Stanley Wasserman

Models and methods in social network analysis

REPRESENTAÇÕES SOCIAIS NA ÁREA DE GESTÃO EM SAÚDE: Teoria e Prática. De Neusa Rolita Cavedon (Org.). 1a Ed. Porto Alegre: Dacasa, 2005. 109 p. ISBN: 85-86072-66-4. O estudo das representações sociais tem ganhado ênfase por parte de pesquisadores brasileiros que buscam um arcabouço teórico sólido e consistente para a investigação qualitativa de fenômenos organizacionais de forma contextualizada, descritiva e reveladora de significados subjetivos. Significados estes que muitas vezes não podem ser captados e/ou explicados pelas abordagens científicas tradicionais. Um exemplo dessa ênfase é a recente obra da professora e pesquisadora Neusa Rolita Cavedon e seus colaboradores (Nota por Thiago Duarte Pimentel CEPEAD/UFMG).

Logit models and logistic regressions for social networks: I. An introduction to Markov graphs andp

Spanning nearly sixty years of research, statistical network analysis has passed through (at least) two generations of researchers and models. Beginning in the late 1930s, the first generation of research dealt with the distribution of various network statistics, under a variety of null models. The second generation, beginning in the 1970s and continuing into the 1980s, concerned models, usually for probabilities of relational ties among very small subsets of actors, in which various simple substantive tendencies were parameterized. Much of this research, most of which utilized log linear models, first appeared in applied statistics publications.But recent developments in social network analysis promise to bring us into a third generation. The Markov random graphs of Frank and Strauss (1986) and especially the estimation strategy for these models developed by Strauss and Ikeda (1990; described in brief in Strauss, 1992), are very recent and promising contributions to this field. Here we describe a large class of models that can be used to investigate structure in social networks. These models include several generalizations of stochastic blockmodels, as well as models parameterizing global tendencies towards clustering and centralization, and individual differences in such tendencies. Approximate model fits are obtained using Strauss and Ikedas (1990) estimation strategy.In this paper we describe and extend these models and demonstrate how they can be used to address a variety of substantive questions about structure in social networks.

Object permanence in five-month-old infants*

Abstract A new method was devised to test object permanence in young infants. Five- month-old infants were habituated to a screen that moved back and forth through a 180-degree arc, in the manner of a drawbridge. After infants reached habituation, a box was centered behind the screen. Infants were shown two test events: a possible event and an impossible event. In the possible event, the screen stopped when it reached the occluded box; in the impossible event, the screen moved through the space occupied by the box. The results indicated that infants looked reliably longer at the impossible than at the possible event. This finding suggested that infants (1) understood that the box continued to exist, in its same location, after it was occluded by the screen, and (2) expected the screen to stop against the occluded box and were surprised, or puzzled, when it failed to do so. A control experiment in which the box was placed next to the screen provided support for this interpretation of the results. Together, the results of these experiments indicate that, contrary to Piagets (1954) claims, infants as young as 5 months of age understand that objects continue to exist when occluded. The results also indicate that 5-month-old infants realize that solid objects do not move through the space occupied by other solid objects.

Advances in social network analysis : research in the social and behavioral sciences

Introduction - Joseph Galaskiewicz and Stanley Wasserman Advances in the Social and Behavioral Sciences from Social Network Analysis PART ONE: SOCIAL PSYCHOLOGY AND DIFFUSION Network Studies of Social Influence - Peter V Marsden and Noah E Friedkin Epidemiology and Social Networks - Martina Morris Modeling Structured Diffusion Statistical Models for Social Support Networks - Michael E Walker, Stanley Wasserman and Barry Wellman Social Cognition in Context - Philippa Pattison Some Applications of Social Network Analysis PART TWO: ANTHROPOLOGY AND COMMUNICATION Anthropological Contributions to the Study of Social Networks - Jeffrey C Johnson A Review Primate Social Networks - Donald Stone Sade and Malcolm M Dow Network Analysis and Computer-Mediated Communication Systems - Ronald E Rice PART THREE: POLITICS AND ORGANIZATIONS Intraorganizational Networks - David Krackhardt and Daniel J Brass The Micro Side Networks of Interorganizational Relations - Mark S Mizruchi and Joseph Galaskiewicz Marketing and Social Networks - Phipps Arabie and Yoram Wind Networks of Elite Structure and Decision Making - David Knoke

LOGIT MODELS AND LOGISTIC REGRESSIONS FOR SOCIAL NETWORKS : II. MULTIVARIATE RELATIONS

The research described here builds on our previous work by generalizing the univariate models described there to models for multivariate relations. This family, labelled p*, generalizes the Markov random graphs of Frank and Strauss, which were further developed by them and others, building on Besags ideas on estimation. These models were first used to model random variables embedded in lattices by Ising, and have been quite common in the study of spatial data. Here, they are applied to the statistical analysis of multigraphs, in general, and the analysis of multivariate social networks, in particular. In this paper, we show how to formulate models for multivariate social networks by considering a range of theoretical claims about social structure. We illustrate the models by developing structural models for several multivariate networks.

A p* primer: Logit models for social networks

Abstract A major criticism of the statistical models for analyzing social networks developed by Holland, Leinhardt, and others [Holland, P.W., Leinhardt, S., 1977. Notes on the statistical analysis of social network data; Holland, P.W., Leinhardt, S., 1981. An exponential family of probability distributions for directed graphs. Journal of the American Statistical Association. 76, pp. 33–65 (with discussion); Fienberg, S.E., Wasserman, S., 1981. Categorical data analysis of single sociometric relations. In: Leinhardt, S. (Ed.), Sociological Methodology 1981, San Francisco: Jossey-Bass, pp. 156–192; Fienberg, S.E., Meyer, M.M., Wasserman, S., 1985. Statistical analysis of multiple sociometric relations. Journal of the American Statistical Association, 80, pp. 51–67; Wasserman, S., Weaver, S., 1985. Statistical analysis of binary relational data: Parameter estimation. Journal of Mathematical Psychology. 29, pp. 406–427; Wasserman, S., 1987. Conformity of two sociometric relations. Psychometrika. 52, pp. 3–18] is the very strong independence assumption made on interacting individuals or units within a network or group. This limiting assumption is no longer necessary given recent developments on models for random graphs made by Frank and Strauss [Frank, O., Strauss, D., 1986. Markov graphs. Journal of the American Statistical Association. 81, pp. 832–842] and Strauss and Ikeda [Strauss, D., Ikeda, M., 1990. Pseudolikelihood estimation for social networks. Journal of the American Statistical Association. 85, pp. 204–212]. The resulting models are extremely flexible and easy to fit to data. Although Wasserman and Pattison [Wasserman, S., Pattison, P., 1996. Logit models and logistic regressions for social networks: I. An introduction to Markov random graphs and p*. Psychometrika. 60, pp. 401–426] present a derivation and extension of these models, this paper is a primer on how to use these important breakthroughs to model the relationships between actors (individuals, units) within a single network and provides an extension of the models to multiple networks. The models for multiple networks permit researchers to study how groups are similar and/or how they are different. The models for single and multiple networks and the modeling process are illustrated using friendship data from elementary school children from a study by Parker and Asher [Parker, J.G., Asher, S.R., 1993. Friendship and friendship quality in middle childhood: Links with peer group acceptance and feelings of loneliness and social dissatisfaction. Developmental Psychology. 29, pp. 611–621].

Models and Methods in Social Network Analysis: Structural Analysis in the Social Sciences

Personal relationships have long been of central interest to social scientists, but the subject of friendship has been relatively neglected. Moreover, most studies of friendship have been social psychological in focus. Placing Friendship in Context is a unique collection bridging social psychological and social structural research to advance understanding of this important subject. In it, some of the world’s leading researchers explore the social and historical contexts in which friendships and similar informal ties develop and how it is that these contexts shape the form and substance the relationships assume. Together, they demonstrate that friendship cannot be understood from individualist or dyadic perspectives alone, but is a relationship significantly influenced by the environment in which it is generated. By analysing the ways in which friendships articulate with the social structures in which they are embedded, Placing Friendship in Context redescribes such personal relationships at both the macro and the micro level.

Statistical Models for Social Support Networks

In recent years, the conceptualization of social support in the literature has become increasingly sophisticated, facilitating the consideration of more complex theories. Researchers no longer consider the mere availability of social ties, but look instead at the flow of specific resources through a social network. This article discusses how the social network has been defined in the context of social support. Research is reviewed, indicating how characteristics of individual tie (e.g., tie strength, proximity, frequency of contact, similarity) are related to the provision of support. Also examined are how characteristics of the personal network (e.g., size, density) relate to support and wellbeing. Statistical models for network analysis and how they should prove useful in studying social support are then discussed.

Statistical Analysis of Multiple Sociometric Relations

Abstract Loglinear models are adapted for the analysis of multivariate social networks, a set of sociometric relations among a group of actors. Models that focus on the similarities and differences between the relations and models that concentrate on individual actors are discussed. This approach allows for the partitioning of the actors into blocks or subgroups. Some ideas for combining these models are described, and the various models and computational methods are applied to the analysis of data for a corporate interlock network of the 25 largest organizations in Minneapolis/St. Paul and for a classic network of 18 monks in a cloister. The computational techniques all involve variations on the standard iterative proportional-fitting algorithm used extensively in the analysis of multidimensional contingency tables.

Analyzing Social Networks as Stochastic Processes

Abstract This article presents a new methodology for studying a social network of interpersonal relationships, based on stochastic modeling of the changes that occur in the network over time. Specifically, we postulate that these changes can be modeled as a continuous-time Markov chain. The transition rates for the chain are dependent on a small set of parameters that measure the importance of various aspects of social structure on the probability of change. We discuss the assumptions of the framework and describe two simple models that are applications of it. We then present, analyze, and interpret several examples, and we outline methods of parameter estimation. The models prove to be quite effective and allow us to better understand the evolution of a network.