Gambling Survey for Great Britain: three gaps remain
"We conclude that the Gambling Commission has met six of our original nine recommendations." The Office for Statistics Regulation (OSR) wrote that on November 19, 2026, in its follow-up review of the Gambling Survey for Great Britain, the official statistics of the UK Gambling Commission (UKGC). Recommendations three, four and six are only partly met, and the OSR expects a public update by the end of February 2027.
Those three gaps govern a Gambling Survey for Great Britain figure. We read the follow-up on the OSR website. The review, requested by the Commission against the Code of Practice for Statistics, does not let an operator, a researcher or a journalist treat the open warnings as settled.
Six recommendations the Commission has closed
The OSR judged recommendations one, two, five, seven, eight and nine met. That is the public plan for Professor Patrick Sturgis's 2024 review, refreshed in July 2026, plus quality-assurance notes. The notes cover work with the Bingo Association and with GamStop on gaps between estimates and administrative records.
A user engagement statement, a statistics user group and a communications plan are in place. The dataset is on the UK Data Service. On April 9, 2026 a bingo check put past-four-week in-person participation at 1.2 percent in the survey and 1.0 percent in Bingo Association data. It does not close recommendation four. Health Survey for England and Adult Psychiatric Morbidity Survey files were still unavailable. The Commission has told the OSR it expects them by the end of 2026.
- February 2024: First Gambling Survey for Great Britain release.
- May 22, 2025: Nine recommendations, with a public response due that July.
- July 24, 2025: Commission response.
- August 14, 2025: Sturgis experiments published.
- October 2025: Gross-up caution removed from the guidance.
- April 9, 2026: Bingo report. Casino, pools and exchange checks still running.
- November 19, 2026: Recommendation 10 added. Dr Anna Price writes to Sarah Fox, copied to Helen Bryce, head of statistics, and Ben Haden, director of research and statistics.
Where the bias warning still falls short
Invitations to this push-to-web survey say the study is about gambling. Naming gambling in the 2025 experiments left the response rate unchanged and lifted reported participation by 4 percentage points. Participation can still run high.
The technical report states: "It should be kept in mind that the survey overestimates the true level of gambling in the population." The further response, updated in January 2026 and again in July 2026, says research found that "the risk of over estimation in the GSGB was not as high as initially thought", so no extra warning went into the release. A reader who stops at the release misses that line.
July 2026 added an interpretation note the OSR calls ambiguous: oversampling is a possibility, the interviewer effect a fact. Guidance revised in October 2025, then in July 2026, is plainer. Its Year 3, 2025 example says the Gambling Survey for Great Britain estimates that 2.4 percent of adults have a Problem Gambling Severity Index (PGSI) score of 8 or more. That is not a measure of addiction, and it should not be lined up with health surveys, including when the figure sits beside rules such as staged financial risk assessments.
What recommendation 10 asks the Commission to explain
Recommendation 10 is about explaining the Sturgis experiments. The OSR wants the purpose, the findings and the limits in plain words, and a clearer note on how that work changed the Commission's confidence.
The Commission's Sturgis page says self-completion "may encourage more honest reporting of gambling behaviours." The OSR says the experiments did not show that. A fairer line is that people may give fewer socially desirable answers. October 2025 guidance also dropped the bar on grossing PGSI estimates up to a population total. The findings agree the change "does not directly follow on from the research findings", and add that this "does not mean that the Gambling Commission’s decision was wrong", if users still call the results estimates.
Recommendation six stays open beside it. The OSR says the Commission should not park a challenge until an unpublished paper clears peer review. That stance delayed feedback. The rewritten text asks for updates on how user concerns are addressed, and recommendation four no longer carries a 2025 date. Professor Heather Wardle's health-survey comparison is preliminary. The OSR does not treat it as the benchmarking Sturgis asked for.
"We have not seen any evidence of an intention to deliberately mislead users about this research. However, the Commission should do more to explain, in its own words, the purpose of the research, its strengths and limitations, its findings, and how it has interpreted this information to make subsequent decisions related to the GSGB." (Office for Statistics Regulation)
This article is informational analysis only and is not gambling or financial advice. Figures are as attributed in the text.
18+Gambling carries financial risk and can be addictive. If you or someone you know needs help, visit GamCare (UK), call 1-800-GAMBLER (US), or see our Responsible Gambling page.





