UC Santa Barbara

Network analysts are increasingly being called upon to apply their expertise to groups for which the only available or reliable data is a contact network. With no opportunity to gather additional data, the merits of such applications depend on empirical studies that validate the employment of structural constructs based on contact networks. Fortunately, we possess such studies in abundance. One of the strongest research traditions in social network analysis is the development of formal constructs that may be employed in analyses of networks. I suggest that greater insight into predictive success of network constructs may be acquired by addressing the following question: what features of the contact network in which a dyad is situated allow the prediction of other relations with an accuracy that validates the imputation of the latter given data on the former? In this article, I present findings on the structural contexts of dyads in contact networks and the relationship of these contexts with two fundamental forms of cohesive cognitive relations-accorded interpersonal influence and perceived interpersonal agreement. Based on these findings, I formalize a measure of structural proximity in contact networks with values that correspond to the conditional probabilities of these two forms of cohesive cognitive relations. The substantive settings of this analysis are policy groups with members who are embedded in contact structures based on regular interpersonal communication on policy issues and cognitive structures based on perceived interpersonal agreement and accorded interpersonal influence. © 2008 Elsevier B.V. All rights reserved.