11 September 2015
Network Models in STI Epidemiology
This summer school builds on the success of the last year’s summer school “Network Statistics in Health Research”. Participants of this year’s summer school will gain a detailed understanding and hands-on experience in applying statistical and computational models to analyse the network dynamics of epidemics of sexually transmitted infections (STIs). Network statistics is a rapidly expanding branch in statistics that is concerned with the description and inference of network properties. Analyses of sexual network data have made crucial contributions to an improved understanding of the epidemiology and sociology behind the transmission of STIs.
After a brief review of traditional compartmental (SIR) models and the methodology for classical descriptive network analysis, Exponential family Random Graph Models (ERGMs) will be introduced. ERGMs represent the processes that drive the formation of links in networks and are a natural and flexible tool to model (sexual) network data.
Agent-based Models (ABMs) offer an alternative “bottom-up” approach to modelling the evolution of a network, and the changes in agent attributes. In this modelling framework, network ties are added and removed, based on characteristics of the (potential) relationship and attributes of the agents involved.
During computer lab sessions, participants will go through examples and tutorials with applications of both the ERGM and ABM approach to modelling network data. The labs will develop programming skills, using the R packages statnet, EpiModel, and RSimpactCyan. Participants will learn how to develop, analyse and visualise stochastic network models for epidemics, with a focus on empirical models of HIV transmission and control.
Participants are expected to bring their own laptop computer, with R and RStudio pre-installed. Although experience with R is not strictly required, participants who have not previously used R are advised to familiarise themselves with the R language prior to the summer school.
Prof Dr Wim Delva
This summer school is aimed primarily at PhD students from Flemish Universities and research institutions, although Master’s students and post-doctoral fellows, as well as applicants from non-Flemish institutions are welcome too.
To introduce methods for modelling sexual networks, and to develop hands-on skills in applying these methods to address research questions related to the epidemiology of HIV and other sexually transmitted infections.
EUR 450: Registration costs 450 euro, and includes tuition, sandwich lunches, coffee breaks and course materials.
Students of co-funding Doctoral Schools will be given a refund after successful completion of the summer school.