This article explores how aggregate level data may be used to make inferences about individual level behaviour. A common strategy in the past was to assume that the relations evident in aggregated data are also present in individual data. Analysis of datasets where there is both individual and aggregated information demonstrates that this assumption is most often incorrect. This means that the relationships observed between variables at an aggregated level are unlikely to be observed in individual level data. This is a problem because quite often social scientists only have aggregated data for exploring individual level behaviour. A key question explored in this article is how is it possible to validly and reliably use aggregated datasets to make inferences about relationships between variables at the individual level. An example analysis is given using electoral data from the Czech Republic.
This article argues that the concept of equivalence is one of the most important methodological aspects of valid and reliable measurement in cross-national survey research. The important topic of survey measure equivalence has not been systematically in Czech social science publications to date and this article hopes to address this gap in the literature. Consequently, the two main goals of this article are (1) to acquaint the reader with techniques that are used to find questions that are interpreted in the same way across countries before data collection and (2) to describe the testing and evaluation of measurement indicators’ equivalence or comparability after data collection. This study presents cognitive approaches to “good” question wording practices, best translation practices and the application of both ‘emic’ (culture specific) and ‘etic’ (culture universal) approaches to survey question design. After data collection a range of statistic techniques are usually employed ranging from basic statistics such as the mean to advanced approaches such as multi-group structural equation modelling, multilevel modelling, latent class modelling and Item Response Theory). This article describes some of these techniques in the context of measurement equivalence and its associated research literature.