Expressions is the key building block of Models and can be used to simplify the specification of conditional probability tables for discrete chance nodes, utility tables for utility nodes, and initial policies for decision nodes. This is particularly useful when the conditional probability distribution for a variable follows (at least approximately) certain functional or distributional forms. In such cases it is cumbersome to specify the conditional probability table manually.
An expression is built using standard statistical distributions (e.g., Normal, Binomial, Beta, Gamma, etc.), arithmetic operators, standard mathematical functions (e.g., logarithmic, exponential, trigonometric, and hyperbolic functions), logical operators (e.g., and, or, if-then-else), and relations (e.g., less-than, equals).
Expressions can be constructed manually or by the assistance of the Expression Builder, which guides the user through the construction, using series of dialog boxes. See the Table Generator Tutorial for more information about expressions.