ESRA 2027 sessions by theme

Back to Overview of Sessions

Session Details

Survey data collection and analysis generate a wealth of information about questionnaire quality — contact-center logs, paradata, response analyses, ad-hoc evaluation studies, and substantive analyses of the survey data itself. In practice, however, these sources are often scattered across the survey organization. This creates two recurring challenges: bringing the data together in a coherent way, and translating the resulting insights into meaningful, implemented improvements to the questionnaire or fieldwork procedures. Recent advances in AI and machine learning open up new possibilities here, for instance by making it easier to systematically analyze large volumes of open-ended respondent comments and feedback.

This session invites papers that address how to structurally monitor and evaluate questionnaire quality — conceptually, methodologically, or through applied case studies. We welcome contributions on, among others:
• frameworks and indicators for monitoring questionnaire and fieldwork quality;
• combining multiple sources — e.g. paradata, respondent comments, non-response reasons, break-off and log-in data — into coherent monitoring systems;
• the use of AI and machine learning to analyze respondent feedback and other monitoring data at scale;
• standardized evaluation instruments and reporting templates that support comparison across surveys and over time;
• embedding monitoring outcomes into questionnaire (re)design decisions and standard production processes;
• lessons learned from implementing monitoring or evaluation programs at national statistical institutes or other survey organizations.

We aim to bring together researchers and practitioners working on questionnaire quality monitoring across different survey types and organizations, to compare approaches and share practical lessons.