Data Fabrication and Falsification: Protecting the Credibility and Impacts of Surveys

• Activity Number: 492 - Data Fabrication and Falsification: Protecting the Credibility and Impacts of Surveys
• Type: Invited
• Date/Time: Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
• Sponsor: Government Statistics Section
• Author(s): Linda J Young* and James Dahlhamer* and Jill DeMatteis *
• Companies: US Centers for Disease Control and Prevention and USDA National Agricultural Statistics Service and Westat
• Keywords: data fabrication; data falsification; surveys

Abstract

The fabrication and falsification of data by researchers and interviewers have the potential to pose serious threats to the credibility of survey research. Falsified data may yield biased estimates, affect the precision of estimates, and impact multivariate relationships. Institutions and organizations have, in many cases, developed their own protocols and procedures for preventing, detecting, investigating, and reporting on falsification, but as the leading professional organizations for those conducting survey research, the American Association for Public Opinion Research (AAPOR) and the American Statistical Association (ASA) jointly engaged a Task Force to make recommendations on best practices for the methods to be used for the prevention and detection of falsification in surveys. Basic findings of the Task Force will be presented, including types of survey data falsification; existing organizational guidelines, policies, and technical documents; approaches for prevention; tools for detection; impacts on analyses, recommendations for addressing it; and future research. An ASA representative will provide constructive criticism of the work.