The BIAS project

Bayesian methods for combining multiple Individual and Aggregate data Sources in observational studies.

BIAS, based at Imperial College, London, is a node of the Economic and Social Research Council's National Centre for Research Methods (NCRM). BIAS I was funded between April 2005 and June 2008 under the first phase of node commissioning. BIAS II is currently funded by the second commissioning phase from July 2008 to June 2011.

The aims of the project are

To develop a set of statistical frameworks for combining data from multiple sources.
To improve the capacity of social science methods to handle the intricacies of observational data.

Bayesian hierarchical models will be used as the basic building blocks for these developments. These offer a natural tool for linking together many different sub-models and data sources.

Find out more about the research programme
Discover the research training opportunities offered.

Latest News

****** Short courses on "Introduction to Bayesian analysis using WinBUGS" and "Bayesian Spatial Analysis of Small Area Data using WinBUGS/GeoBUGS & INLA" will be held at Imperial College London, July 13-16 2010. ******
The Special Issue of Statistical Methodology on Statistical Methods for Statistics and the Social Sciences, honoring the 10th anniversary of the Center for Statistics and the Social Sciences (CSSS) at the University of Washington, has just been published. The publisher, Elsevier, has now decided to make it freely available online for a limited time. There is also a short video introduction to the issue.
Dr. Guangquan (Philip) Li has been awarded a Young Academic Award for participation to the CRiSM workshop on Model Uncertainty, May 2010.
A forthcoming Master class on New Bayesian Methods for Model Comparison (jointly sponsored by the BIAS node and the Lancaster-Warwick-Stirling node), to be held at The Postgraduate Statistics Centre, Department of Maths and Statistics, Lancaster University on 29th March 2010. For more details, please visit the course website.
Course: Introduction to graphical models and Bayesian networks for social scientists (15-16 October 2009)