The Scottish Health Survey 2025 - Volume 2: Technical Report
This publication presents information on the methodology and fieldwork from the Scottish Health Survey 2025.
1.2 Sample design
Requirements
The sample specification for the 2025 SHeS was designed by the Scottish Government. The design was coordinated with the designs for the Scottish Household Survey (SHS) and the Scottish Crime and Justice Survey (SCJS) to improve survey efficiency and to allow the samples of the three surveys to be pooled for further analysis[1].
There were two elements to the SHeS sample in 2025:
- Main sample - to allow annual reporting of Scotland level results and results at Health Board and local authority level for adults using the 2022, 2023, 2024 and 2025 data combined. This required an annual interview target of 5,112 adults for Scotland as a whole and a minimum target of 125 for each local authority. There were additional targets of 1,000 adults to complete each biological measure and 1,026 child interviews.
- Child boost sample – overall there was a requirement for 2,031 child interviews for Scotland. As the main sample was only expected to yield 1,026 child interviews, a further 1,005 interviews were required from a separate boost sample.
Sample design and assumptions
In 2025, the sample utilised a two-stage clustered sample design, with intermediate geographies randomly selected at the first stage and address points at the second stage. With the exception of Orkney, Shetland and Na h-Eileanan Siar councils, the sample was clustered by intermediate geographies (IG) with one quarter of IGs selected for each year of fieldwork. In Orkney, Shetland and Na h-Eileanan Siar the sample was clustered by data zone.
Main sample
As stated above, the annual target sample size for Scotland was 5,112 adults with a minimum local authority target sample size of 125 adults. These sample sizes were the minimum required to allow effective reporting of Scotland-level results annually and Health Board and local authority results with four years of data combined. An iterative approach was taken to efficiently allocate the sample across all Health Boards and local authorities. For the first iteration, 4,000 adult interviews were allocated across local authorities in proportion to the adult population. Any local authorities allocated fewer than 125 adult interviews had their allocation increased to 125.
The remaining sample was then allocated over the remaining local authorities. Where allocations were not whole numbers the number was rounded up. This resulted in a total target of 5,112 adult interviews. The results of the allocation are shown in Table 1.
Table 1: SHeS target annual adult interviews, 2025, by Health Board
|
Health Board |
Target Annual Adult Interviews |
|
Ayrshire and Arran |
375 |
|
Borders |
125 |
|
Dumfries and Galloway |
125 |
|
Fife |
271 |
|
Forth Valley |
375 |
|
Grampian |
488 |
|
Greater Glasgow and Clyde |
1,075 |
|
Highland |
297 |
|
Lanarkshire |
482 |
|
Lothian |
749 |
|
Orkney |
125 |
|
Shetland |
125 |
|
Tayside |
375 |
|
Western Isles |
125 |
|
Total |
5,112 |
To allow for reporting at local authority level over a four-year period (2022/2023/2024/2025) and coordination with the sample selection of the SHS and SCJS, the required sample sizes were set at local authority level. This was done by allocating the target Health Board samples to local authorities proportionate to population.
The number of addresses selected in order to provide the target number of interviews was calculated by:
- Estimating the number of productive adult interviews per co-operating household. Considering response data from previous years, it was estimated that there would be an average of 1.5 interviews per co-operating households in each local authority.
- Allocation of the target interviews and associated estimate of co-operating households to local authority strata proportionate to population.
- The response rate assumptions for local authorities for 2025 were then estimated based on the variation across local authorities in response to the 2018, 2019, 2023 face-to-face surveys, with weights of 0.5 applied to 2023 and 0.25 applied to each of 2018 and 2019.
- The final step was to estimate the level of ineligible addresses. As for previous survey years, the estimates were calculated at local authority level and based on the average level of ineligible addresses from previous years of SHeS, SHS and the SCJS.
Table 2 shows the number of selected addresses used for the main sample in 2025.
Table 2: Selected addresses issued by strata in 2025 – main sample
|
Sample strata |
Addresses for main sample |
|
Aberdeen City |
252 |
|
Aberdeenshire |
274 |
|
Angus |
191 |
|
Argyll & Bute |
211 |
|
Clackmannanshire |
172 |
|
Dumfries & Galloway |
191 |
|
Dundee City |
228 |
|
East Ayrshire |
184 |
|
East Dunbartonshire |
206 |
|
East Lothian |
196 |
|
East Renfrewshire |
185 |
|
Edinburgh, City of |
624 |
|
Falkirk |
205 |
|
Fife |
472 |
|
Glasgow City |
856 |
|
Highland |
275 |
|
Inverclyde |
219 |
|
Midlothian |
197 |
|
Moray |
179 |
|
Na h-Eileanan Siar |
196 |
|
North Ayrshire |
181 |
|
North Lanarkshire |
434 |
|
Orkney Islands |
186 |
|
Perth & Kinross |
211 |
|
Renfrewshire |
230 |
|
Scottish Borders |
181 |
|
Shetland Islands |
187 |
|
South Ayrshire |
198 |
|
South Lanarkshire |
398 |
|
Stirling |
201 |
|
West Dunbartonshire |
236 |
|
West Lothian |
212 |
|
Total |
8,368 |
Child boost sample
For the 2025 survey, 2,031 child interviews were required. It was estimated that the main sample would provide 1,026 child interviews, therefore, to reach the target number of child interviews, a child boost sample was required to yield a further 1,005 interviews.
The child boost sample was linked to health records via the Community Health Index (CHI) to identify households with children. This significantly improved the sample efficiency and response levels. This linkage was carried out by the CHI Linkage (CHILi) Indexing Team at Public Health Scotland.
Table 3: Target annual child interviews, 2025, by Health Board
|
|
Expected child interviews from main sample |
Target child interviews from boost |
Total target child interviews |
|
Ayrshire and Arran |
75 |
70 |
145 |
|
Borders |
25 |
21 |
46 |
|
Dumfries and Galloway |
25 |
27 |
52 |
|
Fife |
54 |
71 |
125 |
|
Forth Valley |
75 |
60 |
135 |
|
Grampian |
97 |
110 |
207 |
|
Greater Glasgow and Clyde |
219 |
216 |
435 |
|
Highland |
60 |
59 |
119 |
|
Lanarkshire |
97 |
131 |
228 |
|
Lothian |
149 |
163 |
312 |
|
Orkney |
25 |
0 |
25 |
|
Shetland |
25 |
0 |
25 |
|
Tayside |
75 |
77 |
152 |
|
Western Isles |
25 |
0 |
25 |
|
Total |
1,026 |
1,005 |
2,031 |
The process for calculating the number of addresses to select for the child boost sample was as follows:
- The child boost target of 1,005 child interviews was allocated proportionally to local authorities based on the child (under 16) population. If the number expected from the child boost was less than 10, then the local authority boost target was set to zero. Table 3 shows the child interview targets for the main sample and child boost sample by Health Board. The child interview target for each local authority was converted into a target number of co-operating households with children, assuming an average of 1.5 children per household. The number of households required was then adjusted using assumptions about household response rates. Based on the performance of the child boost sample between 2013 and 2015, household response rates for the child boost were assumed to be 6 percentage points higher than those for the main sample. Local authority level child boost response rates were calculated by applying this uplift to the response rate assumptions used for the main sample.
- For the child boost, CHI linkage was performed to identify addresses where health records indicated that a child was resident. It was assumed the CHI linking would identify 25% of sampled households as having a child resident. An additional assumption of 79% accuracy of the CHI records was included to allow for cases where health records may not be up-to-date or households had moved.
- The assumptions made on ineligible addresses for the main sample were applied to the address calculations for the child boost sample.
The total numbers of addresses issued for the child boost sample are shown in Table 4.
Table 4: Selected addresses issued by strata in 2025 – Child Boost
|
Sample strata |
Addresses for child boost |
|
Aberdeen City |
58 |
|
Aberdeenshire |
71 |
|
Angus |
24 |
|
Argyll & Bute |
13 |
|
Clackmannanshire |
16 |
|
Dumfries & Galloway |
33 |
|
Dundee City |
36 |
|
East Ayrshire |
43 |
|
East Dunbartonshire |
36 |
|
East Lothian |
34 |
|
East Renfrewshire |
33 |
|
Edinburgh, City of |
119 |
|
Falkirk |
52 |
|
Fife |
110 |
|
Glasgow City |
200 |
|
Highland |
56 |
|
Inverclyde |
17 |
|
Midlothian |
41 |
|
Moray |
23 |
|
Na h-Eileanan Siar |
0 |
|
North Ayrshire |
36 |
|
North Lanarkshire |
118 |
|
Orkney Islands |
0 |
|
Perth & Kinross |
43 |
|
Renfrewshire |
50 |
|
Scottish Borders |
23 |
|
Shetland Islands |
0 |
|
South Ayrshire |
22 |
|
South Lanarkshire |
117 |
|
Stirling |
26 |
|
West Dunbartonshire |
25 |
|
West Lothian |
66 |
|
Total |
1,541 |
Sample selection
The sample frame for address selection was based on an address extract derived from the Royal Mail Postcode Address File (PAF). This extract comprises the PAF with Unique Property Reference Numbers (UPRNs) added from Ordnance Survey’s AddressBase. As such, the sampling frame extends beyond the PAF alone and is sometimes referred to as the ‘NRS address extract’.
The advantages of using this address extract are as follows:
- It has previously been used as the sample frame for Scottish Government surveys so previously recorded levels of ineligible addresses can be used to inform assumptions for the 2025 sample design.
- It has excellent coverage of addresses in Scotland.
- The small user version excludes the majority of businesses.
Despite this, the sample frame still includes a number of ineligible addresses, such as small businesses, second homes, holiday rental accommodation and vacant properties. A review of previous survey performance found that fairly consistent levels of ineligible addresses were recorded for each local authority. This allowed robust assumptions about the expected proportion of ineligible addresses to be incorporated into the sample size calculations.
As the samples for the SHS, SHeS and SCJS have all been selected by the Scottish Government since 2012, addresses selected for any of the surveys are removed from the sample frame so that they cannot be re-sampled for another survey. This helps to reduce respondent burden. The addresses are removed from the sample frame for a minimum of four years.
The sample design was implemented in three stages:
1. All primary sampling units (data zones on the islands, intermediate geographies elsewhere) were randomly allocated to one of four sets. One of these sets will be used in each year of fieldwork. This means that the sample is drawn from one quarter of PSUs each year. The sets were updated ahead of the 2021 sampling and this ensures that over four years of fieldwork (2021 to 2024) all addresses will have a non-zero probability of selection.
Table 5: Primary sampling units selected in 2025 sample
|
Health Board |
PSUs in 2025 Sample |
Total PSUs |
|
Ayrshire and Arran |
24 |
93 |
|
Borders |
7 |
30 |
|
Dumfries and Galloway |
10 |
40 |
|
Fife |
26 |
104 |
|
Forth Valley |
20 |
78 |
|
Grampian |
33 |
132 |
|
Greater Glasgow and Clyde |
66 |
257 |
|
Highland |
20 |
79 |
|
Lanarkshire |
40 |
160 |
|
Lothian |
48 |
192 |
|
Orkney |
7 |
29 |
|
Shetland |
7 |
30 |
|
Tayside |
23 |
92 |
|
Western Isles |
9 |
36 |
|
Total |
338 |
1,352 |
2. The required numbers of addresses for the main and child boost samples gave an overall total of addresses to sample for each stratum (local authorities). The required number of addresses for each stratum was then sampled from the sample frame of addresses in active PSUs. Systematic random sampling was used with addresses within PSUs ordered by urban-rural classification, mean SIMD rank, SIMD rank, postcode and address.
3. Once the overall sample was selected, a proportion of the main sample addresses were randomly allocated to the biological module. One quarter of the target main adult sample was required to complete the biological module. To guard against a lower response rate to the different elements of the biological module, and to correct for inaccurate response assumptions in previous years, a proportion higher than the required one quarter of the adult sample (33% in 2025) were allocated to the biological module.
Selecting individuals within households
For the main sample, all adults aged 16 and over in responding households were eligible for interview. To ease respondent burden, for child interviews for both the main and the child boost samples a maximum of two children were interviewed at each household. If a household contained more than two children, then two were randomly selected for interview.
Selecting households at addresses with multiple dwellings
A small number of addresses have only one entry in the Postcode Address File (PAF) but contain multiple dwelling units. Such addresses are identified in the PAF by the Multiple Occupancy Indicator (MOI). To ensure that households within MOI addresses had the same probability of selection as other households, the likelihood of selecting addresses was increased in proportion to the MOI. At addresses with more than one dwelling, unit fieldworkers have a programme to randomly select the household at which interviews should be sought. There are generally a few cases were the MOI on the PAF is inconsistent with the actual number of dwelling units. When this occurred, the fieldworkers recorded the information, and a correction was made through the survey weighting.
References and notes
[1] Further information on the sample designs and the methodology used is available at: [ARCHIVED CONTENT] Scottish Government Survey Designs 2012-15
Contact
scottishhealthsurvey@gov.scot