Improving and Integrating Global Diversity Estimates Using Transparent Methods

University Of Illinois At Urbana-Champaign, Urbana IL

Investigators

Abstract

Understanding the socio-political impact of ethnic, religious, and linguistic diversity is a vital concern for both social scientists and policy-makers. Using several different datasets measuring diversity around the world, researchers have found that it often has a negative impact on democracy, development and political stability. However, these findings rely on fundamentally flawed datasets: their demographic estimates come from questionable sources and do not vary within countries or over time. This makes them ill-suited to studying outcomes like war and development, which often change rapidly and cluster in space. In addition, the existing datasets cannot be directly compared, making it difficult to assess their accuracy. Rather than investing time and money in the collection of new data, this project builds on an existing resource: 9 million survey responses from 175 countries around the world. By using Artificial Intelligence (AI) methods to compare these surveys to official statistics and generate improved diversity estimates, other researchers will be able to apply this method in other areas like health and inequality where government statistics are missing or questionable. Further, this project will make our results directly comparable to existing datasets. These data and methods will be made available through a user-friendly online portal, where scientists, policy-makers, and members of the public will be able to explore the data. They will also be able to create their own datasets and use visualization tools to see how the world's demographics are changing and consider what this means for our future. Existing estimates of ethnic, religious, and linguistic diversity are correlated cross-sectionally with a number of socio-political and economic outcomes including development, conflict, and social capital. Close examination of these data raises validity concerns: few are based on high-quality official statistics, the majority coming from questionable secondary sources. Further, criteria for group inclusion (i.e., ontologies) are opaque and inconsistently applied. Even where they appear accurate, data are static and aggregated at the country level, although they are often used to explain time-varying and spatially disaggregated outcomes. Ontologies in extant datasets are also incompatible, making comparison and integration difficult. This proposal improves existing measures by applying machine learning methods to compare 9 million responses across 175 countries with a new database of census results. An algorithm will identify survey design features that maximize accuracy, to define a compensatory weighting scheme across these features. The result is a set of survey-based demographic estimates with improved validity, even for countries lacking reliable census data. This method of triangulating surveys and official statistics is generalizable to research areas that use either source and can also inform improved survey design. The project will also develop tools for linking surveys, censuses, and existing datasets based on explicit and transparent decision rules to facilitate their comparison and integration. An online portal will provide access to datasets and code, supporting customized data manipulation and visualization. The methods and tools proposed here -- emphasizing accuracy, transparency, and cross-resource integration -- should serve as a model for future data collection. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.