ABSTRACT
Social scientists use aggregate data to gain accurate knowledge of groups of persons or of institutions, such as Japanese voters, South American peasants, US teachers unions, or European parliaments. Data on the characteristics of an entire group of individual people or organizations are referred to as aggregate data. Two general categories of aggregate data are summative indicators, and syntality indicators. Data from each category are available on many different kinds of groups from a variety of sources. Most of the aggregate data available to social scientists are gathered for reasons unrelated to research. Six types of aggregate data are explained in roughly descending order of the extent to which they are likely to be valid and reliable. Six types of aggregate data are census data, organizational statistics, sample surveys, publications' content, event data, and judgmental data. Aggregate data analysts face the challenge of finding theoretically and methodologically justifiable ways of converting raw data into useful measures.
