Social selection models for multilevel networks

Abstract

a b s t r a c tSocial selection models (SSMs) incorporate nodal attributes as explanatory covariates for modelling network ties (Robins et al., 2001). The underlying assumption is that the social processes represented by the graph configurations without attributes are not homogenous, and the network heterogeneity maybe captured by nodal level exogenous covariates. In this article, we propose SSMs for multilevel networks as extensions to exponential random graph models (ERGMs) for multilevel networks . We categorize the proposed model configurations by their similarities in interpretations arising from complex dependencies among ties within and across levels as well as the different types of nodal attributes. The features of the proposed models are illustrated using a network data set collected among French elite cancer researchers and their affiliated laboratories with attribute information about both researchers and laboratories (Lazega et al., 2006(Lazega et al., , 2008. Comparisons between the models with and without nodal attributes highlight the importance of attribute effects across levels, where the attributes of nodes at one level affect the network structure at the other level.

Organizational learning across multi-level networks

“…We provide empirical evidence on this claim specifying and estimating newly developed Multilevel Exponential Random Graph Models (MERGMs -Wang et al, 2013, 2015. They represent a significant improvement on previous multilevel methods that are unable to analyze hierarchical systems of nested relations in depth.…”

“…The diverse experiences of network partners draw attention to existing information (Fiske and Taylor, 1984) and provide individuals and organizations with a variety of normative, instrumental and procedural information for better causal inference on the possible consequences of specific actions (Beckman and Haunschild, 2002). Hence, a higher level of network heterogeneity (Reagans and McEvily, 2003;Williams and O'Reilly, 1998) increases individual creativity and innovativeness (Burt, 2004) as well as organizational productivity (Beckman et al, 2004) and competitiveness (Argote and Ingram, 2000).…”

A Social Network Analysis on the Culture of Helping in Health Institutions

“…This may be related to the hierarchical structure of the institutions. In terms of comparison with the social network structure, Wang et al, (2016) found an arc of −3754 and reciprocity of 1.719 in the network of laboratory cooperative research involving 82 laboratories and 97 researchers. In our research, these rates were low in terms of reciprocal linkages.…”

Social Capital Inequalities among Postgraduate Students and Social Selection Processes

“…The SSM was proposed by [Robins et al 2001] with the goal of accounting for heterogeneity within the social structures using nodal attributes as exogenous covariates. So, in addition to modelling endogenous variables, i.e., network configurations that explain self-organizing processes, the SSM accounts for exogenous variables that also have an effect of structure emergence [Wang et al 2016]. Beyond that, I also analyze the effect of dyadic covariates, i.e., the effect of the existence of an i-j tie in another relation network on the existence of an i-j tie in the modelled network [Robins and Daraganova 2013].…”