Postgraduate Course: Analysing Social Networks with Statistics (PGSP11452)
|School||School of Social and Political Science
||College||College of Humanities and Social Science
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||The course enables students to use statistical tools to analyse social network data. While Social Network Analysis (SNA) has long been used as an exploratory method, hypothesis testing and estimation techniques with network data is becoming an increasingly popular method in social science that require specific statistical techniques.
The course enables students to use statistical tools to analyse social network data. While Social Network Analysis (SNA) has long been used as an exploratory method, hypothesis testing and estimation techniques with network data is becoming an increasingly popular method in social science that require specific statistical techniques.
The course will have a practical focus and will introduce students to a range of basic and more advanced statistical models through hands-on computer work. These techniques will enable students to test the research questions (hypotheses) they will consider in their dissertation work. Students will also learn how to analyse network dynamics and large samples of ego-networks (personal networks) using single- and multi-level modelling.
- Are women significantly more central than men within Facebook networks?
- Is support within postżdivorce families more likely between people having blood relationships?
- Are friendship ties more likely between people from the same social class?
- What factors explain the persistence of ties before and after migration within personal networks of migrants?
- Are structural factors (e.g. density of connection) more important than individual (country of origin) or relational factors (tie strength)?
These (and others) are the kind of questions that students will be able to test at the end of the course.
- Starting with UCINet: Importing, visualising and transforming social network data
- Analysing the network cohesion: density, reciprocity and transitivity
- Analysing power and prestige: centrality measures
- Detecting communities: cohesive subgroup analysis
- Analysing affiliation (two-mode) networks
- Analysing network data with R and statnet
- Statistical testing and regression analysis with network data using permutation-based methods
- Ego-network analysis with R
- Introduction to multilevel modelling with ego-networks
- Introduction to longitudinal models: Analysing network dynamics with RSiena
This is a course for Q-Step degree programmes Social Policy with Quantitative Methods, Sociology with QM, Politics with QM and International Relations with QM. It is also open to all other Honours students who have successfully completed Doing Social Research with Statistics (SSPS08007) or any equivalent statistical course. The course can also be offered to PG students who have completed Social Network Analysis: Mapping and Exploring the Network Society (PGSP11372) and PG students with appropriate background knowledge in statistics.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| None
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2016/17, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 20,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||Three 750-word exercises, worth 40% of total mark«br /»
One 3,000-word essay (appendices and bibliography excluded), worth 60% of total mark.«br /»
The essay will address a research question briefly situated in scientific literature using network data, exploratory SNA (social network analysis) and a (set of) statistical model(s). The essay will include a substantive introduction, a short literature review, a methodology section and an appropriate SNA, a substantive discussion of the results and a conclusion.
||The course will include formative feedback through weekly exercises. The goal of the weekly exercises is to encourage students to participate actively in Computer Lab sessions. The exercises will be technically oriented to ensure that students have a good command of the software packages. Nevertheless, students will be encouraged to reflect on the short lectures and readings to discuss the results.
Three exercises will be assessed during the course, providing students with feedback for their final essay.
The three exercises will be returned with feedback within 15 working days of submission.
|No Exam Information
On completion of this course, the student will be able to:
- Use the software packages UCINet and R to analyse social networks
- Test scientific questions in SNA terms
- Undertake analysis of network data using statistical models
- Plan, design and execute a study using real-world network data and SNA in one area linked to a discipline of their choosing
- Interpret and communicate the results of exploratory and confirmatory SNA clearly
|Acton, R. M. Jasny, L. (2012). An introduction to network analysis with R and statnet. Sunbelt XXXII Workshop Series.|
Borgatti, S. P. Everett, M. G. Johnson, J. C. (2013). Analyzing social networks. Sage.
Crossley, N. Bellotti, E. Edwards, G. Everett, M. G. Koskinen, J. Tranmer, M. (2015). Social network analysis for ego-nets. Sage.
Hanneman, R. A. Riddle, M. Introduction to social network methods. http://faculty.ucr.edu/~hanneman/nettext/
Kolaczyk, E. D. Csárdi, G. (2014). Statistical analysis of network data with R. Springer.
Ripley, R. M., Snijders, T. A. B. Boda, Z. Vörös, A. Preciado, P. (2014). Manual for RSiena. University of Oxford, Department of Statistics, Nuffield College.
|Graduate Attributes and Skills
||Developing advanced SNA techniques and the capacity to use them in applied scientific context.
|Course organiser||Dr Gil Viry
Tel: (0131 6)51 5768
|Course secretary||Ms Nicole Develing-Bogdan
Tel: (0131 6)51 5067
© Copyright 2016 The University of Edinburgh - 3 February 2017 5:02 am