Search

Despite the central role of self-assembled groups in animal and human societies, statistical tools to explain their composition are limited. The authors introduce a statistical framework for cross-sectional observations of groups with exclusive membership to illuminate the social and organizational mechanisms that bring people together. Drawing from stochastic models for networks and partitions, the proposed framework introduces an exponential family of distributions for partitions. The authors derive its main mathematical properties and suggest strategies to specify and estimate such models. A case study on hackathon events applies the developed framework to the study of mechanisms underlying the formation of self-assembled project teams.

The study investigates to what degree Indonesia’s large-scale decentralization and democratization changed corruption networks. A role structure approach is developed to move current analysis of dyad-level structures to the network level. This approach is empirically tested by comparing the relational content and third-party structures of 96 corruption networks operating in the first phase of decentralization (2001–2004), characterized by indirect democracy and a powerful local council, with 94 corruption networks detected in the second phase (2005–2013), when direct local elections were introduced and the power of the local council declined. Building on Fiske’s relational model theory, it is argued and found that the local executive’s reduced dependence on the local council provided the opportunity to initiate corrupt exchanges with a broader set of players both inside and outside the bureaucracy. Whereas deep dependence power relations (i.e. formal authority) remained important, an increasing proportion of corruption networks involved compound role structures characterized by both shallow (non-embedded profit and work relations) and deep interdependence (kin- and friendship). Furthermore, third party intermediaries became more important. Implications for the study of networks of corruption are discussed.

Background: Despite the widespread knowledge about social support and health, there is little information about the association between social support and HIV risk behaviors such as condom use among female sex workers (FSWs) in Iran. This study aimed to determine the association between social support and frequency of condom use among FSWs in Tehran, Iran. Methods: Using mixed sampling methods, we recruited 170 FSWs in Tehran in 2017. We measured self-reported social support by face-to-face interviews using a standardized questionnaire. Linear regression was used to assess the association between socio-demographic characteristics (age, education level, marital status, and place of living), transactional sex characteristics (age at first transactional sex and frequency of transactional sex in the last month), HIV knowledge, social support network characteristics (social network size, duration of tie, intimacy, social support), and condom use behavior. Results: Of the total of 1193 persons in FSW’s social networks, 615 (51%) were sexual partners, 529 (44%) were peer sex workers, and 36 (5%) were family members. The participants perceived moderate social support from sexual partners, low from peer sex workers, and very low from family members. Adjusted for individual and other network characteristics, peer sex worker social support (b = 0.28, 95%CI 0.06, 0.50), and family support (b = 1.12, 95%CI 0.028, 2.23) were significantly associated with condom use. Conclusion: Family and peer sex worker social support are associated with condom use, but less strongly than HIV knowledge or place of living. However, very few FSWs are socially connected with families. Interventions to promote condom use among this vulnerable population should also consider social and familial support.

Using data on 32 actors and ties among them drawn from available court files, we combine analytical sociology with statistical models for networks in order to analyse a case of a counterfeit alcohol distribution network from the Czech Republic. We formulate a theory of action and identify relational mechanisms which could explain how the structure of the network emerged and describe. We use the exponential random graph model to test these mechanisms. The analysis reveals that the two actors capable of manufacturing the poisonous mixture were considerably though not optimally proximate to others enabling fast distribution of the mixture. Our model results that the structure was formed by mechanisms of triadic closure, negative tendency to concentrate ties, and tie translation of pre-existing ties into operational ties. We conclude with the discussion of the implications our approach for the study of criminal networks.

Stochastic actor-oriented models (SAOMs) are a modelling framework for analysing network dynamics using network panel data. This paper extends the SAOM to the analysis of multilevel network panels through a random coefficient model, estimated with a Bayesian approach. The proposed model allows testing theories about network dynamics, social influence, and interdependence of multiple networks. It is illustrated by a study of the dynamic interdependence of friendship networks and minor delinquency. Data were available for 126 classrooms in the first year of secondary school, of which 82 were used, containing relatively few missing data points and having not too much network turnover.

BACKGROUND Validation of the 2016 LANO MRI scorecard for leptomeningeal metastasis failed for multiple reasons. The objective of this joint EORTC Brain Tumor Group and RANO effort was to validate the feasibility of the revised MRI scorecard for assessing response in leptomeningeal metastasis. METHODS Coded paired cerebrospinal MRI of 20 patients with leptomeningeal metastases from solid cancers at baseline and follow-up after treatment and instructions for assessment were provided via the EORTC imaging platform. The kappa coefficient (K) was used to evaluate inter-observer pairwise agreement. Statistical analyses were performed using SAS V9.4 software (Cary, NC). The sponsor of the study was the University Hospital Zurich (2018-00192). RESULTS Thirty-five raters participated, including 9 neuroradiologists, 17 neurologists, 4 radiation oncologists, 3 neurosurgeons and 2 medical oncologists. Among leptomeningeal metastases-related items at baseline, the best median concordance was noted for hydrocephalus (K=0.63), and the worst median for spinal linear enhancing disease (K=0.46). The median concordance for overall response was moderate (K=0.44). Notably, the interobserver agreement for the presence of parenchymal brain metastases at baseline was minimal (K=0.29). Significant differences were observed when considering the specialty of the raters. Only 394 of 700 ratings (56%) were fully completed. Among 394 fully completed ratings, perfect concordance was noted in 293 ratings (74%) when comparing the overall response according to the guidelines provided in the scorecard and the overall response provided by the raters. The main discordances were noted for partial response according to the rater versus stable disease according to the guidelines (n=44), followed by progression according to the raters versus stable disease according to the guidelines (n=23). CONCLUSION Electronic case report forms with "blocking solutions" are probably required to enforce completeness and quality of scoring. These results confirm the necessity of central review and the need for training of MRI assessment in clinical trials.

This research focuses on ambivalence in family networks and presents a framework for investigating how triadic configurations, beyond specific dyads, may affect individual outcomes such as well-being. First, the paper introduces the ambivalent triad census, counting the frequencies of 18 non-isomorphic triads in which ties can be positive, negative, or ambivalent, in non-directed networks, and proposes the linear combinations of three theoretical mechanisms (ambivalent balance, diffusion of stress, divide and conquer) predicting how embeddedness in an ambivalent triad may affect individual well-being. Second, the ambivalent triad census is applied to 300 non-directed family networks, 150 stepfamilies and 150 first-time families, in which mothers reported about the relationships with and between family members. Results show that mothers embedded in triads exhibiting more ambivalent balance and less diffusion of stress score higher on social self-esteem. The study emphasizes the importance of studying ambivalence in higher-level relational structures, such as triads, in families.

This paper proposes that common measures for network transitivity, based on the enumeration of transitive triples, do not reflect the theoretical statements about transitivity they aim to describe. These statements are often formulated as comparative conditional probabilities, but these are not directly reflected by simple functions of enumerations. We think that a better approach is obtained by considering the probability of a tie between two randomly drawn nodes, conditional on selected features of the network. Two measures of transitivity based on correlation coefficients between the existence of a tie and the existence, or the number, of two-paths between the nodes are developed, and called “Transitivity Phi” and “Transitivity Correlation.” Some desirable properties for these measures are studied and compared to existing clustering coefficients, in both random (Erdös–Renyi) and in stylized networks (windmills). Furthermore, it is shown that in a directed graph, under the condition of zero Transitivity Correlation, the total number of transitive triples is determined by four underlying features: size, density, reciprocity, and the covariance between in- and outdegrees. Also, it is demonstrated that plotting conditional probability of ties, given the number of two-paths, provides valuable insights into empirical regularities and irregularities of transitivity patterns.

The dynamics of individual behavior are related to the dynamics of the social structures in which individuals are embedded. This implies that in order to study social mechanisms such as social selection or peer influence, we need to model the evolution of social networks and the attributes of network actors as interdependent processes. The stochastic actor-oriented model is a statistical approach to study network-attribute coevolution based on longitudinal data. In its standard specification, the coevolving actor attributes are assumed to be measured on an ordinal categorical scale. Continuous variables first need to be discretized to fit into such a modeling framework. This article presents an extension of the stochastic actor-oriented model that does away with this restriction by using a stochastic differential equation to model the evolution of a continuous attribute. We propose a measure for explained variance and give an interpretation of parameter sizes. The proposed method is illustrated by a study of the relationship between friendship, alcohol consumption, and self-esteem among adolescents.

We consider the specification of effects of numerical actor attributes, having an interval level of measurement, in statistical models for directed social networks. A fundamental mechanism is homophily or assortativity, where actors have a higher likelihood to be tied with others having similar values of the variable under study. But there are other mechanisms that may also play a role in how the attribute values of two actors influence the likelihood of a tie between them. We discuss three additional mechanisms: aspiration, the tendency to send more ties to others having high values; attachment conformity, sending more ties to others whose values are close to the “social norm”; and sociability, where those having higher values will tend to send more ties generally. These mechanisms may operate jointly, and then their effects will be confounded. We present a specification representing these effects simultaneously by a four-parameter quadratic function of the values of sender and receiver. Flexibility can be increased by a five-parameter extension. We argue that for numerical actor attributes having important effects on directed networks, these specifications may provide an improvement. An illustration is given of dependence of advice ties on academic grades, analyzed by the Stochastic Actor-oriented Model.

This study investigated if and how children and teachers differ in their assessment of victim-aggressor relationships in kindergartens. Self-, peer, and teacher reports of victimization-aggression networks (who is victimized by whom) were investigated in 25 Swiss kindergartens with 402 5- to 7-years-old. It was examined whether child characteristics (sex and parent-reported internalizing and externalizing behavior) influence informant reports of victimization and/or aggression. Findings from statistical network models indicated higher concordance between self and peer reports than between one of these and teacher reports. Results further showed more agreement among informants on aggressors than on victims. Aggressors reported by self and peer reports were low on internalizing behavior, and aggressors reported by self and teacher reports were high on externalizing behavior; teacher-reported victims were also high on externalizing behavior. Internalizing behavior was unrelated to victimization. According to self and peer reports, boys as well as girls were victimized by boys and girls equally; teachers reported less cross-sex victimization than same-sex victimization. The different views of teachers and children on victim-aggressor relationships have implications for the identification of aggression in early childhood. Mutual sharing of information between children, their parents, peers, and teachers may contribute to signaling victims and aggressors in the early school years., Aggressive Behavior, vol. 45, no. 3, p. 275

For empirical work on macro-micro-macro issues, it is indispensable to have statistical models reflecting in a plausible way the data structures and theoretical relations that are the basis of such issues. A basic family of models for macro-micro effects is provided by multilevel analysis. An important way of studying micromacro transitions is by means of simulation. Network modeling provides another, particularly appropriate, approach to macromicro-macro issues. Network models represent, in a more subtle way than multilevel models, that what can be observed at the macro level is the result of phenomena at the micro level, while these phenomena themselves are conditioned by the macro level. The use of appropriate statistical network models, with sufficient attention to model fit, can lead to important progress in our understanding of macro-micro-macro issues. This is more a matter of promises for the future than of past achievements, however. A major reason for the limitations in the current state of the art is that the feedback issues which are essential to how networks operate, are so difficult to express in statistical models in a manageable and plausible way. In models for single (i.e., one-moment) observations of a social network, the time dimension of the feedback process is beaten flat, which leads to grave difficulties both of interpretation and of mathematical modeling. Although modeling single observations of social networks still is necessary and useful, more insight may be gained from repeated (multi-moment) observations of social networks. If such a dynamic model would include not only the relations between actors but also changing actor attributes (e.g., attitudes, behavior, performance) and the larger pattern of social settings in which networks are embedded, it would capture a great part of what we regard as macro-micro-macro processes. Such an integrated model does not yet exist, but work is currently under way toward the construction of this type of models. Para llevar a cabo el trabajo empírico sobre temas macro-micro-macro, es indispensable tener modelos estadísticos que reflejen de manera plausible la estructura de los datos y las relaciones teóricas en la base de tales cuestiones. Una familia básica de modelos para los efectos macro-micro es ofrecida por el análisis multinivel. Una manera importante de estudiar las transiciones micro-macro es mediante simulación. Los modelos sobre redes proponen otra perspectiva, particularmente apropiada, a los temas macro-micro-macro. Los modelos de redes representan, de manera más sutil que los modelos multinivel, que lo que puede ser observado a nivel macro es el resultado de fenómenos a nivel micro, mientras que estos fenómenos están condicionados por el nivel macro. El uso de modelos estadísticos apropiados para redes, con atención suficiente al ajuste del modelo, puede conducir a progresos importantes en nuestra comprensión de las cuestiones macro-micro-macro. Sin embargo, esto es más una promesa de cara al futuro que un logro del pasado. Una razón de importancia mayor de las limitaciones en el estado actual del arte es que las cuestiones de retroalimentación (feedback) que son esenciales en cómo operan las redes, son extremadamente difíciles de expresar en modelos estadísticos de forma operativa y plausible. En los modelos para una única observación (en un momento dado) de una red social, la dimensión temporal de la retroalimentación es aplastada, lo que conduce a dificultades graves tanto de cara a la interpretación como al modelado matemático. A pesar de que modelar observaciones en un momento dado de las redes sociales es todavía necesario y útil, es posible ganar en comprensión a partir de observaciones repetidas de redes sociales (en varios momentos diferentes). Si tal modelo dinámico incluyese, no sólo las relaciones entre actores, pero también los atributos cambiantes de los actores (por ejemplo, las actitudes, comportamientos, resultados) y las pautas englobantes de los contextos sociales en que las redes se encuentran inmersas, capturaría una gran parte de lo que consideramos como procesos macro-micro-macro. Tal modelo integrado no existe todavía, pero se están llevando a cabo avances hacia la construcción de este tipo de modelo.

Success for All (SfA) is a comprehensive school reform program with a strong emphasis on cooperative learning that aims to improve students' social emotional learning alongside students' cognitive learning. In the present study it was examined whether SfA led to improved students' social behavior in Grade 1-3 of primary education. Peer sociometric data was collected for 974 students aged 6-9. Using multivariate multilevel analysis we found no significant effect of SfA on students' proand antisocial behavior over time. However, a significant interaction effect was found showing that antisocial behavior of students from disadvantaged backgrounds decreased in the intervention condition in Grade 2. This is a promising finding given that the SfA program was especially developed for schools serving large numbers of disadvantaged students. Implications of the study are described.

This study examines ethnic integration in secondary school. Social identity theory suggests that perception of relevant individual attributes plays a crucial role in defining ingroups and outgroups, contributing to befriending, and disliking others. Therefore, we analyze the role of peer-perceived ethnicity in social ties. Networks of friendship, dislike, and perceived ethnicity were modeled together using dynamic stochastic actor-oriented models, separating the effect of perceived ethnicity on social ties from that of social ties on perceived ethnicity. Data came from a Hungarian sample of 12 school classes with one minority group: the Roma. Treating friendship and dislike as mutually exclusive and comparing them to neutral relations, we found evidence for the role of perceived ethnicity in dislike—majority students disliked those they perceived as minority peers. However, we saw no direct effect of ethnicity on the friendship network. Implications of the joint modeling of mutually exclusive relationship aspects are discussed.