Validating cross-national surveys
29 November 2012
In an increasingly open world, cross-national studies are used to inform policy and practice. One of the challenges of using this sort of survey data is to ensure that researchers have valid and reliable methods of comparing results from different countries. Cross-national surveys compare knowledge of and attitudes towards certain issues, such as the average levels of support for immigration, between different countries. Such surveys also need to consider whether the questions which are meant to be comparable across countries really are comparable. The Latent Variable Modelling of Categorical Data (LCAT) project examined statistical methods and developed computing tools to help researchers test questions to determine how comparable the results are, which enables surveys to deliver better and more reliable policy recommendations.