Introduction
This report describes the key technical features of the UK Public Survey of Risk Perception, Resilience and Preparedness 2025. It covers the following elements of technical survey delivery:
- This ‘Introduction’ covers the purpose of the project, and the supplier
- ‘Questionnaire design’ covers the process of designing the questionnaire
- ‘Sample design’ describes the approach taken to design the sample and conduct fieldwork
- ‘Data production’ describes the data processing methods used to assure the quality of the dataset
- ‘Weighting’ describes the weighting method employed, and the variables used
Savanta was commissioned to deliver the survey and obtained respondents from online panels. 10,536 respondents were interviewed online in a single wave, which took place between 11 March and 14 April 2025. During and after fieldwork, the data underwent quality assurance checks conducted by Savanta. Following fieldwork, final quality control checks were applied by UK Health Security Agency (UKHSA) analysts, prior to the data’s use and publication. All work was carried out in line with the ethical standards of the Market Research Society’s Code of Conduct.
Questionnaire design
The initial questionnaire was drafted by the Cabinet Office in collaboration with UKHSA and the Department for Environment, Food and Rural Affairs and shared with Savanta in February 2025. The questionnaire was then reviewed by representatives from national, local and devolved governments, to further develop the questions. A further review was undertaken by external experts including social and behavioural scientists who specialise in this topic. Each review resulted in updates to the questionnaire.
The questionnaire was designed so that it would take respondents a maximum of 20 minutes to answer. The median time taken by respondents to complete the survey was 13 minutes, 38 seconds.
The questionnaire itself was designed according to the Market Research Society’s Code of Conduct. Respondents were informed at the start of the questionnaire about the subject and purpose of the data collected. They were also informed that the questions they were about to answer may relate to potentially sensitive or distressing topics, and that they should feel free to pause or leave the survey should the questions make them feel uncomfortable. At the end of the survey respondents were also directed towards support services in case they had experienced any distress, and to websites where they might find further official information about preparing for emergencies.
Once survey design was complete, Savanta conducted 9 cognitive testing interviews in March 2025. The aim of cognitive testing was to examine how well respondents understood the survey questions, whether their answers were accurate and reasonable, and to assess whether any elements of the questionnaire might cause confusion or distress. Interviewees were asked for feedback at the end of the survey, where they uniformly found the survey to be informative and easy to complete. No interviewees reported experiencing any distress related to the questions or the survey topic.
Respondents for cognitive testing were recruited by Acumen Ltd. Quotas were applied to ensure the respondents came from a mix of age groups, genders, countries, social grades and ethnicities. Those interviewed fall into the following demographic categories.
Table 1.1. Number of cognitive testing respondents that fell into each of the following demographic categories
| Category |
Number of interviewees |
| Male - Age 18-34 |
2 |
| Male - Age 35-64 |
1 |
| Male - Age 65+ |
1 |
| Female - Age 18-34 |
2 |
| Female - Age 35-64 |
2 |
| Female - Age 65+ |
1 |
| England |
3 |
| Scotland |
1 |
| Wales |
2 |
| Northern Ireland |
3 |
| Social Grade AB |
3 |
| Social Grade C1 |
2 |
| Social Grade C2 |
2 |
| Social Grade DE |
2 |
| White British/Irish |
5 |
| Asian/Asian British |
1 |
| Black/Black British |
2 |
| Mixed/Other Ethnicity |
1 |
| Highest qualification: Degree |
2 |
| Highest qualification: A-Level |
4 |
| Highest qualification: GCSE |
3 |
All interviews were conducted online and recorded. During the interviews, respondents were asked to fill in the online version of the questionnaire, narrating their experience as they went, under supervision from a Savanta researcher.
Following completion of cognitive testing, the questionnaire was amended in line with findings from these initial interviews to ensure understanding of the questions and the response options. After the revised questionnaire received sign off from the Cabinet Office, it was live trialled in March 2025 with 813 respondents as part of Savanta’s standard ‘soft launch’ procedure, to test that all questions in the survey were answered as intended. At this point no changes were identified as needing to be made, and the survey was fully launched.
Sample design and limitations
One purpose of the UK Public Survey of Risk Perception, Resilience and Preparedness was to provide robust data for each of the UK’s constituent nations. To ensure this was the case, respondents from Scotland, Wales and Northern Ireland were oversampled during fieldwork, to ensure enough participants were recruited in these areas for the analysis to be robust. The targets were to recruit 1,500 people living in Scotland, and 1,000 living in Wales and Northern Ireland respectively. These results have been provided in separate data tables. For the UK-level analysis, weights have been used to adjust for the oversampling and ensure the results are representative of the UK adult population.
The method of data collection used in the survey was Computer Assisted Web Interviews (CAWI). Respondents were recruited using the Savanta Hub API from multiple MRS-member and/or ESOMAR-accredited online panel providers. Each panel has their own procedures for recruiting people, which can include: direct recruitment from telephone research, face-to-face recruitment after completing on-street or in-home interviews, referrals from existing panellists, direct sign-ups on the panel website, targeting specific online communities, and recruiting via social media and mobile advertisements. To aid survey completion and engagement, the Savanta survey platform is designed to be accessible, with screen-reading and other accessibility features built in to ensure a good respondent experience for common disabilities such as visual impairments, hearing impairments and motor impairments. Respondents who completed the survey were rewarded with incentives as is normal practice in panel-based surveys. The value of these incentives varied over time, and according to whether or not the respondent was included in a quota boost sample plan. Given this high variation in incentives paid, it is not possible to report at an individual level how much each respondent was paid, but the amounts fell within the range of £0.15 - £6.50.
Using online access panels to recruit respondents has many advantages. It is a particularly efficient means of gathering survey data, allowing for the recruitment of large samples at speed and at low cost. It also reduces social desirability bias, as there is no interviewer present to shape responses. However, recruiting a sample from online panels does carry a risk of nonresponse bias. This is when estimates taken from a survey do not accurately reflect the true opinions of the population, due to the survey sample differing markedly in composition from the population (in this case people aged 18+ and living in the UK). Certain nonresponse bias is unavoidable. For example, people without access to the internet will not be part of an online access panel. However, according to latest research from Ofcom, 98% of all residential properties in the UK currently have access to superfast broadband coverage[footnote 1].
One other limitation emerged in the number of people recruited to the survey who report having no qualifications. Looking at the combined results of the 2021 ONS Census (covering England and Wales), Scotland’s Census, and the 2021 NISRA Census (covering Northern Ireland), 18% of the UK population reported having no qualifications. In the survey 1% of people reported having ‘no formal education’. However, the starkness of this difference may be at least partially driven by a difference in question wording. The questionnaire asked respondents ‘What is the highest educational level that you have achieved to date?’ The 2021 England and Wales census (for example) asked two questions to gather similar data: ‘Have you achieved a qualification at degree level or above’ and ‘Have you achieved any other qualifications?’. The response options offered at both questions are very similar however, with the same qualifications being mentioned at both questions, so it seems unlikely that differences in wording would heavily change responses. Future versions of this survey could investigate this issue by directly replicating the language of the census, thereby assessing whether the issue is one of language, or of skew in the panels.
Steps were taken to address nonresponse bias in the sample, through the application of quotas. Using data from a range of official sources (listed below) the proportion of the population that lives in each constituent nation of the UK, is aged 18 and over, and falls into a set of different demographic categories, was calculated. This was done for each constituent nation to ensure the final sample was representative at constituent-country level. These proportions were then applied to the planned sample size for each constituent nation, to calculate how many people in each category should be recruited. During fieldwork the number of people recruited in each of these groups was monitored, with the goal of ensuring that the final number of respondents fell between 90 and 120% of quota. On some occasions there was a choice to be made as to whether to allow a particular demographic group to be under-sampled, or, in correcting that under-sampling, oversample other groups. In these instances, it was decided to over-sample and down-weight rather than under-sample and upweight respondents. As such some demographic groups are over 120% of quota. For categories of people where regular fieldwork fell below quota, boost plans were used. This meant creating routes to the survey that advertised and screened for people in specific demographics, and that offered higher incentives for survey completion, increasing outreach to these underrepresented groups.
Quotas were set for the following characteristics. Population statistics used for the quotas were sourced from the ONS Mid-Year Population Estimates and the England & Wales, Northern Ireland and Scotland Censuses.
- Age and gender (interlocked)
- Region
- Ethnicity
- Social grade
- Religion or religion brought up in (Northern Ireland only)
In addition to these, a balancing quota was set on education, to monitor proportion of respondents in the sample with and without an undergraduate degree (or equivalent qualification). Region quotas and weights for Scotland, Wales and Northern Ireland were created by aggregating Council Areas, Unitary Authorities and Local Government Districts respectively. As all respondents needed to be assigned to a quota, it was necessary to exclude respondents who reported that they did not know the name of their Local Authority (identified in all cases as ‘the body that collects your bins’). For consistency, respondents in England who did not know their Local Authority were also excluded.
The choice of what region to quota in Scotland changed during fieldwork. At the start of fieldwork, it was agreed that quotas would be set on regions based on Scottish Parliamentary regions. Respondents were asked “Which part of Scotland do you live in?” and presented with a list of regions based on the eight Scottish Parliamentary regions and their response was used to allocate them to a region. Over the course of fieldwork, a substantial proportion of respondents who stated that they lived in council areas within the South Scotland Scottish Parliamentary region (in particular those in East and South Ayrshire), assigned themselves incorrectly to the West of Scotland region. Following consultation with Scottish Government analysts, it was decided to switch to using a region variable that aggregated council areas for quotas and weights, on the basis that people were more likely to assign themselves to a region accurately if presented with a more specific geographic area.
A comparison of quotas applied and the demographic balance of the dataset is provided below in the following four tables, showing the number of respondents in each quota recruited from each part of the United Kingdom.
Table 2.1. Target quotas and sample achieved in each demographic category in England
Gender / Age
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Male x 18-24 |
350 |
358 |
102% |
| Male x 25-34 |
543 |
575 |
106% |
| Male x 35-44 |
533 |
554 |
104% |
| Male x 45-54 |
507 |
500 |
99% |
| Male x 55-64 |
512 |
562 |
110% |
| Male x 65+ |
704 |
719 |
102% |
| Female x 18-24 |
334 |
341 |
102% |
| Female x 25-34 |
565 |
581 |
103% |
| Female x 35-44 |
567 |
586 |
103% |
| Female x 45-54 |
524 |
574 |
110% |
| Female x 55-64 |
532 |
524 |
99% |
| Female x 65+ |
830 |
838 |
101% |
Region
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| North-West |
854 |
923 |
108% |
| North-East |
310 |
335 |
108% |
| Yorkshire & Humberside |
630 |
682 |
108% |
| West Midlands |
677 |
685 |
101% |
| East Midlands |
565 |
587 |
104% |
| South-West |
670 |
700 |
104% |
| South-East |
1066 |
1106 |
104% |
| Eastern |
726 |
739 |
102% |
| London |
1002 |
970 |
97% |
Ethnicity
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| White |
5414 |
5608 |
104% |
| Mixed |
126 |
144 |
114% |
| Asian |
578 |
593 |
103% |
| Black |
249 |
269 |
108% |
| Other |
133 |
114 |
86% |
Approximated social grade
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| AB |
1516 |
1649 |
109% |
| C1 |
2185 |
2150 |
98% |
| C2 |
1386 |
1371 |
99% |
| DE |
1413 |
1557 |
110% |
Highest qualification
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Degree |
2266 |
2963 |
131% |
| Below degree |
4234 |
3764 |
89% |
Total
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Total |
6,500 |
6,727 |
103% |
Table 2.2. Target quotas and number of respondents recruited in each demographic category in Wales
Gender / Age
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Male x 18-24 |
55 |
53 |
97% |
| Male x 25-34 |
76 |
74 |
97% |
| Male x 35-44 |
74 |
89 |
120% |
| Male x 45-54 |
73 |
80 |
109% |
| Male x 55-64 |
83 |
92 |
111% |
| Male x 65+ |
124 |
128 |
103% |
| Female x 18-24 |
50 |
53 |
106% |
| Female x 25-34 |
78 |
82 |
105% |
| Female x 35-44 |
78 |
84 |
108% |
| Female x 45-54 |
77 |
85 |
110% |
| Female x 55-64 |
88 |
97 |
111% |
| Female x 65+ |
144 |
134 |
93% |
Region
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Mid and West Wales |
206 |
222 |
108% |
| North Wales |
181 |
199 |
110% |
| South Wales Central |
238 |
238 |
100% |
| South Wales East |
204 |
219 |
107% |
| South Wales West |
170 |
176 |
104% |
Ethnicity
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| White |
947 |
1000 |
106% |
| Ethnic minority (excluding white minorities) |
53 |
54 |
103% |
Approximated social grade
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| AB |
195 |
211 |
108% |
| C1 |
336 |
347 |
103% |
| C2 |
230 |
232 |
101% |
| DE |
238 |
264 |
111% |
Highest qualification
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Degree |
324 |
456 |
141% |
| Below degree |
676 |
598 |
88% |
Total
| Level |
Quota count |
Respondents recruited |
% of Quota recruited |
| Total |
1,000 |
1,054 |
105% |
Table 2.3. Target quotas and number of respondents recruited in each demographic category in Scotland
Gender / Age
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| Male x 18-24 |
78 |
73 |
93% |
| Male x 25-34 |
116 |
131 |
113% |
| Male x 35-44 |
115 |
132 |
115% |
| Male x 45-54 |
113 |
132 |
117% |
| Male x 55-64 |
128 |
153 |
120% |
| Male x 65+ |
170 |
181 |
106% |
| Female x 18-24 |
78 |
87 |
111% |
| Female x 25-34 |
120 |
141 |
117% |
| Female x 35-44 |
121 |
141 |
117% |
| Female x 45-54 |
120 |
147 |
122% |
| Female x 55-64 |
136 |
162 |
119% |
| Female x 65+ |
204 |
182 |
89% |
Region
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| North Eastern Scotland |
133 |
148 |
111% |
| Highlands And Islands |
135 |
154 |
114% |
| Eastern Scotland |
551 |
624 |
113% |
| West Central Scotland |
419 |
398 |
95% |
| Southern Scotland |
263 |
347 |
132% |
Ethnicity
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| White |
1408 |
1578 |
112% |
| Ethnic minority (excluding white minorities) |
92 |
93 |
101% |
Approximated social grade (Scotland calculation)
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| AB |
353 |
445 |
126% |
| C1 |
344 |
440 |
128% |
| C2 |
147 |
178 |
121% |
| DE |
656 |
608 |
93% |
Highest qualification | Degree
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| 712 |
767 |
108% |
|
| Below degree |
788 |
904 |
115% |
Total
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
|
| Total |
Total |
1,500 |
1,671 |
111% |
Table 2.4. Target quotas and number of respondents recruited in each demographic category in Northern Ireland
Gender
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| Male x 18-24 |
53 |
55 |
104% |
| Male x 25-34 |
80 |
92 |
114% |
| Male x 35-44 |
83 |
96 |
115% |
| Male x 45-54 |
82 |
96 |
117% |
| Male x 55-64 |
82 |
95 |
116% |
| Male x 65+ |
105 |
121 |
115% |
| Female x 18-24 |
49 |
47 |
96% |
| Female x 25-34 |
83 |
77 |
93% |
| Female x 35-44 |
89 |
80 |
90% |
| Female x 45-54 |
86 |
107 |
125% |
| Female x 55-64 |
86 |
103 |
120% |
| Female x 65+ |
122 |
114 |
93% |
Region
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| East |
505 |
606 |
120% |
| South |
206 |
197 |
96% |
| North |
153 |
152 |
99% |
| West |
137 |
129 |
94% |
Ethnicity
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| White |
970 |
1060 |
109% |
| Ethnic minority (excluding white minorities) |
30 |
24 |
80% |
Approximated social grade
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| AB |
200 |
207 |
103% |
| C1 |
305 |
337 |
111% |
| C2 |
232 |
206 |
89% |
| DE |
262 |
334 |
127% |
Religion or Religion brought up in
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| Catholic |
448 |
521 |
116% |
| Protestant and Other Christian |
465 |
493 |
106% |
| Other religion/None |
15 |
70 |
80% |
Highest qualification
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
| Degree |
331 |
327 |
99% |
| Below degree |
669 |
757 |
113% |
Total
| Level |
Quota Count |
Respondents recruited |
% of Quota Recruited |
|
| Total |
Total |
1,000 |
1,084 |
108% |
Data processing
To ensure the data collected as part of this project was always of the highest quality, all survey data went through several stages of quality assurance (QA) with automated cleaning processes used where appropriate.
Pre-processing checks
Using their in-house survey platform, Savanta automatically removed the following:
- Respondents who took 33% or less of the median time to answer a question, on 40% of questions.
- Respondents who took 33% or less of the median time to answer the survey as a whole
- Respondents who gave the same answer to 66% of the ‘scale’ questions used in the survey.
- Respondents flagged as potentially fraudulent by RelevantID. RelevantID is an industry standard tool that uses a variety of respondent metadata (e.g. the respondent’s browser, operating system and location) to create a ‘machine fingerprint’ to determine the likelihood of a respondent taking the same survey on multiple occasions. It then provides both a ‘dupe’ (duplicate) score and a fraud profile score. Scores above particular levels cause the associated respondent to be shadow banned from taking part in future surveys.
Savanta then reviewed the data collected in Excel, and removed respondents according to the following criteria:
- The respondents that did not write the word ‘blue’ (or a close misspelling, such as ‘bluu, bluey’ etc.) in response to the question COLOUR_TRAP (“Please write ‘blue’ in the box below. This is a quality check to test attention”)
- The respondents whose stated age differed from their age as calculated using their stated year of birth, by 4 or more years
- The respondents whose stated ITL1 Region did not match at least one of the possible ITL1 Regions calculated using the first half (outward code) of their postcode
- The respondents whose postcode outward code was not a ‘live’ code in the November 2024 ONS Postcode Directory
- Respondents in Scotland, whose Council Area could not plausibly overlap with the broad area of Scotland they reported living in (Scotland only)
- The respondents who were below the age of 65 but claimed they were in receipt of a state pension
- The respondents who were below the age of 55 but claimed they were in receipt of a private pension
- The respondents who said they had children aged 0-17 living in their household at CHILDREN_AGE, but reported having no children aged 0-17 living in their household at HOUSEHOLD
Northern Ireland
In order to collect a representative sample of around 1,000 people in Northern Ireland, Savanta both recruited respondents via the Savanta Hub API, and contracted a local specialist company (LucidTalk) to obtain additional respondents. The resulting combined sample was both too large, and demographically skewed to be included in the database directly. To adjust for this, Savanta extracted a more demographically representative sub-sample from this total in the following way:
Using the R programming language, a small random sample of respondents was selected from the combined Savanta/LucidTalk sample. Respondents were then selected to be included in the new sub-sample, according to what quotas needed to be filled. This process was automatically repeated until all quotas were filled as much as was possible, without overfilling any of them. Overfilling was defined as the demographic group’s proportion in the sample exceeding 120% of their proportion in the population. The R code used to select the sample can be shared on request.
Post-collection data processing
Further QA checks were performed by UKHSA in relation to question routing and response quality. This resulted in the removal of additional data:
- Responses for Q24b_3 (‘Have you done any of the following in the last 12 months: Talked to your children about what happens in an emergency, or what they should do if they are involved in one’) for respondents who said ‘prefer not to say’ for CHILDREN
- Respondents with inconsistent responses between Q26_3/26_4 (‘Which of the following items, if any, do you have at home: Baby formula to last 3 days/7 days’) and Q29 (Approximately how many days’ worth of baby formula do you have at home’).
Weighting
Weighting was applied to the final results to ensure the demographic profile of the sample matched both the adult (18+) UK population and, for country-level tables, the adult (18+) population of England, Scotland, Wales and Northern Ireland.
Weights are values that cause individual respondents to count for more, or less, depending on whether their demographics are underrepresented or overrepresented in the sample relative to the target population. For example, if the survey sample is 50% men, but the UK population is 48% men, men in the survey sample would be underweighted so that they would comprise 48% of the weighted sample.
Savanta used RIM weighting, also known as raking, to calculate the survey weights. This method iteratively adjusts the proportions in the sample for each variable in a list, until they match the target proportions. The list of variables used in the UK and country-level weighting schemes are shown in the table below, alongside the relevant proportions. The data sources used to construct these weights are listed in Section 6 of this report.
Table 3.1. The impact of the UK weighting scheme
Gender / Age
| Level |
Unweighted proportion |
Weighted proportion |
| Male x 18-24 |
5.1% |
5.4% |
| Male x 25-34 |
8.3% |
8.3% |
| Male x 35-44 |
8.3% |
8.1% |
| Male x 45-54 |
7.7% |
7.8% |
| Male x 55-64 |
8.6% |
8.0% |
| Male x 65+ |
10.9% |
10.9% |
| Female x 18-24 |
5.0% |
5.1% |
| Female x 25-34 |
8.4% |
8.6% |
| Female x 35-44 |
8.5% |
8.6% |
| Female x 45-54 |
8.7% |
8.0% |
| Female x 55-64 |
8.4% |
8.3% |
| Female x 65+ |
12.0% |
12.9% |
Region
| Level |
Unweighted proportion |
Weighted proportion |
| Northern Ireland |
10.3% |
2.7% |
| Scotland |
15.9% |
8.4% |
| North-West |
8.8% |
11.1% |
| North-East |
3.2% |
4.0% |
| Yorkshire & Humberside |
6.5% |
8.2% |
| Wales |
10.0% |
4.7% |
| West Midlands |
6.5% |
8.8% |
| East Midlands |
5.6% |
7.3% |
| South-West |
6.6% |
8.7% |
| South-East |
10.5% |
13.8% |
| Eastern |
7.0% |
9.4% |
| London |
9.2% |
13.0% |
Ethnicity
| Level |
Unweighted proportion |
Weighted proportion |
| White |
87.8% |
85.0% |
| Mixed |
1.8% |
1.8% |
| Asian |
6.1% |
8.0% |
| Black |
3.2% |
3.4% |
| Other |
1.2% |
1.8% |
Approximated social grade
| Level |
Unweighted proportion |
Weighted proportion |
| AB |
23.8% |
23.0% |
| C1 |
31.1% |
32.4% |
| C2 |
18.9% |
20.2% |
| DE |
26.2% |
24.4% |
Table 3.2. The impact of the England weighting scheme
Gender / Age
| Level |
Unweighted proportion |
Weighted proportion |
| Male x 18-24 |
5.3% |
5.4% |
| Male x 25-34 |
8.5% |
8.4% |
| Male x 35-44 |
8.2% |
8.2% |
| Male x 45-54 |
7.4% |
7.8% |
| Male x 55-64 |
8.4% |
7.9% |
| Male x 65+ |
10.7% |
10.8% |
| Female x 18-24 |
5.1% |
5.1% |
| Female x 25-34 |
8.6% |
8.7% |
| Female x 35-44 |
8.7% |
8.7% |
| Female x 45-54 |
8.5% |
8.1% |
| Female x 55-64 |
7.8% |
8.1% |
| Female x 65+ |
12.5% |
12.8% |
Region
| Level |
Unweighted proportion |
Weighted proportion |
| North-West |
13.7% |
13.1% |
| North-East |
5.0% |
4.8% |
| Yorkshire & Humberside |
10.1% |
9.7% |
| West Midlands |
10.2% |
10.4% |
| East Midlands |
8.7% |
8.7% |
| South-West |
10.4% |
10.3% |
| South-East |
16.4% |
16.4% |
| Eastern |
11.0% |
11.2% |
| London |
14.4% |
15.4% |
Ethnicity
| Level |
Unweighted proportion |
Weighted proportion |
| White |
83.4% |
83.4% |
| Mixed |
2.1% |
1.9% |
| Asian |
8.8% |
8.9% |
| Black |
4.0% |
3.8% |
| Other |
1.7% |
2.0% |
Approximated social grade
| Level |
Unweighted proportion |
Weighted proportion |
| AB |
24.5% |
23.3% |
| C1 |
32.0% |
33.7% |
| C2 |
20.4% |
21.3% |
| DE |
23.1% |
21.7% |
Table 3.3. The impact of the Wales weighting scheme
Gender / Age
| Level |
Unweighted proportion |
Weighted proportion |
| Male x 18-24 |
5.0% |
5.5% |
| Male x 25-34 |
7.0% |
7.6% |
| Male x 35-44 |
8.4% |
7.4% |
| Male x 45-54 |
7.6% |
7.3% |
| Male x 55-64 |
8.7% |
8.3% |
| Male x 65+ |
12.1% |
12.4% |
| Female x 18-24 |
5.0% |
5.0% |
| Female x 25-34 |
7.8% |
7.8% |
| Female x 35-44 |
8.0% |
7.8% |
| Female x 45-54 |
8.1% |
7.7% |
| Female x 55-64 |
9.2% |
8.8% |
| Female x 65+ |
12.7% |
14.4% |
Region
| Level |
Unweighted proportion |
Weighted proportion |
| Mid and West Wales |
21.1% |
20.7% |
| North Wales |
18.9% |
18.1% |
| South Wales Central |
22.6% |
23.8% |
| South Wales East |
20.8% |
20.3% |
| South Wales West |
16.7% |
17.0% |
Ethnicity
| Level |
Unweighted proportion |
Weighted proportion |
| White |
94.9% |
94.7% |
| Ethnic minority (excluding white minorities) |
5.1% |
5.3% |
Approximated social grade
| Level |
Unweighted proportion |
Weighted proportion |
| AB |
20.0% |
19.4% |
| C1 |
32.9% |
33.7% |
| C2 |
22.0% |
23.0% |
| DE |
25.0% |
23.8% |
Table 3.4. The impact of the Scotland weighting scheme
Gender / Age
| Level |
Unweighted proportion |
Weighted proportion |
| Male x 18-24 |
4.4% |
5.2% |
| Male x 25-34 |
7.8% |
7.7% |
| Male x 35-44 |
7.9% |
7.7% |
| Male x 45-54 |
7.9% |
7.5% |
| Male x 55-64 |
9.2% |
8.5% |
| Male x 65+ |
10.8% |
11.3% |
| Female x 18-24 |
5.2% |
5.2% |
| Female x 25-34 |
8.4% |
8.0% |
| Female x 35-44 |
8.4% |
8.1% |
| Female x 45-54 |
8.8% |
8.0% |
| Female x 55-64 |
9.7% |
9.1% |
| Female x 65+ |
10.9% |
13.5% |
Region
| Level |
Unweighted proportion |
Weighted proportion |
| North Eastern Scotland |
8.9% |
9.0% |
| Highlands And Islands |
9.2% |
9.0% |
| Eastern Scotland |
37.3% |
36.7% |
| West Central Scotland |
23.8% |
27.9% |
| Southern Scotland |
20.8% |
17.4% |
Ethnicity
| Level |
Unweighted proportion |
Weighted proportion |
| White |
94.4% |
93.9% |
| Ethnic minority (excluding white minorities) |
5.6% |
6.1% |
Approximated social grade
| Level |
Unweighted proportion |
Weighted proportion |
| AB |
26.6% |
23.5% |
| C1 |
26.3% |
22.9% |
| C2 |
10.7% |
9.7% |
| DE |
36.4% |
43.8% |
Table 3.5. The impact of the Northern Ireland weighting scheme
Gender / Age
| Level |
Unweighted proportion |
Weighted proportion |
| Male x 18-24 |
5.1% |
5.2% |
| Male x 25-34 |
8.5% |
8.0% |
| Male x 35-44 |
8.9% |
8.4% |
| Male x 45-54 |
8.9% |
8.1% |
| Male x 55-64 |
8.8% |
8.2% |
| Male x 65+ |
11.2% |
10.7% |
| Female x 18-24 |
4.3% |
4.8% |
| Female x 25-34 |
7.1% |
8.1% |
| Female x 35-44 |
7.4% |
9.0% |
| Female x 45-54 |
9.9% |
8.4% |
| Female x 55-64 |
9.5% |
8.6% |
| Female x 65+ |
10.5% |
12.4% |
Region
| Level |
Unweighted proportion |
Weighted proportion |
| East |
55.9% |
50.5% |
| South |
18.2% |
20.7% |
| North |
14.0% |
15.2% |
| West |
11.9% |
13.6% |
Ethnicity
| Level |
Unweighted proportion |
Weighted proportion |
| White |
97.8% |
97.0% |
| Ethnic minority (excluding white minorities) |
2.2% |
3.0% |
Approximated social grade
| Level |
Unweighted proportion |
Weighted proportion |
| AB |
19.1% |
20.0% |
| C1 |
31.1% |
30.5% |
| C2 |
19.0% |
23.2% |
| DE |
30.8% |
26.3% |
Religion or religion brought up in
| Level |
Unweighted proportion |
Weighted proportion |
| Roman Catholic |
48.1% |
44.8% |
| Protestant and Other Christian |
45.5% |
46.5% |
| Other religion/None |
6.5% |
8.8% |
Approximated social grade
Social grade is a ‘common currency’ socio-economic classification of people, developed by the Market Research Society and commonly used in advertising and market research. The classification groups people according to the occupation and employment status of their household’s Chief Income Earner, defined as the individual in the household that earns or earned the highest salary.
An approximate count of people in each social grade, based on the characteristics of their Household Reference Person, has traditionally been produced using data from the census. This has been done using the 2021 census by the ONS for England and Wales, and by NISRA for Northern Ireland. However, at the time this research was conducted, there was no similar work done using the 2022 Scotland census. On the advice of Scottish analysts, Savanta instead assigned respondents in Scotland to a social grade based on their personal occupation and employment activity, rather than that of their HRP. A table showing how social grades were matched to different combinations of occupation and employment activity for Scottish respondents is available on request.
Devolved government regions
For UK and England weights, respondents were assigned to an ITL1 region based on their own self-reported residence (validated using their postcode). For Wales weights, respondents were assigned to Senedd Cymru Electoral Regions based on their Unitary Authorities. However, for Scotland and Northern Ireland, there are no similarly official regions that respondents can be easily assigned to. As such, in Northern Ireland, Savanta grouped Local Government Districts based on their location into four regions named North, South, East and West. In Scotland, Savanta grouped Council Areas into five regions based on old NUTS2 regions, named North Eastern Scotland, Highlands and Islands, Eastern Scotland, West Central Scotland, and Southern Scotland. A table showing how Local Authorities were matched to regions in Northern Ireland and Scotland is available on request.
Annex: Source data
Unless otherwise specified, the data sources below were used to create both quotas and weights. A different data source was used for Northern Ireland’s age by gender and region weights, than was used for Northern Ireland’s age by gender and region quotas. This was done in order to make use of the most up-to-date data, as NISRA released new population estimates for Northern Ireland Local Government Districts on 29 May 2025.UK ethnicity, social grade and education statistics were created by aggregating the results from the following three Censuses:
- 2021 ONS Census. This covers England and Wales and was conducted in 2021 by the Office for National Statistics.
- Scotland’s Census. This was conducted in 2022 by the National Records of Scotland.
- 2021 NISRA Census. This covers Northern Ireland and was conducted in 2021 by the Northern Ireland Statistics and Research Agency.
Age by gender
Region
Ethnicity
Approximated social grade
For England, Wales and Northern Ireland, the population used is ‘all usual residents in households’, not the household reference person.
Education quotas
