Re-designing the UK’s Annual Structural Earnings Survey

The methods underpinning the UK’s annual structural earnings survey – the New Earnings Survey (NES) – have remained largely unchanged since the survey’s inception in 1970. A recent major review of earnings statistics in the UK, along with gradual changes in the labour market in recent years have led to a re-design of the NES. This paper describes some of the shortcomings of the NES and then presents the methodological work undertaken to redesign the survey. The methodological work covered several topics: • better use of administrative data; • development of the sampling design (which exploits a dual frame approach to reduce under-coverage of the survey); • improved data collection procedures, including an intensive follow-up pilot; • better procedures to analyse the characteristics of people who change jobs; and • a weighting strategy to account for both non-selection and non-response. Experiences from pilot work are described along with plans for full implementation in 2004.