am aware of several such tools. I recommend in particular BN5 by Data > Digest (www.data-digest.com) which does a very fine job of learning > Probabilistic Models form data. > > Regards, > > Jorge > > On Fri, 5 Jul 2002, Bob Welch wrote: > > > To UAI List members -- > > > > I would be interested in knowing what software GUI tools are available for > > probability assessment, either commercial or academic products. Such tools > > would be designed to avoid or test for the well known biases that have been > > documented by Kahneman D. Slovic P. & Tversky A.(eds). Judgement under > > Uncertainty: Heuristics and Biases. Cambridge University Press, (1982) and > > othere writers. Examples of these biases are: > > > > Representativeness: > > Base-rate neglect > > Insensitivity to prior probability of outcomes > > Insensitivity to sample size > > Misperception of chance and randomness > > > > Denial of uncertainty > > Availability > > Adjustment and Anchoring > > Conjunction fallacy > > Hindsight bias > > Difficulties in assessing variance, covariance and correlation > > Conservatism > > Overconfidence > > Fallacies associated with causal and diagnostic reasoning > > > > Thanks in advance. > > > > Bob Welch. > > >
