Asia: expert system

Evidence propagation

Lauritzen and Spiegelhalter (1988) introduce a fictitious "expert system" representing the diagnosis of a patient presenting to a chest clinic, having just come back from a trip to Asia and showing dyspnoea (shortness-of-breath). The BUGS code is shown below and the conditional probabilities used are given in Lauritzen and Spiegelhalter (1988). Note the use of max to do the logical-or. The dcat distribution is used to sample values with domain (1,2) with probability distribution given by the relevant entries in the conditional probability
tables.


    model
    {
       smoking ~ dcat(p.smoking[1:2])
       tuberculosis ~ dcat(p.tuberculosis[asia,1:2])
       lung.cancer ~ dcat(p.lung.cancer[smoking,1:2])
       bronchitis ~ dcat(p.bronchitis[smoking,1:2])
       either <- max(tuberculosis,lung.cancer)
       xray ~ dcat(p.xray[either,1:2])
       dyspnoea ~ dcat(p.dyspnoea[either,bronchitis,1:2])
    }


Data ( click to open )

Inits for chain 1        Inits for chain 2    ( click to open )

Results