Health and Care Experience Survey 2025 to 2026: Technical Report
This report contains information about the methodology and background of the 2025 to 2026 Health and Care Experience (HACE) Survey.It is intended primarily for more technical users who wish to understand the how the survey was designed, delivered and analysed.
Sample Design
Sampling Frame
The sampling frame (the database from which the sample is drawn) is the Community Health Index (CHI). Public Health Scotland (PHS) selected a random sample of people who were registered with a General Practice in Scotland, had a recorded address in Scotland, and were aged 17 and over. PHS co-ordinated checks against the NHS Central Registry and the Community Health Index (CHI) database to remove people from the sample who have passed away.
People registered with some general practices run by NHS Boards to provide primary care services to particular groups of people (e.g. practices for homeless people, armed force or for prisoners) were excluded because of historically low response rates, the sensitivities associated with contacting these groups, and practical difficulties in contacting individuals by post.
A number of practices that had been excluded from previous surveys due to low response rates were reintroduced to the survey sample in 2023 to 2024. These included a number of practices associated with universities that have a low response rate.
Sampling Design and Sample Size Calculation
The sample was stratified by General Practice, with the aim of collecting a sufficient number of responses at each practice to represent the experiences of patients receiving care at that practice.
For some practices with very small numbers of eligible people, all patients were included in the survey in order to meet the minimum sample size requirements identified.
Minimum number of responses (M)
To ensure that survey results for each General Practice are sufficiently precise, the minimum number of responses was calculated for each practice.
For each General Practice, we calculated sample sizes to reach the Minimum number of responses (M) required to achieve an estimate of a percentage that has a 95 per cent confidence interval with width +/- nine percentage points, sampled from a finite population. The target confidence interval range was increased from eight percentage points in 2023 to 2024 to nine percentage points in 2025 to 2026 to reduce the cost of the survey. The number of survey invites sent out determine the cost of the survey and various options for reducing the sample size were considered. The final approach aims to balance cost savings with maintaining representativeness and ensuring all demographic groups can share their experiences.
Under these assumptions, the formula for the minimum number of responses required (M) is:
M = B / (1+((B-1) / N))
Where:
- B = z2p(1-p) / c2 using the following definitions:
- p is the proportion answering in a given way, assume 0.5 to give maximum variability;
- z is 1.96 for a 95 per cent confidence interval (using the standard normal distribution);
- c gives maximum acceptable size of confidence interval, in this case 0.09 (nine percentage points).
- N is the number of people on the sampling frame (i.e. the number of people registered with a practice and aged 17 or over);
Table 1 shows the minimum number of responses required (M) based on the assumptions above, for some example practice population sizes.
An illustration of the number of responses required to achieve the desired level of accuracy by the practice list size.
Table 1: Examples of the minimum number of responses required for different General Practice list sizes.
|
Practice List Size (N) |
200 |
500 |
1,000 |
2,000 |
5,000 |
10,000 |
20,000 |
|
Min. required responses (M) |
75 |
96 |
107 |
112 |
116 |
118 |
118 |
|
Percentage of General Practice population required to respond |
38% |
19% |
11% |
6% |
2% |
1% |
1% |
In practice, if the proportion answering a particular way is actually higher or lower than 0.5, then these numbers of responses would give narrower confidence intervals (or fewer responses would be required for the same accuracy).
The number of people to be sampled is then calculated by adjusting the minimum number of responses required upwards, based on the assumed non response to the survey.
Estimated response rates to the 2025 to 2026 survey for each individual General Practice were based on the response rate of the 2023 to 2024 survey. Where response rates were not available, i.e. for a new practice, assumed response rates were used based on the proportion of the eligible population living in the most deprived 15% of data zones (based on the Scottish Index of Multiple Deprivation 2020). Scottish Index of Multiple Deprivation ranking is strongly correlated with the likelihood of a person responding to the survey.
Estimated required sample sizes were capped at a maximum of 1,000 for individual practices.
The addresses from CHI were cross checked against the Scottish Postcode Directory to ensure that they were complete. Any instances of invalid, deleted or incomplete postcodes were removed prior to sample selection, as were a small number of people who had requested not to be included in this or other surveys.
A total of 492,976 people were sampled for inclusion in the Health and Care Experience Survey 2025 to 2026.
PHS checked for any cases where the same name (first name, middle name and surname) and address appear. Each of these cases within the “duplicate” are removed prior to sample selection. The duplicates may be relatives living together or errors in the source data. Removing them ensures there is no ambiguity as to who is being asked to participate in the survey and reduces the risk of questionnaires being sent out in error.
Sample Selection
For the majority of practices in Scotland, a random sample of the required number of people from each practice was taken from the Community Health Index (CHI) database by Public Health Scotland. For some practices with very small numbers of eligible people, all were included in the survey in order to meet the minimum sample size requirements identified from the calculation above. The sample was selected using the statistical software package R.
The CHI population is based on patients registered at GP practices and it is the population to which GPs will refer when considering the services they provide to their patients. The number of people registered in GP practices is larger than the Scottish population by approximately 500,000 as estimated by the National Records of Scotland (NRS). This is due to list size inflation caused by factors such as people not de-registering with their GP after moving outwith the UK or not registering with a new GP if moving within the UK. For example, students moving from Scotland. For more information please see the notes section of the PHS General Practice List Sizes and Demographics dashboard.