***** To join INSNA, visit http://www.insna.org *****
I would like to compare the densities of two networks (valued graphs) of the relations on the same set of nodes. However, graph 2 is based on more absolute observations and consequently the absolute values of the relationships between nodes (representing the 'strength' of relations) are different.
I would appreciate any thoughts and any pointers to literature that could help me understand how/if it is possible to handle density comparisons among valued graphs that contain the same nodes and the same relations but the 'strength' of the relation is confounded by different quantities of data the networks are based upon.
I was thinking to normalize the matrices and hence to control for the differences in graph values and hence relationship magnitudes due to the higher numbers of observations in network 2,which should allow me to compare the densities of the normalized valued graphs.
Any thoughts would be much appreciated.
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.