The sample survey is based on information held by HMRC tax offices on persons who could be liable to UK tax. It is carried out annually and covers the income assessable for tax in each tax year.
Samples were selected from three HMRC operational IT systems, which are as follows: COP:this covers all employees and occupational pension recipients with a PAYE record; CESA: this covers the self assessment (SA) population; those with self employment, rent or untaxed investment income, directors, those subject to higher rate tax and other people with complex tax affairs. Some people have both a COP and CESA record. Claims: this covers people without COP or CESA records who have had too much tax deducted at source and claim repayment.
Sponsor:
HM Revenue & Customs (HMRC)
Contractor:
Size of data collection:
The approximate sample sizes (number of individuals) for recent survey years are as follows: 1999-00 150,000 / 2000-01 200,000 / 2001-02 300,000 / 2002-03 400,000 / 2003-04 450,000 / 2004-05 500,000 / 2005-06 550,000
Linked surveys/sources:
HMRC Administrative Systems: CESA, COP and Claims
Method:
Other large-scale (Sample) Survey
Status:
Ongoing
Frequency of collection or compilation:
Annually
Reference period:
Tax year
Timeliness:
The results are not available until fifteen months after the end of the reference period. Full results are published about three months later, but some results may be made available in the intervening period upon request. Two months after final file produced although some tables are available earlier upon request.
Year data first available:
1978-79
Year of latest available data:
2005-06
History of data collection / breaks and discontinuities:
The first formal survey was for 1937-38. There have been annual surveys since 1967-68, with the exception of 1981/82 when no survey was done. It is not possible to provide any analysis prior to 1978-79 as the data no longer exists.
Main areas for which data is collected:
National: UK
Extent of geographical coverage:
Sampled: The sample for the SPI is drawn at random from records held by HMRC of persons who could be liable to UK tax, irrespective of where they live. The population of records is not grouped (stratified) by geographical region before the sample is selected. The geography indicators are attached only to the selected sample based on address and postcode. It follows that sub-UK estimates based on SPI are not controlled to known and fixed taxpayer population figures for each area. They are subject to random error caused by sampling and, where sample size is small, estimates for a geographical area can be subject to large sampling errors.
Spatial units of data collection:
Smallest spatial unit for which data are made available:
Commonly available units for which aggregate data are made available:
to a larger district level
Standard geographical classification or coding systems used:
Data cover the United Kingdom and are available at country, regional, county, metropolitan borough and larger no-metropolitan local authority district levels, although the lower the level of analysis used, the larger the standard errors.
Descriptive summary of geographical coverage and geographic referencing system:
Data are available for income distributions before and after tax, numbers of taxpayers with income and deductions of various types and the amounts concerned. Some information on tax liabilities and self-employment income is also available. Survey data on self-employment income, income from property, and investment income are used in the preparation of National and Regional Accounts.
