Past events

Social network analysis four-day course: Theory, method and application

You are viewing a past event.

Date: Tuesday 14 February to Friday 17 February 2017
Venue: AGSE207 Hawthorn Campus

Add to Calendar

Join the four-day intensive social network analysis (SNA) course. Learn how to conduct social network research. Move from the fundamentals of networks to how to use cutting-edge statistical network models. Some general statistical knowledge is assumed.

Social network analysis four-day course: Theory, method and application

You will require your own PC laptop (or Mac with Windows installed).

The course includes all course exercise materials, plus books on doing network research and ERGM. Lunch and afternoon tea is provided. 

Registration cost

$2400 (Full-time PhD students $1200; discounts for Swinburne staff and students).

Follow the 'Register Now' link at the bottom of this page to purchase tickets on Eventbrite.

Download the flyer

Social Network Analysis four-day course flyer [PDF, 456KB]

Contact Information: Dr Peng Wang, Centre for Transformative Innovation
Email: Tel: 03 9214 8230

Day 1: Network Fundamentals

Network Fundamentals

  • What is distinctive about social network research?
  • Network representations and network data.
  • Qualitative versus quantitative data collection.
  • Primary versus secondary data collection.
  • Ethics and network research.
  • Organisational network methods.
  • Data entry, data processing and management.
  • Software options for visualisation and analysis.
  • Network case study: Network research design.

Day 2: Key concepts and descriptive SNA

Key concepts and descriptive SNA

  • Density and reciprocity.
  • Clustering and triadic closure.
  • Influential nodes and degree distributions.
  • Preferential attachment and small worlds.
  • Actor attributes.
  • Multiplex and bipartite networks.
  • Simple random graph distributions.
  • Network case study: Why do we need statistical models for social networks?

Day 3: Introduction to ERGM

Introduction to ERGM

  • What are exponential random graph models?
  • Formation of network structure.
  • MPNet software for network models.
  • Working with graph distributions.
  • Dependence assumptions: Bernoulli, Markov and Social Circuit models.
  • Estimating ERGMs (modelling network data).
  • Network case study: ERGMs for organisations.

Day 4: ERGM extensions

ERGM extensions

  • Simulation and Goodness of Fit with ERGM.
  • Estimating directed ERGMs.
  • Estimating ERGMs with actor attributes.
  • Multilevel networks.
  • Causality in networks.
  • ALAAMs – social influence models.
  • Problem solving for ERGM model fit.
  • Future directions.
  • Network case study: Applications of ERGM.