The ABI is a sample survey, not a census, so the information it provides on the number of jobs in an area is an estimate and will be subject to sampling variability. The survey achieves a response rate of about 85 per cent, although the response of the largest employers, who make up the bulk of the statistical data, is closer to 100 per cent.
The major strengths of the ABI are its comprehensive coverage of UK businesses and the level of industrial detail available. The two-part form of the ABI enables employment and financial data to be linked, which makes a valuable source for generating productivity statistics.
In terms of measuring employment, the ABI is the best source for measuring jobs, rather than people in employment, which is better measured by the Annual Population Survey (APS)/Labour Force Survey (LFS). The ABI also covers the whole of the UK, rather than just Great Britain.
The disadvantages of the ABI are that it does not cover the agricultural sector, nor does it include jobs in private households, jobs in organisations not held on the IDBR, homeworkers, jobs in non-UK businesses or the self-employed. In addition, the December reference date results in employment data that can be heavily influenced by seasonal factors.
For analysis of year-to-year changes in the number of jobs, the workforce jobs series is the source recommended by ONS. The ABI is preferred as a source of information on the industrial structure of the UK economy at a specific point in time.
However, interpretation should be made with caution and the data presented here are estimates, subject to both sampling errors (arising from the fact that the ABI is a survey, not a census) and non-sampling errors. For further information on confidence issues and standard errors, go to:
https://www.nomisweb.co.uk/articles/447.aspx