Survey Improvements
Gambling Survey for Great Britain Continuous Improvement: Implementing the recommendations from Professor Sturgis
In line with best practice the Gambling Commission will continue to refine and improve the Gambling Survey for Great Britain (GSGB).
In February 2024, Professor Sturgis published an independent review of the GSGB. The independent review (opens new tab) assessed the GSGB’s methodological approach and made recommendations for improvements to ensure the quality and robustness of the statistics continue to build stakeholder and public confidence. The recommendations focus on how the Gambling Commission should address unresolved issues relating to how the shift to self-completion has affected estimates of gambling behaviours.
We have outlined how we plan to address each of these recommendations. Recommendations 1 to 4 were considered by Professor Sturgis to be the highest priority, whilst recommendations 5 to 7 were for longer term implementation and to some extent, dependent on circumstances outside of the Commission’s control.
Recommendation 1: The Commission should conduct research to better understand the relationship between survey topic and the propensity of gamblers to respond to survey invitations.
How we will implement the recommendation
Given the high priority of this recommendation and the need for independence in the methodological development work, we will be issuing an Invitation to Tender to invite external organisations to undertake this research on our behalf.
Delivery
An external supplier working with the Gambling Commission.
Timescales
We will issue an Invitation to Tender by September 2024.
Recommendation 2: The Gambling Commission should undertake additional research to better understand the role of socially desirable responding as the driver of the difference in gambling estimates between in-person and self-completion surveys.
How we will implement the recommendation
Given the high priority of this recommendation and the need for independence in the methodological development work, we will be issuing an Invitation to Tender to invite external organisations to undertake this research on our behalf.
Delivery
An external supplier working with the Gambling Commission.
Timescales
We will issue an Invitation to Tender by September 2024.
Recommendation 3: The Gambling Commission should undertake a randomised experiment to evaluate the effect of the updated list of gambling activities on estimates of gambling prevalence and harm.
How we will implement the recommendation
We conducted an initial experiment using the YouGov panel. We undertook a split sample experiment with approximately 2,000 panelists with half of the sample receiving the Health Survey for England gambling participation list to ask about gambling in the past 12 months followed by the Problem Gambling Severity Index (PGSI) and the other half receiving the GSGB participation question followed by the PGSI.
Initial findings show that the percentage of people who had gambled in the past 12 months was similar for those who answered the Health Survey activity list and those who answered the GSGB activity list. There were also no significant differences in PGSI scores between the two groups. We plan to conduct further analysis to compare estimates of online and in-person gambling between the Health Survey and GSGB activity lists. Findings from this analysis will be published August 2024.
Importantly, our analysis is limited by the relatively low sample size (2,000 panelists in total) and so we intend to include this recommendation within the Invitation to Tender to explore the findings in more detail with a larger sample.
Delivery
The Gambling Commission and an external supplier.
Timescales
Questions were added to the YouGov panel in March 2024, with the results to be published August in 2024.
We will issue an Invitation to Tender by September 2024.
Recommendation 4: The Gambling Commission should take steps to assess the extent of potential bias in the subset of questions administered to online respondents only.
How we will implement the recommendation
In 2024 to 2025 we will conduct further analysis of the GSGB findings by mode to understand the differences in responses between those respondents answering on paper compared to those answering online.
In designing the 2025 GSGB survey, we will also consider including an online only question on the paper version of the survey to assess the difference in responses.
Delivery
The Gambling Commission.
Timescales
2024 to 2025
Recommendation 5: The Gambling Commission should continue to monitor best practice developments in the area of within household selection of adults in push-to-web surveys.
How we will implement the recommendation
We will engage with our research supplier, National Centre (NatCen) for Social Social Research to explore any best practice developments around household selection. We will conduct our own desk research in this area and we will engage with other official statistics producers and research groups in this area through our existing networks.
Delivery
The Gambling Commission and NatCen Social Research.
Timescales
Ongoing.
Recommendation 6: The Gambling Commission should carry out research on the prevalence of gambling and gambling harm in groups that are excluded from the GSGB because they are not included on the sampling frame.
How we will implement the recommendation
Our Evidence gaps and priorities 2023-2026 outlines areas of interest and focus for research, with one theme specifically aimed at gambling related harms and vulnerability.
We have a Consumer Voice programme with whom we can undertake research with specific consumer groups, who may be excluded from the GSGB as well as learning from our expert groups and taking on board findings from other external research in this space.
Delivery
The Gambling Commission.
Timescales
Ongoing through evidence gaps and priorities 2023 to 2026.
Recommendation 7: The Gambling Commission should seek opportunities to benchmark the estimates from the GSGB against a contemporaneous face-to-face interview survey in the future.
How we will implement the recommendation
This would be unaffordable to do as a standalone data collection exercise.
There may be an opportunity to benchmark a few questions via a Health Survey if the Health Survey continues with its face to face methodology, or via the Adult Psychiatric Morbidity Survey (APMS), although this may take several years for results to be available. It is also not certain that we would be able to place questions on these surveys and there will be a further cost implication.
We will consider value for money if the opportunity becomes available.
Delivery
Unknown.
Timescales
Unknown.
Last updated: 25 July 2024
Show updates to this content
No changes to show.