Using integrated non-survey data for evaluating and correcting for non-response bias in surveys

Over the past decade, the landscape of survey data has substantially changed as response rates in probability-based surveys have seen a steady decline. Survey non-response can have a substantial impact on data quality, including the precision and reliability of survey estimates. The integration of non-survey data sources (i.e. administrative records, geospatial characteristics and digital trace data) can help to facilitate a more effective evaluation and correction of non-response bias in survey data.

This free workshop, delivered collaboratively by the Survey Futures Team (Strand 7) and the UK Data Service, explores the role of data integration in addressing non-response bias in social surveys. Presenters include Dr Thomas O’Toole, Professor Joe Sakshaug, and Dr Pierre Walthery.

This workshop is the second in a series of workshops on data integration. The recording of the first Data Integration Good Practice Workshop can be found on YouTube.

The workshop will provide:

• An understanding of the mechanisms which drive non-response bias.
• An overview of integrated data sources and methods for evaluating the implications of non-response bias on data quality and correcting for non-response biases.
• An assessment of the benefits and challenges of working with integrated survey-to-non-survey data to address non-response bias.
• How to find and access sources of integrated data.

Presentations on:

• Using integrated non-survey data for evaluating and correcting for non-response bias in surveys data, Dr Thomas O’Toole, The University of Manchester
• Evaluating the utility of linked administrative data for non-response bias adjustment in a piggyback longitudinal survey, Professor Joe Sakshaug, Institute for Employment Research (IAB) and LMU-Munich
• Integrated survey data curated by the UK Data Service: Overview and conditions of access, Dr Pierre Walthery, UK Data Service and The University of Manchester

By the end of the course participants will:

• Understand the background and reasoning for non-response evaluation and correction.
• Understand the characteristics of various sources of integrated survey and non-survey data, and how these can be used to evaluate and correct for non-response bias.
• Understand how and where to access sources of integrated survey and non-survey data.

This workshop is aimed at PhD students, post-doctoral researchers and lecturers, in addition to practitioners from survey agencies. No existing knowledge of data linkage or integration is needed but attendees may find watching the recording of the previous workshop useful.

This event will be livestreamed on our UK Data Service YouTube channel but the chat will be disabled. By registering and attending the Zoom event you will be able to ask questions and interact.

Recordings of UK Data Service events are made available on our YouTube channel and, together with the slides, on our past events pages soon after the event has taken place.