Uses of Alternative Data Sources for Public Health Statistics and Policymaking: Challenges and Opportunities

• Activity Number: 231 - Uses of Alternative Data Sources for Federal Statistics
• Type: Topic Contributed
• Date/Time: Monday, July 30, 2018 : 2:00 PM to 3:50 PM
• Sponsor: Government Statistics Section
• Author(s): Zachary H Seeskin* and Felicia LeClere and Jaehoon Ahn and Joshua Williams
• Companies: NORC at the University of Chicago and NORC at the University of Chicago and NORC at the University of Chicago and Office of the Assistant Secretary for Planning and Evaluation
• Keywords: Data quality; Combining data from multiple sources; Administrative records; Electronic health records; Sensor data; Social media

Abstract

Alternative data sources beyond surveys and censuses are increasingly seen as a potential resource for health statistics and policy analysis. These non-traditional data sources can have advantages due to, among other factors, providing novel information, the speed of data collection, and increased geographic granularity. However, such data sources must be evaluated carefully to ensure that they meet the quality standards needed for policy analysis. While administrative records have been used successfully for some data products and analyses, the understanding of how to evaluate the quality of other alternative data sources, from electronic health records to data from environmental and health sensors to social media, is still maturing. The strengths and weaknesses of different alternative sources should guide whether and how they are applied. Researchers and analysts may look to alternative health data sources, for example, for new methods of analysis because the strength of timely data collection is more important than weaknesses of accuracy and reliability. In this paper, we examine the challenges and opportunities of using alternative data sources to answer policy-relevant questions in the context of public health policy by reviewing recent examples of such uses.