This course will be taught at the Department of Politics and International Relations, Manor Road Building, Oxford University

Introduction to Generalized Nonlinear Models: The use of generalized linear models (including multiple linear regression, logistic regression, log-linear models, proportional hazards models, etc.) is by now very familiar in empirical social science. But often the use of a linear predictor is unduly restrictive. The familiar GLM framework can be extended to include a wide variety of non-standard models that have been devised by social scientists: these include row-column association models for multi-way tables, log-multiplicative ("UNIDIFF") and layer-effects ("topological") models for mobility data, diagonal-reference models for dependence on a square classification, parametric hazard models for duration data, etc. The aim of the course will be to present an overview of such models, their interpretation, and their unified implementation via the "gnm" package for the open-source R statistical computing environment.

A pre-requisite for this course is familiarity with R (for which see http://www.r-project.org) to the level of the Spring School's "Crash Course in R". Participants who are not familiar with R should also attend the Crash Course in R. Some previous exposure to GLM methods such as logistic regression and log-linear models is also assumed: a rapid refresher will be provided at the start of this course.

Crash Course in R: This is a short introductory course presenting the basics of the R statistical package. R is a fully-documented, modern and free statistical computing environment, providing extensive graphics capabilities and implementations of many cutting-edge methods. It is very similar to S-plus.

Both courses can be taken separately. Please indicate on the registration form which course(s) you would like to attend.

The Crash Course in R will take place on Monday morning (12 December) from 9:30am-1pm. The Introduction to Generalized Nonlinear Models in Social Research course will take place on Monday afternoon (12 December) from 2-5:30pm and all day on Tuesday (13 December) from 9:30am-5:30pm.

For a map of how to get to the Manor Road Building and links to information on travelling to Oxford, please click here.

[top]

Instructors

David Firth
Professor of Statistics in the Department of Statistics, University of Warwick.
Research interests: statistical theory and applications in areas such as social mobility, health, deprivation and voting.

Heather Turner
Research Fellow in the Department of Statistics, University of Warwick.
Research interests: plaid models for gene expression data, statistical methods for social science

[top]

Cost

The cost of attending the courses will be:

• Participants from UK Institutions: Crash Course in R - £30; Generalized Nonlinear Models - £90
• Participants from non-UK ECPR Institutions: Crash Course in R - £37.50; Generalized Nonlinear Models - £112.50
• Participants from non-UK, non-ECPR Institutions: Crash Course in R - £50; Generalized Nonlinear Models - £150

Teaching staff at UK universities can apply for an ESRC Training Bursary to cover the cost of attending the Spring School. The system has recently changed and the ESRC Research Methods Programme is accepting applications at any time (in advance of the event for which funding is being sought). For information on how to apply for bursaries, please see their website: www.ccsr.ac.uk/methods/bursaries.

Participants from ECPR institutions are also eligible to apply for travel and accommodation costs through the ECPR's mobility fund, and for fees through its scholarship fund. Details on the ECPR mobility fund can be found here.

[top]

Accommodation

Unfortunately, we are unable to offer accommodation for this course. If you would like to make your own arrangements to stay in Oxford, you can find information about accommodation on the Oxford City website or on the Oxford Daily Information website.

 

Registration

Registration for these courses has now closed. Please keep an eye on our website for other courses that may be of interest to you.

[top]