To ask the Chancellor of the Exchequer what assessment he has made of the statistical reliability of the calculation of average wage levels using the (a) New Earnings survey and (b) Labour Force survey. 
The information requested falls within the responsibility of the National Statistician. I have asked him to reply.
Letter from Len Cook to Mr. Michael Foster, dated 2 July 2003:
As National Statistician, I have been asked to reply to your recent question on the statistical reliability of average earnings data from the New Earnings Survey and the Labour Force Survey.(122518)
Earnings data from the New Earnings Survey (NES) and from the Labour Force Survey (LFS) are valuable in different circumstances. The NES data are available annually and are based on a larger sample than those from the LFS. The LFS data are available quarterly and for a wider range of population subgroups than from the NES. An article describing the background and uses of ONS average earnings data was published in the February 2003 edition of "Labour Market Trends", a copy of which can be found in the Library.
Sampling errors have been calculated for both NES and LFS estimates and are available from the National Statistics website (www.statistics.gov.uk). Given the smaller sample size of the LFS, the sampling errors tend to be larger than the equivalent NES sampling errors.
Following an extensive quality review of the NES last year the survey is currently undergoing a significant redevelopment to further improve the quality of the estimates. The action plan for implementing the results of this review are also on the National Statistics website (www.statistics.gov.uk/cci/nugget.asp?id = 280). This will reduce known biases in the existing survey which arise principally from the fact that the sample only includes employees who are on Pay As You Earn tax schemes, but also because of differential response rates by size of business and region.