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

Principal Investigator: Professor Nicky Best

BIAS (Bayesian methods for combining multiple Individual and Aggregate data Sources in observational studies) was interested in modelling the complexities and core processes that underlie observational social science data and in developing a set of statistical frameworks for combining data from different sources.

These data include aggregate level data, longitudinal studies, multilevel data and surveys amongst others. As these data are notoriously full of missing values, non-responses, selection biases and other idiosyncrasies, simple analyses can be very misleading. Further, it is typically the case that a single dataset fails to provide all the necessary information, thus to answer relevant research questions it is necessary to combine datasets from multiple sources.

The researchers at BIAS aimed to construct a comprehensive set of inter-dependent sub-models to cater for the complex structure in the data. To do this, they used Bayesian hierarchical and graphical models as they offer a natural tool for linking together many different sub-models and data sources. The BIAS project also ran courses in Bayesian hierarchical models and small area estimation as well as disseminating its research and providing computer code to run the models.

BIAS was based at Imperial College London.

For further information please see BIAS website.