http://www.stats.ox.ac.uk/~snijders/siena/SnijdersSteglichVdBunt2009.pdf

Introduction to stochastic actor-based models for network dynamics

Social network analysis has been one of the fastest growing and most influential areas of recent times. This sparkling Handbook offers an unrivalled resource. Systematically, it introduces readers to the key concepts, substantive topics, central methods, and prime debates. The result is a peerless resource for teachers and students. Instead of consulting a variety of books and journal articles, the Handbook offers a one-stop guide that will be used by readers for decades to come.

The SAGE Handbook of Social Network Analysis

Here, we review the research we have conducted on social contagion. We describe the methods we have employed (and the assumptions they have entailed) to examine several datasets with complementary strengths and weaknesses, including the Framingham Heart Study, the National Longitudinal Study of Adolescent Health, and other observational and experimental datasets that we and others have collected. We describe the regularities that led us to propose that human social networks may exhibit a ‘three degrees of influence’ property, and we review statistical approaches we have used to characterize interpersonal influence with respect to phenomena as diverse as obesity, smoking, cooperation, and happiness. We do not claim that this work is the final word, but we do believe that it provides some novel, informative, and stimulating evidence regarding social contagion in longitudinally followed networks. Along with other scholars, we are working to develop new methods for identifying causal effects using social network data, and we believe that this area is ripe for statistical development as current methods have known and often unavoidable limitations. Copyright © 2012 John Wiley & Sons, Ltd.

/pdf/social-contagion-theory-examining-dynamic-social-networks-4usp1qzmeh.pdf

Social contagion theory: examining dynamic social networks and human behavior

Statistical models for social networks as dependent variables must represent the typical network dependencies between tie variables such as reciprocity, homophily, transitivity, etc. This review first treats models for single (cross-sectionally observed) networks and then for network dynamics. For single networks, the older literature concentrated on conditionally uniform models. Various types of latent space models have been developed: for discrete, general metric, ultrametric, Euclidean, and partially ordered spaces. Exponential random graph models were proposed long ago but now are applied more and more thanks to the non-Markovian social circuit specifications that were recently proposed. Modeling network dynamics is less complicated than modeling single network observations because dependencies are spread out in time. For modeling network dynamics, continuous-time models are more fruitful. Actor-oriented models here provide a model that can represent many dependencies in a flexible way. Strong model d...

/pdf/statistical-models-for-social-networks-19aymsimrf.pdf

Statistical Models for Social Networks

http://www.stats.ox.ac.uk/~snijders/RobinsSnijdersWangHandcockPattison.pdf

Recent developments in exponential random graph (p*) models for social networks

A recurrent problem in the analysis of behavioral dynamics, given a simultaneously evolving social network, is the difficulty of separating the effects of partner selection from the effects of social influence. Because misattribution of selection effects to social influence, or vice versa, suggests wrong conclusions about the social mechanisms underlying the observed dynamics, special diligence in data analysis is advisable. While a dependable and validmethod would benefit several research areas, according to the best of our knowledge, it has been lacking in the extant literature. In this paper, we present a recently developed family of statistical models that enables researchers to separate the two effects in a statistically adequate manner. To illustrate our method, we investigate the roles of homophile selection and peer influence mechanisms in the joint dynamics of friendship formation and substance use among adolescents. Making use of a three-wave panel measured in the years 1995–1997 at a school in ...

/pdf/dynamic-networks-and-behavior-separating-selection-from-2gvu0wsapc.pdf

Dynamic networks and behavior: separating selection from influence

Social network analysis is applied at the first two time points of a longitudinal study which examines how smoking and drug use in adolescence is associated with social position within peer group structures. One hundred and fifty secondary second grade students in one school named up to six best friends. This allowed for the categorization of each adolescent as a group member, a group peripheral, or a relative isolate. It was found that risk-taking behaviour occurred across all social positions. At both time points of the study the behaviour of pupils on the periphery of peer groups reflected both the gender and the behaviour of the groups themselves. At the second time point of the study there were far more pupils on the periphery of risk-taking groups than on the periphery of non-risktaking groups. The relationship appears to verify that risk-taking and non-risk-taking behaviour is learned predominantly in the context of peer clusters, and that risk-taking peer clusters act as a greater focus of influen...

Smoke rings: social network analysis of friendship groups, smoking and drug-taking

We analyse the co-evolution of social networks and substance use behaviour of adolescents and address the problem of separating the effects of homophily and assimilation. Adolescents who prefer friends with the same substance-use behaviour exhibit the homophily principle. Adolescents who adapt their substance use behaviour to match that of their friends display the assimilation principle. We use the Siena software to illustrate the co-evolution of friendship networks, smoking, cannabis use and drinking among sport-active teenagers. Results indicate strong network selection effects occurring with a preference for same sex reciprocated relationships in closed networks. Assimilation occurs among cannabis and alcohol but not tobacco users. Homophily prevails among tobacco and alcohol users. Cannabis use influences smoking behavior positively (i.e., increasing cannabis increases smoking). Weaker effects include drinkers smoking more and cannabis users drinking more. Homophily and assimilation are not significant mechanisms with regard to sporting activity for any substance. There is, however, a significant reduction of sporting activity among smokers. Also, girls engaged in less sport than boys. Some recommendations for health promotion programmes are made.

/pdf/homophily-and-assimilation-among-sport-active-adolescent-21v9fmscmz.pdf

Homophily and assimilation among sport- active adolescent substance users 1

Homophily and assimilation among sportactive adolescent substance users

Social network analysis is applied to three time points of a longitudinal study, which examines how risk-taking (represented by smoking and cannabis use) in adolescence is associated with social position within peer group structures. One hundred and fifty two students in the second year of secondary education in one Scottish school named up to six best friends, allowing for the categorization of each adolescent as a group member, a group peripheral or a relative isolate. Building on previous work, it is shown that transitions from non risk-taking to risk-taking behavior occur predominantly at peer group, rather than peripheral or isolate membership level. The transitions of pupils from time point one through to time point three are modeled as a Markov process, based on the assumption that the social position and risk-taking behavior (or transitional state) of a pupil at a certain time point depends only on their state at the previous time point. The results show that the Markov process is not stationary. The expected length of time spent by pupils in the various transitional states is also modeled, and provides another (time) dimension to the influence of peers on risk-taking behavior. We hypothesize that the influence exercised by an individual in a social network context increases with the cohesiveness of the individual’s social network position and the length of time he or she occupies that position. The results testify to the importance of risk-taking peer groups, both as a source of influence and selection of peripheral members, and to the need for differential targeting by sociometric state when delivering health education and intervention programs.

Michael Pearson

Papers

Dynamic networks and behavior: separating selection from influence

Smoke rings: social network analysis of friendship groups, smoking and drug-taking

Homophily and assimilation among sport- active adolescent substance users 1

Homophily and assimilation among sportactive adolescent substance users

Drifting Smoke Rings: Social Network Analysis and Markov Processes in a Longitudinal Study of Friendship Groups and Risk-taking 1