The use of multiple informants in public administration research: Data aggregation using organizational echelons

Abstract

Surveys are an important methodological tool in public management research. Multiple informant surveys are held to have considerable methodological advantages over elite surveys (the practice of surveying a top manager, e.g., a chief executive). Although in principle multiple informant surveys can provide a more accurate organizational picture, problems of data aggregation arise in practice. To promote better use of multiple informant surveys, this article reviews approaches to aggregating organizational data. It provides the first empirical test of echelon methods of data aggregation for public management research. We find significant differences between echelon aggregations, elite surveys and unstandardized forms of aggregations (e.g., a simple mean). These results support our argument that careful theoretical and empirical analysis of multiple informant surveys data is required to provide valid and reliable measures of organizational properties.