Full Description
Interest in social networks - patterns of relations between social actors such as individuals, corporations, and countries - has grown in the last decade, and analysis of longitudinal network data has moved forward strongly. Social networks often change; understanding this process, where changes lead to other changes, requires tools that can uncover the rules driving these changes. In 'Stochastic Actor-Oriented Models for Longitudinal Networks,' Tom A. B. Snijders and Christian Steglich bring together the first comprehensive textbook on the Stochastic Actor-Oriented Model (SAOM), a leading method for analyzing dynamic network data. They present the diverse SAOM variants developed since the 1990s, covering the co-evolution of networks and actor attributes as well as the co-evolution of multiple one-mode and two-mode networks. Providing a foundation for applying the methods as well as advice for problems encountered in practice, this book offers a detailed guide into the best practices of modeling longitudinal network data.
Contents
List of Illustrations; List of Tables; Preface; Part I. Network Dynamics: 1. Network dynamics: ties have consequences; 2. Longitudinal network data; 3. Actor-oriented models: fundamentals; 4. What drives network dynamics: effects; 5. Parameter estimation and testing; 6. Actor-oriented models: elaboration; 7. Rate functions; 8. Creating new and maintaining existing ties; 9. Local models, global consequences; 10. Absent data; Part II. Networks and Behavior: 11. Behavior change in a network context; 12. Longitudinal behavior data; 13. Modeling network-behavior co-evolution; 14. Effects for behavior; 15. Estimation and model construction for co-evolution models; 16. Diffusion of innovations; 17. Goodness-of-fit and other uses of simulated data; Part III. Special Data Structures: 18. Non-directed networks; 19. Multivariate networks; 20. Valued networks; 21. Two-mode networks; 22. Multiple groups; Glossary; References; Index.



