BNET Procedure

The network shown in Figure 1 does not include the variable Sex or Duration, because PROC BNET automatically removes these variables from the network by using independence tests. PROC BNET produces the table in Figure 3, which shows the results of independence tests that are conducted to select variables. Variables that are found to be marginally independent or conditionally independent of the target variable are removed from the network. PROC BNET removes Duration from the network because the p-value of the chi-square and G-square statistics of Duration are greater than 0.05 (the default value of the ALPHA= option). Sex is conditionally independent of Pain given Treatment; therefore, PROC BNET removes Sex from the network.