Bayesian Network Model Nuggets

Note: If you select Continue training existing parameters on the modeling node Model tab, the information that is shown on the model nugget Model tab is updated each time that you regenerate the model.

The model nugget Model tab is split into two panes.

Left Pane

Basic This view contains a network graph of nodes that displays the relationship between the target and its most important predictors, and the relationship between the predictors. The importance of each predictor is shown by the density of its color; a strong color shows an important predictor, and vice versa.

The bin values for nodes that represent a range are displayed in a tooltip when you hover the mouse pointer over the node.

You can use the graph tools in IBM® SPSS® Modeler to interact, edit, and save the graph. For example, for use in other applications such as MS Word.

Tip: If the network contains many nodes, you can click to select a node and drag it to make the graph more legible.

Distribution This view displays the conditional probabilities for each node in the network as a mini graph. Hover the mouse pointer over a graph to display its values in a tooltip.

Right Pane

Predictor Importance This displays a chart that indicates the relative importance of each predictor in estimating the model. For more information, see Predictor Importance.

Conditional Probabilities When you select a node or mini distribution graph in the left pane the associated conditional probabilities table is displayed in the right pane. This table contains the conditional probability value for each node value and each combination of values in its parent nodes. In addition, it includes the number of records that are observed for each record value and each combination of values in the parent nodes.