Annex B: About the Annual Population Survey
What is the APS and what is it used for?
The Annual Population Survey (APS) combines results from the Labour Force Survey (LFS) and the English, Welsh and Scottish Labour Force Survey boosts. The boosts increase the sample size which means the APS can provide more robust labour market estimates for local areas compared to the main LFS. Thus the APS is the primary source for information on local labour markets providing headline estimates on employment, unemployment and economic activity. The APS is the largest annual household survey in Scotland and provides a wealth of information about individuals' personal circumstances and their work.
Information from the APS is used by the Scottish Government to inform government targets and policies. Some of the many external users of the APS include Local authorities, Scottish Enterprise, Highlands & Islands Enterprise, Skills Development Scotland, Higher & Further Education sector. Uses include monitoring targets, statistical analysis, policy development and briefing.
The APS is the source of information for 2 of the Government's Purpose targets and 1 of the 45 national indicators in the Government's National Performance Framework. This report provides information on progress against these targets and national indicators:
- Participation - To close the gap with the top five OECD economies by 2017
- Cohesion - To narrow the gap in participation between Scotland's best and worst performing regions by 2017.
- Improve the skill profile of the population - Reduce number of working age people with severe literacy and numeracy problems
What topics are available?
A wide range of topics are included in the survey:
- Economic Activity (present or past)
- Employment in main job and second jobs
- Working conditions (hours, work pattern etc.)
- Reasons why people are not in the labour force
- Geographical mobility
- Education and training
- Individual and household characteristics
How and when is the survey conducted?
The Office for National Statistics (ONS) carries out the LFS and associated boosts.
The APS datasets are based on calendar quarters and are produced quarterly on a rolling annual basis (covering 12 months of data). So the four annual APS datasets produced by ONS each year cover the periods January to December, April to March, July to June and October to September.
The APS data use the existing continuous quarterly LFS in addition to annual enhancements. In the quarterly LFS, each person in a selected household is interviewed five times at 13-week intervals. In any three-month period, about a fifth of the sample are being interviewed for the first time, another fifth are receiving their second interview and so on, with 20% being interviewed for the fifth and final time. Each of these roughly equal groups is termed a wave i.e. 'wave 1' refers to those people having their first interview.
Who takes part in the survey?
The LFS surveys individuals living at private households in the UK and is designed to be representative of the national population.
The Scottish Government funds the boost to the LFS sample in Scotland, taking the sample size from approximately 5,800 households each year to 20,000 households.
The target sample size in each local authority is 675 economically active adults except for Clackmannanshire (250); Dumfries and Galloway (700), East Lothian (600); East Renfrewshire (600); Eilean Siar (200); Inverclyde (600); Midlothian (600); Moray (600), Orkney Islands (200); Shetland Islands (200); Stirling (600) and West Dunbartonshire (700).
Revision of estimates
The APS was reweighted based on outputs from the 2011 Census on 19 March 2015. This has had some impact on historical estimates for population, economic activity indicators and equality group estimates within local authorities. The Scottish Government does not plan to retrospectively revise all estimates in previous publications, although some revised tables may be issues to provide revised estimates for key indicators.
How reliable are the results?
As survey results, these are subject to a degree of error and implied changes between years which may not be significant and instead be within a given error range. Confidence limits for estimates should be taken into account, especially for changes over time. Annex B provides more information and confidence limits are included in the web tables for each indicator.
Interaction of labour market statistics
The three main labour market indicators - employment, unemployment and economic inactivity - are all inter-related. Increases in employment rates are likely to result in corresponding decreases in either or both unemployment and economic inactivity rates (as an increase in employment means there should be less unemployed or inactive people). However, more subtle interactions exist. It is possible for a shift in people between employment and inactivity to change the unemployment rate, even though there has been no change in the actual number of people unemployed. This is because the unemployment rate is based against the economically active population (those in employment plus those unemployed) as opposed to the total relevant population. The same effect does not occur for employment and inactivity rates because they are based against the total relevant population
Residence, Households and Workplace based statistics
The information and data presented in this publication is predominantly based on residence based statistics - that is, the statistics relate to the characteristics of residents of a geographical area. These statistics do not give information about the number of jobs or people employed within a local area as this will be different to the number of employed people living within the same area (due to people commuting in and out of the area for work). This is covered briefly in the section on Commuting patterns in the Employment chapter.
Workplace based statistics are available from the APS. These are freely available from Nomis at: http://www.nomisweb.co.uk/.
Employer surveys, such as the Business Register Employment Survey (BRES) and Workforce Jobs are workplace based, relating to an employers specific business locations. These surveys do not gather any corresponding residence based data (unlike the APS).
Household surveys differ from individual surveys in that the main unit of measure is the household. These surveys can be used to gather information about the different household characteristics within the country, especially in regards to working and workless households. This report does not publish household estimates. These are available from Nomis at: http://www.nomisweb.co.uk/.
Hours and Earnings statistics
The APS records self-reported hours and earnings data (including usual and actual hours worked, usual and actual pay, gross and net income, overtime and bonuses). However, the data is self-certified (there is no check with employer or HMRC to check the data is accurate), and the respondent can choose not to answer these questions.
The official source for data on hours and earnings is the Annual Survey of Hours and Earnings (ASHE). Data for ASHE is available from:
Email: Alan Winetrobe