Stochastic Actor-oriented Models Research Articles

Stochastic actor-oriented modeling for studying homophily and social influence in OSS projects

Open Source Software projects are communities in which people "learn the ropes" from each other. The social and technical activities of developers evolve together, and as they link to each other th...

Understanding Dynamics of Information Transmission in Drosophila melanogaster Using a Statistical Modeling Framework for Longitudinal Network Data (the RSiena Package).

Social learning – the transmission of behaviors through observation or interaction with conspecifics – can be viewed as a decision-making process driven by interactions among individuals. Animal group structures change over time and interactions among individuals occur in particular orders that may be repeated following specific patterns, change in their nature, or disappear completely. Here we used a stochastic actor-oriented model built using the RSiena package in R to estimate individual behaviors and their changes through time, by analyzing the dynamic of the interaction network of the fruit fly Drosophila melanogaster during social learning experiments. In particular, we re-analyzed an experimental dataset where uninformed flies, left free to interact with informed ones, acquired and later used information about oviposition site choice obtained by social interactions. We estimated the degree to which the uninformed flies had successfully acquired the information carried by informed individuals using the proportion of eggs laid by uninformed flies on the medium their conspecifics had been trained to favor. Regardless of the degree of information acquisition measured in uninformed individuals, they always received and started interactions more frequently than informed ones did. However, information was efficiently transmitted (i.e., uninformed flies predominantly laid eggs on the same medium informed ones had learn to prefer) only when the difference in contacts sent between the two fly types was small. Interestingly, we found that the degree of reciprocation, the tendency of individuals to form mutual connections between each other, strongly affected oviposition site choice in uninformed flies. This work highlights the great potential of RSiena and its utility in the studies of interaction networks among non-human animals.

The evolution of global trade and impacts on countries’ carbon trade imbalances

We examine carbon trade imbalances among 172 countries over a 10-year period (2000–2010). A carbon trade imbalance refers to the extent to which the carbon emissions embodied in a country's exports exceeds the emissions embodied in its imports. Although past research has considered how such imbalances coincide with variances in wealth and/or trade patterns, none have considered how such imbalances arise in the context of an evolving network structure. In this paper, we consider trade networks and carbon trade imbalances as co-evolving phenomena, and study these using an innovative combination of multi-regional input–output (MRIO) analysis with stochastic actor-oriented models (SAOMs). Our findings both challenge and support arguments made by ecological unequal exchange theory and the Gravity Model, and highlight the role emerging economies play in shaping network structure and the distribution of carbon trade balances overtime.

Competition for foundation patronage and the differential effects of prestige on the grant market success of social movement organisations

Extant models of the financial patronage of Social Movement Organisations (SMOs) by private foundations exclusively use population density to account for competition. However, density fails to reveal how SMOs win grants whilst neglecting the strategic decision-making of foundation-investors. Here I recast patronage as a mutualistic network represented by a dynamic bipartite graph wherein SMOs and foundations cooperate across class whilst SMOs compete within class for financial support. A SMO's competitiveness rests with its position in a network-based prestige hierarchy and a foundation's propensity to invest is mediated by its structural position within the grant market. While previous research has predicted a positive monotonic relationship between status and patronage, using Stochastic Actor-Oriented Models I find a tendency for status-based disassortativity in the mutualistic system such that high-status foundations prefer to invest in low-status SMOs. I attribute this counterintuitive finding to foundations’ preferences for grantees that can innovate around social problems. Relative to their peripheral counterparts, well-funded SMOs may suffer a rigidity of goals due to the risk of alienating an existing support-base through organisational change. Data consist of 3261 grants given from 2003 to 2007 by 136 private foundations to 66 professional SMOs with nonprofit status loosely mobilised against the notion of anthropogenic climate change.

Energy and resilience: The effects of endogenous interdependencies on trade network formation across space among major Japanese firms

AbstractThe dynamic drivers of interfirm interactions across space have rarely been explored in the context of disaster recovery; therefore, the mechanism through which shocks propagate is unclear. This paper uses stochastic actor-oriented modeling to examine how trade networks among the 500 largest Japanese companies evolved during 2010 and 2011, i.e. before and after the Great East Japan Earthquake to identify sources of vulnerability in the system. In contrast to previous reports on broken supply chains, the network displayed only modest change even in the directly affected areas. Controlling for distance and for firm size, we find that when firms changed their partners, they preferred firms that were popular among other firms, that had partners in common with them and that also bought some products or services from them. These findings concur with a criticism that Japanese firms avoid external actors and exhibit inflexibility in reorganizing their networks in times of need, which contrasts with the non-cliquish network structures observed in high-performing economic sectors. The results also highlight the role of energy firms in disaster resilience. Unlike other large Japanese companies that cluster in major urban centers, energy firms are distributed across Japan. However, despite their peripheral physical locations, energy firms are centrally located in trade networks. Thus, while a disaster in any region may affect some energy firms and lead to large-scale temporary shocks, the entire network is unlikely to be disconnected by any region-specific disaster because of the spatial distribution of the topological network core formed by energy companies.

Does Price Competition Drive Cooperation in Health Care? A Stochastic Actor Oriented Model Analysis

Pro-competitive reforms have been enacted throughout Western healthcare systems despite mixed evidence of their effect. Although healthcare organizations competing under non-price competition have been shown to cooperate using patient transfers, little is known about cooperative strategies of healthcare organizations in price-competitive healthcare markets. This paper investigates a novel and understudied form of inter-hospital cooperation described as potentially hazardous to well-functioning healthcare markets, namely the act of sharing medical specialists between hospitals. In particular, it investigates the influence of price-competition on cooperative hospital strategies. We use a stochastic actor-oriented model to analyze the cooperative dynamics amongst 94 general and academic hospitals in the Netherlands between 2010 and 2015. Our results show that, in a price-competitive healthcare sector, hospitals predominantly cooperate with their direct competitors. However, the ratio of price-competitive to ...

The evolution of social networks through the implementation of evidence-informed decision-making interventions: a longitudinal analysis of three public health units in Canada.

BackgroundWe studied the evolution of information-seeking networks over a 2-year period during which an organization-wide intervention was implemented to promote evidence-informed decision-making (EIDM) in three public health units in Ontario, Canada. We tested whether engagement of staff in the intervention and their EIDM behavior were associated with being chosen as information source and how the trend of inter-divisional communications and the dominance of experts evolved over time.MethodsLocal managers at each health unit selected a group of staff to get engage in Knowledge Broker-led workshops and development of evidence summaries to address local public health problems. The staff were invited to answer three online surveys (at baseline and two annual follow-ups) including name generator questions eliciting the list of the staff they would turn to for help integrating research evidence into practice. We used stochastic actor-oriented modeling to study the evolution of networks. We tested the effect of engagement in the intervention, EIDM behavior scores, organizational divisions, and structural dynamics of social networks on the tendency of staff to select information sources, and the change in its trend between year 1 and year 2 of follow-up.ResultsIn all the three health units, and especially in the two units with higher levels of engagement in the intervention, the network evolved towards a more centralized structure, with an increasing significance of already central staff. The staff showed greater tendencies to seek information from peers with higher EIDM behavior scores. In the public health unit that had highest engagement and stronger leadership support, the engaged staff became more central. In all public health units, the engaged staff showed an increasing tendency towards forming clusters. The staff in the three public health units showed a tendency towards limiting their connections within their divisions.ConclusionsThe longitudinal analysis provided us with a means to study the microstructural changes in public health units, clues to the sustainability of the implementation. The hierarchical transformation of networks towards experts and formation of clusters among staff who were engaged in the intervention show how implementing organizational interventions to promote EIDM may affect the knowledge flow and distribution in health care communities, which may lead to unanticipated consequences.Electronic supplementary materialThe online version of this article (doi:10.1186/s13012-015-0355-5) contains supplementary material, which is available to authorized users.

A Multilevel Network Study of the Effects of Delinquent Behavior on Friendship Evolution

A multilevel approach is proposed to the study of the evolution of multiple networks. In this approach, the basic evolution process is assumed to be the same, while parameter values may differ between different networks. For the network evolution process, stochastic actor-oriented models are used, of which the parameters are estimated by Markov chain Monte Carlo methods. This is applied to the study of effects of delinquent behavior on friendship formation, a question of long standing in criminology. The evolution of friendship is studied empirically in 19 school classes. It is concluded that there is evidence for an effect of similarity in delinquent behavior on friendship evolution. Similarity of the degree of delinquent behavior has a positive effect on tie formation but also on tie dissolution. The last result seems to contradict current criminological theories, and deserves further study.

Disentangling the relation between young immigrants’ host country identification and their friendships with natives

Immigrants who strongly identify with the host country have more native friends than immigrants with weaker host country identification. However, the mechanisms underlying this correlation are not well understood. Immigrants with strong host country identification might have stronger preferences for native friends, or they might be more often chosen as friends by natives. In turn, having native friends or friends with strong host country identification might increase immigrants’ host country identification. Using longitudinal network data of 18 Dutch school classes, we test these hypotheses with stochastic actor-oriented models. We find that immigrants’ host country identification affects friendship selections of natives but not of immigrants. We find no evidence of social influence processes.

Assimilation and differentiation: A multilevel perspective on organizational and network change

This paper builds on recently derived stochastic actor-oriented models (SAOMs) for the coevolution of one-mode and two-mode networks, and extends them to the analysis of how concurrent multilevel processes of (internal) organizational and (external) network change affect one another over time. New effects are presented that afford specification and identification of two apparently conflicting micro-relational mechanisms that jointly affect decisions to modify the portfolio of internal organizational activities. The first mechanism, assimilation, makes network partners more similar by facilitating the replication and diffusion of experience. The second mechanism, functional differentiation, operates to maintain and amplify differences between network partners by preventing or limiting internal organizational change. We illustrate the empirical value of the model in the context of data that we have collected on a regional community of hospital organizations connected by collaborative patient transfer relations observed over a period of seven years. We find that processes of social influence conveyed by network ties may lead both to similarity and differences among connected organizations. We discuss the implications of the results in the context of current research on interorganizational networks.

Ethnic segregation of friendship networks in school: Testing a rational-choice argument of differences in ethnic homophily between classroom- and grade-level networks

Adolescents’ school-based friendship networks tend to be segregated along ethnic lines. But few studies have examined whether variation in network boundaries affects the degree of ethnic friendship segregation. We use rational-choice theory to argue that ethnic homophily is more pronounced for friendships between classrooms than for those within classrooms. We empirically test this hypothesis using two-wave German panel data (N=1258) and stochastic actor-oriented models (RSiena). In line with our theoretical argument, we find that the tendency to form same-ethnic friendships is indeed stronger at the grade level, which translates into stronger ethnic segregation in friendship networks at the grade level than at the classroom level. Implications for research on ethnic segregation in school-based friendship networks are discussed.

Statistical Models for Analysis of Social Network Dynamics in Educational Studies

Research on co-evolution of networks and behavior became possible with the emergence of student performance and behavior dynamic data collection and storage tools, as well as with the development of new social network analysis methods. Dynamic network analysis answers the question, how specific forms of student behavior, like bad habits, develop and propagate. It is also helpful in following how school or university students enter into friendship or antagonism with each other, as well as in assessing the impact social relations have on academic performance. The paper gives a review of the two key methods used for empirical analysis of social network dynamics. Stochastic Actor-Oriented Models (SAOM) represent one of the most elaborated techniques of social network dynamics investigation. This approach regards the present state of a network as dependable on its preceding state uniquely. Network evolution appears to be continuous, not discrete, so that a structural macro change is, in fact, a multitude of micro changes. Instead of dealing with structure of the network and prerequisites for its development, the SAOM model studies the processes underlying any changes recorded. Separable Temporal Exponential Random Graph Models (STERGM) are an alternative approach towards research on social network dynamics. In this case, the social network observed is a materialization of one of possible networks with predetermined characteristics. Any network develops in the result of a stochastic process, and the research should be aimed at discovering what forces this process is driven by. Comparison of an empirically discovered network with networks of similar size reveals structural features of the network and characteristics of actors who influenced the process of its establishment. In this paper, we also give an example of how both models can be used with the same set of data.

Influence Versus Selection: A Network Perspective on Opinion Leadership

Over the past decades, research on opinion leaders has been based on an implicit assumption that the structure of social networks is stable and that only attitudes and behavior are subject to change in a diffusion process. The finding that social groups often display similar attitudes or behavior was therefore regarded as evidence of opinion leaders’ influence. However, network autocorrelation also can emerge due to social selection processes in which likeminded people establish new ties and cut dissonant ties. In fact, without controlling for social selection processes, one is likely to overestimate the power of influence processes. Stochastic actor-oriented modeling of dynamic social networks allows disentangling and quantifying these two processes. This reanalysis of a four-wave panel survey of adolescents’ conversation networks and their TV use is the first to do this on the level of specific TV programs. The results demonstrate that influence of opinion leaders may become insignificant if parameters for social selection and general patterns of program preferences are included in the analysis. Overall, this study challenges an overly simplistic view of opinion leadership and illustrates the power of longitudinal social network analysis for disentangling social influence and social selection processes.

Building Service Delivery Networks: Partnership Evolution Among Children's Behavioral Health Agencies in Response to New Funding.

Meeting the complex needs of youth with behavioral health problems requires a coordinated network of community-based agencies. Although fiscal scarcity or retrenchment can limit coordinated services, munificence can stimulate service delivery partnerships as agencies expand programs, hire staff, and spend more time coordinating services. This study examines the 2-year evolution of referral and staff expertise sharing networks in response to substantial new funding for services within a regional network of children's mental health organizations. Quantitative network survey data were collected from directors of 22 nonprofit organizations that receive funding from a county government-based behavioral health service fund. Both referral and staff expertise sharing networks changed over time, but results of a stochastic actor-oriented model of network dynamics suggest the nature of this change varies for these networks. Agencies with higher numbers of referral and staff expertise sharing partners tend to maintain these ties and/or develop new relationships over the 2 years. Agencies tend to refer to agencies they trust, but trust was not associated with staff expertise sharing ties. However, agencies maintain or form staff expertise sharing ties with referral partners, or with organizations that provide similar services. In addition, agencies tend to reciprocate staff expertise sharing, but not referrals. Findings suggest that during periods of resource munificence and service expansion, behavioral health organizations build service delivery partnerships in complex ways that build upon prior collaborative history and coordinate services among similar types of providers. Referral partnerships can pave the way for future information sharing relationships.

Reciprocity, transitivity, and the mysterious three-cycle

Reciprocity and transitivity are the two most important structural mechanisms underlying friendship network evolution. While on their own they are understood in great detail, the relation between them is rarely studied systematically. Are friendships outside of social groups more or less likely to be reciprocated than friendships embedded in a group? Using a theoretical framework that focusses on the situations in which friends interact and the social structures that stabilise one-sided friendships, I propose that the tendency towards reciprocation of friendships within transitive groups is usually lower than outside of transitive groups. In a meta-analysis of two datasets including 29 friendship networks using stochastic actor-oriented models (SAOMs), the interaction between reciprocity and transitivity is analysed. Supporting the theoretical reasoning, the interaction is consistently negative. Second, the tendency against forming three-cycles in friendship networks, which was consistently found in previous studies, is shown to be spurious and a result of neglecting to control for the tendency against reciprocation in transitive groups. The tendency against three-cycles is commonly seen as an indicator that unreciprocated friendships indicate local hierarchy differences between individuals; this proposition has to be re-evaluated in light of the findings of this study. Future studies that analyse the evolution of friendship networks should consider modelling reciprocation in transitive triplets and potentially omit modelling three-cycles.

Gender, Friendship Networks, and Delinquency: A Dynamic Network Approach.

Researchers have examined selection and influence processes in shaping delinquency similarity among friends, but little is known about the role of gender in moderating these relationships. Our objective is to examine differences between adolescent boys and girls regarding delinquency-based selection and influence processes. Using longitudinal network data from adolescents attending two large schools in AddHealth (N = 1,857) and stochastic actor-oriented models, we evaluate whether girls are influenced to a greater degree by friends' violence or delinquency than boys (influence hypothesis) and whether girls are more likely to select friends based on violent or delinquent behavior than boys (selection hypothesis). The results indicate that girls are more likely than boys to be influenced by their friends' involvement in violence. Although a similar pattern emerges for nonviolent delinquency, the gender differences are not significant. Some evidence shows that boys are influenced toward increasing their violence or delinquency when exposed to more delinquent or violent friends but are immune to reducing their violence or delinquency when associating with less violent or delinquent friends. In terms of selection dynamics, although both boys and girls have a tendency to select friends based on friends' behavior, girls have a stronger tendency to do so, suggesting that among girls, friends' involvement in violence or delinquency is an especially decisive factor for determining friendship ties.

Social Networks and Social Settings: Developing a Coevolutionary View

One way to think about social context is as a sample of alters. To understand individual action, therefore, it matters greatly where these alters may be coming from, and how they are connected. According to one vision, connections among alters induce local dependencies—emergent rules of social interaction that generate endogenously the observed network structure of social settings. Social selection is the decision of interest in this perspective. According to a second vision, social settings are collections of social foci—physical or symbolic locales where actors meet. Because alters are more likely to be drawn from focused sets, shared social foci are frequently considered as the main generators of network ties, and hence of setting structure. Affiliation to social foci is the decision of central interest in this second view. In this paper we show how stochastic actor–oriented models (SAOMs) originally derived for studying the dynamics of multiple networks may be adopted to represent and examine these interconnected systems of decisions (selection and affiliation) within a unified analytical framework. We illustrate the empirical value of the model in the context of a longitudinal sample of adolescent participating in the Glasgow Teenage Friends and Lifestyle Study. Social selection decisions are examined in the context of networks of friendship relations. The analysis treats musical genres as the main social foci of interest.

Spread of Unethical Behavior in Organizations: A Dynamic Social Network Perspective

The spread of unethical behavior in organizations has mainly been studied in terms of processes occurring in a general social context, rather than in terms of actors’ reactions in the context of their specific social relationships. This paper introduces a dynamic social network analysis framework in which this spread is conceptualized as the result of the reactions of perpetrators, victims, and observers to an initial act of unethical behavior. This theoretical framework shows that the social relationships of the actors involved in an initial act impact in multiple ways the likelihood that unethical behavior spreads. It reveals furthermore that social relationships may change in the wake of unethical behavior, such that indirect negative consequences can arise for organizations. The proposed framework provides a basis for the development of a formal stochastic actor-oriented model of network dynamics which would enable simulations of the spread of unethical behavior.

Modeling knowledge networks in economic geography: a discussion of four methods

The importance of network structures for the transmission of knowledge and the diffusion of technological change has been recently emphasized in economic geography. Since network structures drive the innovative and economic performance of actors in regional contexts, it is crucial to explain how networks form and evolve over time and how they facilitate inter-organizational learning and knowledge transfer. The analysis of relational dependent variables, however, requires specific statistical procedures. In this paper, we discuss four different models that have been used in economic geography to explain the spatial context of network structures and their dynamics. First, we review gravity models and their recent extensions and modifications to deal with the specific characteristics of networked (individual level) relations. Second, we discuss the quadratic assignment procedure that has been developed in mathematical sociology for diminishing the bias induced by network dependencies. Third, we present exponential random graph models that not only allow dependence between observations, but also model such network dependencies explicitly. Finally, we deal with dynamic networks, by introducing stochastic actor-oriented models. Strengths and weaknesses of the different approach are discussed together with domains of applicability the geography of innovation studies.

Diffusion of Innovations in Dynamic Networks

Summary The evolution of a dynamic social network and the diffusion of an innovation are jointly modelled, dependent on one another, by using an extension of a stochastic actor-oriented model developed by Snijders, which is modified so that the adoption times follow a proportional hazards model. The asymptotic behaviour of the method-of-moments estimator is examined. The model is demonstrated on a data set involving the initiation of cannabis smoking among adolescents, and a simulation study is presented.