Measuring Social Capital with Aggregated Indicators: A Case of Ecological Fallacy?

Social capital has become a highly successful concept in social science despite widely perceived shortcomings in conceptualization and operationalization. The latter is frequently performed as a principal component analysis of individual survey data with subsequent aggregation to regional or national levels. The central focus of this paper is the interpretation of the diverging correlations observed between the dimensions elaborated on an individual and an aggregate level. We illustrate that the correlations of regionally aggregated components are the result of an improper application of a single-level model to a multilevel structure. This mechanism is demonstrated empirically by adopting results from the European Social Survey and elaborating dimensions of social capital from both individual and aggregate survey data for European regions. The findings clearly indicate that the observed ecological correlations are not simply spurious or inconsistent due to an ecological fallacy condition, but rather reflect the influence of regional driving forces. Researchers need to be more careful in taking account of the multilevel nature of the data in order to produce valid results. In fact, the often applied procedure of individual factorization and subsequent aggregation of data provides a mixture of the two level effects with potentially misleading implications.