NETWORK Procedure

SUMMARY Statement

SUMMARY < options >;

The SUMMARY statement invokes an algorithm that calculates various summary metrics for an input graph. For more information about summary metrics, see the section Summary Statistics.

You can specify the following options:

ASSORTATIVITYDEGREE=WEIGHT | UNWEIGHT | BOTH

calculates degree assortativity and specifies which type of calculation to perform. You can specify the following values:

WEIGHT: calculates degree assortativity by using the weighted graph.
UNWEIGHT: calculates degree assortativity by using the unweighted graph.
BOTH: calculates degree assortativity by using both the weighted and unweighted graphs.

If the input graph does not contain link weights, then ASSORTATIVITYDEGREE=WEIGHT and ASSORTATIVITYDEGREE=UNWEIGHT produce the same results.

ASSORTATIVITYNOMINAL=column

specifies the name of the data variable for computing the nominal assortativity. The variable can be numeric or character.

ASSORTATIVITYNUMERIC=column

specifies the name of the data variable for computing the numeric assortativity. The variable must be numeric.

BICONNECTEDCOMPONENTS

calculates information about biconnected components. You can use this option only for an undirected graph.

CLUSTERINGCOEFFICIENT CLUSTERINGCOEF

calculates information about clustering coefficients. You can use this option only for an undirected graph.

CONNECTEDCOMPONENTS

calculates information about connected components.

DIAMETERAPPROX=WEIGHT | UNWEIGHT | BOTH

calculates information about the approximate diameter and specifies which type of calculation to perform. Use this option when calculating the exact diameter (by calculating all shortest paths) is too computationally expensive. You can specify the following values:

WEIGHT: calculates the approximate diameter by using the weighted graph.
UNWEIGHT: calculates the approximate diameter by using the unweighted graph.
BOTH: calculates the approximate diameter by using both the weighted and unweighted graphs.

If the input graph does not contain link weights, then DIAMETERAPPROX=WEIGHT and DIAMETERAPPROX=UNWEIGHT produce the same results. This option works only for undirected graphs.

FINITEPATH

includes only finite values when calculating descriptive statistics that are related to shortest paths (eccentricity, diameter, and so on).

OUT=libref.data-table

specifies the output data table to contain the summary results. libref.data-table is a two-level name, where libref refers to the library, and data-table specifies the name of the output data table. For more information about this two-level name, see the section Using CAS Sessions and CAS Engine Librefs in Chapter 1, Introduction.

SHORTESTPATH=WEIGHT | UNWEIGHT | BOTH

calculates information about shortest paths and specifies which type of calculation to perform. You can specify the following values:

WEIGHT: calculates shortest paths by using the weighted graph.
UNWEIGHT: calculates shortest paths by using the unweighted graph.
BOTH: calculates shortest paths by using both the weighted and unweighted graphs.

If the input graph does not contain link weights, then SHORTESTPATH=WEIGHT and SHORTESTPATH=UNWEIGHT produce the same results.

Last updated: August 07, 2026