Network Science

(3 cr.) P: Consent of instructor. Network science is concerned with
the relationships between individuals, organizations, groups, and
other "social" entities. This methodological and theoretical approach
to the social world has gained interest in fields across the social,
behavioral and political sciences - and shares much in terms of
methods with network studies in the natural sciences. At the core of
the field is attention to the interconnected nature of actors and
their relationships. This type of approach requires a different set of
assumptions and analytical tools than standard statistical methods.

This course will primarily focus on statistical methodology for
relational data measured on groups of social actors. Topics to be
discussed include an introduction to graph theory and the use of
directed graphs to study structural theories of actor interrelations;
structural and locational properties of actors, such as centrality,
prestige, and prominence; subgroups and cliques; equivalence of
actors, including structural equivalence, blockmodels, and an
introduction to role algebras; an introduction to local analyses,
including dyadic and triad analysis; and statistical global analyses,
using models such as pl, p*, and their relatives. The course will also
introduce data collection and harvesting methods, egocentric analysis,
and the use of popular networks analysis and visualization software
packages.

This is not a course in network theory; it is a course in methodology,
with emphasis on statistical approaches.

Students are expected to attend lectures and register for lab
sessions. Assignments will include regular lab exercises and a final
network project. Students should have completed at least two upper
level statistics courses or contact the instructors for permission to
enroll in the course.