Methodology & Notes

Background

Scottish Annual Business Statistics (SABS) is based on data from the Annual Business Survey (ABS) (formerly Annual Business Inquiry (ABI)) conducted by the Office for National Statistics (ONS).

The statistics have been produced under partnership procedures agreed between ONS and the Scottish Government (SG). These have resulted in an improvement in the quality of the underlying data and consistency in the figures used by ONS and SG.

The ABS is the UK’s key resource for understanding the detailed structure and performance of businesses across the UK, classified to the UK Standard Industrial Classification (SIC) system.  Estimates 1, by industry (using SIC codes), are published for: 

Estimates included in the SABS results:
Local unit counts                                                              Increase in Stocks
Employment                                                                    Gross Wages and Salaries
Employee Jobs                                                                 Total Labour Costs   
Turnover                                                                         Total Output at basic prices
Purchases of goods and services                                      GVA per Head
Approximate Gross Value Added (GVA) at basic prices       Gross Wages and Salaries per Head
Taxes                                                                              Total Labour Costs per Head

Within SABS, estimates by industry sector are published for Scotland, Scottish local authority areas and business ownership groups. These estimates are presented as monetary values, and give a snapshot of business activity that can be used to understand the level of contributions to the Scottish economy from different industry sectors, local authority areas and ownership groups.

[1] Definitions for the employment and financial estimates are available at: http://www.scotland.gov.uk/Topics/Statistics/Browse/Business/SABS/Definitions

Coverage

Coverage

The ABS is an annual survey of registered 2 businesses covering the production (including manufacturing), construction and service industries (including distribution) which represent the UK Business Economy. This is about two thirds of the UK’s whole economy in terms of Gross Value Added. The statistics do not cover the whole economy, omitting much of the public sector, parts of finance and agriculture.

Exclusions

The following sub-classes of SIC 1 (Crop and animal production, hunting and related service activities) are omitted:

01.1 – Growing of non-perennial crops 
01.2 – Growing of perennial crops 
01.3 – Plant propagation
01.4 – Animal production
01.5 – Mixed farming

Within SABS, the services sector is defined as division codes 45 to 96 of SIC 2007 (SIC07). Although the publication refers to the services sector for simplicity, it should be noted that the figures quoted do not relate to the entire services sector, but only to those sectors covered by the ABS. The main industries excluded from the services sector are:

  • Financial intermediation (SIC 64 (Financial service activities, except insurance and pension funding), SIC 65.3 (Pension Funding), SIC 66 (Activities auxiliary to financial services and insurance activities) in Section K);
  • Public Administration and defence (Section O);
  • Education (public provision in Section P); and
  • Health (SIC 86.2, public provision in SIC 86.1 and 86.9 in Section Q).

Insurance and Reinsurance sector (SIC 65.1 and 65.2)

Only part of the finance sector is covered by the ABS (Insurance and reinsurance only (SIC 65.1 and 65.2)) and this coverage is relatively new, beginning in 2008. Development work was undertaken by ONS to ensure the questionnaire was as relevant as possible for this sector. The ONS ABS team will continue to monitor the data being collated to ensure it is as relevant and accurate as possible but until a longer time series is available results remain experimental. See full note on this sector under heading below.

Oil & Gas

ABS data relating to Oil & Gas extraction (SIC 6) is allocated to UK regions (including Scotland) according to the address at which the business is registered - onshore and offshore Oil & Gas extraction and activities are allocated in this way. GVA associated with off-shore activity, under UK regional accounts procedures, is normally allocated to a separate ‘Extra Regio’ category rather than allocated to a region within the UK.

[2] Businesses registered for Value Added Tax (VAT) and/or Pay As you Earn (PAYE)

Insurance and Reinsurance sector (covers SIC 65.1 & 65.2)

This note is to advise users of on-going data issues surrounding Insurance and Reinsurance sector (covers SIC 65.1 & 65.2). Due to on-going volatility in the data, and following discussions with key users, results for Insurance and Reinsurance have been removed from Office for National Statistics (ONS) Annual Business Survey (ABS) release for reference year 2012 (this covers national figures published in November 2013 and June 2014), while a more detailed quality assessment is undertaken. Their removal does not affect other industries published as part of the ABS releases and has no impact on any other financial statistics published by the ONS.

Please note that regional data (includes Scotland) for this sector currently remains in 2008-11 Scottish Annual Business Statistics (SABS) Tables available on this web site to match regional totals previously published by ONS. However, results for this sector should be treated as experimental and any comparisons between years should be undertaken with caution.

For information, Insurance and Reinsurance data will be removed from 2008-12 SABS Tables to be published on 20th August 2014. Full background information follows:

The ABS covers only part of Insurance, reinsurance and pension funding, except compulsory social security (Division 65) in Financial and insurance activities (section K). The industries covered are:

  • Insurance - Group 65.1
  • Reinsurance - Group 65.2

Please note that references to 2012 data below is to national figures published in November 2013 and June 2014, regional 2012 data (includes Scotland) is due for release in Summer 2014. The ABS has included results for the Insurance and Reinsurance industry in its UK National releases since 2008. While the experimental results for Insurance and Reinsurance will not appear in ABS releases from reference year 2012, the national data will be available on request, but users should take into account the following issues concerning data quality:

  • Quality assurance has led the figures to be revised substantially with breaks in the series between 2009 and 2010 and between 2011 and 2012. Validation of data returns for 2011 highlighted that a small number of businesses within the finance and insurance sector were returning global figures rather than UK only. Results for 2010 and 2011 have been revised to reflect UK figures, but previous years (2008 and 2009) have not been revised and should therefore not be compared directly with 2010 and 2011.
  • Validation of data returns for 2012 have highlighted that a small number of businesses within the finance and insurance sector were not reporting all their purchase costs on the questionnaire. Previous years (2008, 2009, 2010 and 2011) have not been revised and should therefore not be compared directly with 2012. National results for 2011 will be revised in June 2014 to make them comparable with 2012 but, in line with the ABS revisions policy, previous years (2008, 2009 and 2010) will not be revised.

A review of the questionnaire for Insurance and Reinsurance businesses will be undertaken alongside continued validation of returns to the survey,  with the aim of reintroducing them to the ABS publications when the quality of the data has improved. Updates on progress will be available on the ONS ABS News Page.

Use

Use

The Annual Business Survey (ABS) is a valuable source dataset which is used alongside a number of other important datasets in the production of macro-economic statistics for Scotland and the UK as a whole.  It is important to note that overall growth rates associated with the ABS are not comparable to the official growth rates for the whole economy given that significant sectors of the economy are not included in the ABS and the results have not been balanced with other datasets.  The SABS statistics are therefore best suited to analyses of individual industries rather than the economy as a whole. 

The SABS data allows analysis of business structure, ownership and location within detailed sectors of the Scottish business economy.  SABS figures are used extensively, by the Scottish Government, to inform sectoral policy (including the growth sectors) and regional/local economic development. A consultation on the use made of SABS, carried out in the Spring of 2011, showed that other users of SABS include local authorities, the enterprise networks, academics and consultants.  For more details on the consultation, please consider the following document:  http://www.scotland.gov.uk/Topics/Statistics/Browse/Business/scotstat/SABSFindingsReport

The SABS results can be used to answer questions such as:

  • how much value has been created in a particular industry, and how many people are employed by it?
  • has there been a shift in activity from one industrial sector to another, and which sub-industries are driving the change?
  • are any industries particularly dominant in specific local authority areas?
  • how productive is a particular industry and what is it that is having an impact on productivity? 

Links to examples of how the Scottish Annual Business Statistics results have been used are provided below: 

Assessing Legacy 2014 website. Scotland and Glasgow City local authority GVA data from SABS is used in this site to track a set of outcome indicators which form part of the evaluation of the XX Commonwealth Games that will be held in Glasgow in the summer of 2014.
http://www.scotland.gov.uk/Topics/ArtsCultureSport/Sport/MajorEvents/Glasgow-2014/Commonwealth-games/Indicators

The City of Edinburgh, Edinburgh by Numbers publication. The 2013/14 publication below includes use of SABS data under Figure 42: Total labour costs per employee by sector 2010.
http://www.edinburgh.gov.uk/info/239/support_for_businesses-economic_information_and_development/443/local_economy-reports_and_forecasts/3

Falkirk Local Authority data. The February 2013 Statistics publication below includes SABS Local Authority level data in Tables 4, 5 and 6. 
http://www.falkirk.gov.uk/services/corporate_neighbourhood/policy_performance_review/research_information/
economy_and_labour_market/falkirk_as_a_location.aspx

Scottish Enterprise, Textiles Key Facts. This publication includes a number of facts sourced to SABS data including GVA and turnover figures. 
http://www.scottish-enterprise.com/your-sector/textiles/textiles-industry-in-scotland/textiles-key-facts.aspx

Aberdeen City and Shire Economic Future (ACSEF) use SABS GVA per employee data at link below.
http://www.acsef.co.uk/reportSubGroups.cfm?pageID=12
 

Major Time Series Analysis Caveats

Major Time Series Analysis Caveats

2011 (impact on 2008-09 data)

Please note that validation of data returns for 2011 highlighted that a small number of businesses within the Insurance and Reinsurance sector (SIC 65.1 and 65.2) were returning global figures rather than UK only. A revised 2010 estimate (together with new 2011 data) are now available in this publication. However, any global figures reported will remain in 2008 and 2009 published data in line with current Annual Business Survey (ABS) revisions policy. This can have a significant impact on Insurance, reinsurance, professional, scientific and technical activities (Section KM) time series data, as well as overall Totals, in particular local authority areas. Results for this sector are experimental and any comparisons between years should be undertaken with caution.

2010

Further Education (FE) Colleges were reclassified as Central Government entities on 13 October 2010, transferring FE Colleges from the private/business sector to the public sector.  This change brings FE Colleges out with scope of ABS survey from 2010 onwards, which represents a step change in the 2010 results for SIC 85 compared to data for earlier years. 

2009

The data, from 2008 onwards, are published on a Standard Industrial Classification (SIC) 2007 basis – data pre-2008 were published on a SIC 2003 basis.  Updates to the SIC are required to enable it to more accurately reflect the structure of the modern economy - SIC 2003 was replaced by SIC 2007 in January 2008. The revision was motivated by the need to adapt the classification to changes in the world economy. The revised classification reflects the growing importance of service activities in economies over the last fifteen years, mainly due to the developments in information and communications technologies.  

More information on SIC (2007) is available at:  http://www.scotland.gov.uk/Topics/Statistics/Browse/Business/Corporate/sic2007note#top and http://www.ons.gov.uk/ons/guide-method/classifications/current-standard-classifications/standard-industrial-classification/index.html

The employee/employment data published in SABS, from 2008 onwards, are based on Business Register and Employment Survey (BRES) – previous years SABS employee data were based on the employment part of the Annual Business Inquiry (ABI/1).  The BRES replaced and integrated the Business Register Survey (BRS) and the ABI/1 in 2009 (note that there was a pilot of BRES in 2008 which allowed 2008 BRES estimates to be produced).  For businesses that are surveyed by BRES, the regional and local estimates of employment are more accurate (than those from the ABI/1) because, rather than producing data by a headquarter-based apportionment model, they are obtained directly from data reported at site level (shop, office, factory, etc).  More information on BRES is available on the ONS website at: http://www.ons.gov.uk/ons/publications/all-releases.html?definition=tcm:77-230512

The 2008 and 2009 ABS followed a similar sample selection criteria (see Sample Design section below) and were both sampled on a SIC 2007 basis.  It is important to note that 2009 marked the full introduction of the BRES, this and the change to SIC 2007 may lead to some discontinuity with businesses moving from one SIC to another between years.  It is not unusual for some businesses to change SIC code over time, but there are some particular movements between 2008 and 2009 that users should be aware of e.g. a large number of landscape business sites have moved from SIC 01 (Crop and animal production, hunting and related service activities) to SIC 81 (Services to Building and Landscape Activities) between 2008 and 2009 – this is a result of the change from SIC03 (where landscape businesses were included with the agricultural sectors) to SIC07 (where landscape businesses fall under the services sector). 

Insurance and Reinsurance (SIC 65.1 and 65.2) data is published for 2008 onwards – this is the first time that these data have been included in SABS.  Please note that SIC 65.3 (Pension funding) is still omitted from the SABS results.

2008

ONS improved the sample design for the 2008 survey which means that the results for 2008 onwards cannot be compared with historical trends. Although this temporary loss of comparability over time is a downside - it means that the results for 2008 onwards are more accurate, and comparisons can still be made between sectors across the UK. More details are provided below on the change in sample design due to SIC 2007 and the complete re-allocation of the sample.

Notwithstanding, the change in sampling, the high energy prices in 2008 have had a significant impact on the "Remaining Sectors" results for Scotland in 2008.

2006

For 1998-2005 data, Scottish Government analysts merged ABI/1 (employment survey) and ABI/2 (financial survey) results in order to produce consistent "per employee" totals (e.g. GVA per employee). During this process, employee data was retained only if a company was part of smaller financial survey. However, for 2006-07, there was a change in the sampling arrangements for the two parts of the ABI. In previous years, ABI/2 was a sub-sample of ABI/1 but they moved to being sampled separately in different months. This led to non-matching between the two sets of results - affecting around 3-4% of total ABI/2 units. For these units, employee totals were set to their values from the Inter-Departmental Business Register (IDBR).

Further, for 2006-07, ABI/1 survey reference date moved from December to September. This step change should be taken into consideration when analysing time series data.

2001

From 2001 coverage of Section A (on SIC 2003 basis) was further extended to include Groups 01.4 (Agricultural and animal husbandry service activities, except veterinary activities; landscape gardening) and 01.5 (Hunting, trapping and game propagation including related service activities). Within Groups 01.4 and 01.5 employee data is volatile between years due to small sample size - time series should therefore be treated with caution.  

2000

From 2000 ABI coverage (on SIC 2003 basis) was extended to include Division 02 of Section A (Forestry, Logging and Related Service Activities) and Division 05 in Section B (Fishing).

1999

From 1999 improvements to the questionnaires for Sections M (Education - excludes some public sector) and N (Health and social work - excludes some public sector), both on SIC 2003 basis, led to a movement of data from 'total turnover' to 'value of grants/donations received'. This caused the approximate Gross Value Added at basic prices to fall between 1998 and 1999.

Rounding of Figures

Rounding of Figures 

Where necessary, figures have been rounded to the nearest final digit shown. Consequently, there may be slight discrepancies within a table between totals and the sums of constituent items.

Symbols and Abbreviations

Symbols and Abbreviations

The following symbols and abbreviations are used within the ABS data:

.. not available

- nil

* Information suppressed to avoid disclosure

Inter Departmental Business Register

Inter Departmental Business Register 

The sampling frame used for the ABS is the Inter Departmental Business Register (IDBR), which consists of companies, partnerships, sole proprietorships, public authorities, central government departments, local authorities and non-profit making bodies. The main administrative source for updating the IDBR is the HM Revenue and Customs (HMRC) for VAT and PAYE details.

Each legal unit is classified to a single activity, whether it is wholly or mainly engaged in that activity. The nature of a business can change with time, possibly because another business has been absorbed in a take-over. Some businesses have a very significant secondary activity, perhaps completely different from their main activity, and a small change of direction can lead to a new main activity and to the reclassification of the business. Other changes may arise from improvements to classification data held on the IDBR as a result of new information received about individual businesses. The reclassification of businesses for reasons such as these contributes to the year on year changes in the figures published.

Further information on the IDBR can be found at http://www.ons.gov.uk/ons/about-ons/who-we-are/services/idbr/index.html

Sample Design

Sample Design 

The ABS sample is designed as a stratified random sample of around 70,000 businesses from the IDBR. The survey population or universe is stratified by Standard Industrial Classification, employment, and country using the information from the IDBR. The sampling scheme is designed to give best estimates of the population totals for a given sample size and involves selecting all the largest businesses with a progressively reducing fraction of smaller businesses. This method ensures the sample size is kept to a minimum.

The inquiry results are grossed up to the register population, so that they relate to all active UK businesses on the IDBR for the sectors covered.

Scottish sample

Since 1998, the Scottish Government has funded an enhanced ABS sample in Scotland, to improve the quality of Scottish figures. In 2011, around 2,600 extra firms in Scotland were sampled as a result of this "boost", giving a total sample size in Scotland of around 8,100 firms.

Changes to the sample

From 2008 onwards, the sampling stratification and resultant estimation has been carried out on a SIC 2007 basis.

Please note that, for the 2008 sample, ONS undertook a complete sample re-allocation (using the Neyman methodology) to ensure that sufficient account of the variability within the micro businesses was reflected in the sample.

Due to the complexity of the ABS sample structure ONS had erred away from regularly re-allocating the sample. Hence, for a number of years ONS were left in the position of having the basis of the original sample produced in 1998 but with a number of manual tweaks. The earlier sample design did not adequately take account of the greater variability of smaller businesses, which should have led to a larger proportion of smaller businesses than was actually selected over that period. Consequently, the share of smaller businesses in 2007 and earlier was smaller than it should have been. 

The Sampling Framework table shows that, since 2008, there has been a significant increase in businesses sampled in 0-9 employment size.  In 2007, businesses in the 0-9 employment size band made up 43% of the Scottish ABS sample, this share increased to 58% in 2008 and 2009, 59% in 2010 and 60% in 2011. 

The change in the sample design, due to the SIC 2007 and the sample re-allocation from 2008, means that the results for 2008 onwards are not strictly comparable with earlier years data.

Response

Response 

Details of UK-wide ABS response rates are made available by ONS at:
http://www.ons.gov.uk/ons/rel/abs/annual-business-survey/2011-revised-results/abs-2011r---abs-quality-measures--june-2013-.xls

Selective editing

When ABS responses are received, checks are undertaken by ONS to ensure the information is correct. This is known as editing and validation. Selective editing has been used to validate responses for the first time for the 2011 results using software called SELEKT. SELEKT is a generic selective editing tool which highlights responses which appear to be in error if they fall outside the range of what is expected and have a large influence on key estimates. Those responses with the highest score are prioritised for editing and validation. This increases the efficiency of the editing process by focussing on the responses with the highest impact and importance.

The introduction of selective editing should at least maintain, if not improve the quality of the ABS results as it should: minimise the bias introduced by processing (removing over-editing); remove non-value adding activities from the process; and focus resources to errors that impact on the results.

However, the full impact on quality is not yet known. This will continue to be monitored and any updates will be included with future ONS ABS releases. For more information on SELEKT, see Chapter 5 of the ABS Technical Report (1.61 Mb Pdf) .

Confidentiality

Confidentiality 

The Statistics of Trade Act 1947 prohibits the disclosure of any information relating to an individual undertaking without the consent of the person carrying on that undertaking. Rigorous checks have been made to ensure that information relating to individual businesses has not been disclosed, either directly or by deduction, in any of the figures released. Similar precautions will be taken in safeguarding the confidentiality of returns in the preparation of any ad-hoc analyses.

Estimation

Estimation 

Factors are produced to enable estimates for all businesses classified to each SIC(2007) to be compiled from data provided by responding businesses. These factors are calculated for each employment size-band within each SIC(2007) and are equivalent to the ratio of responding businesses to the total number of businesses. Northern Ireland and Scotland are sampled and estimated for separately, England and Wales are sampled separately but are combined for the estimation procedure.

Returns for the few large non-responders are estimated for individually. This estimation is normally based on summary data received from the business, or on the business's return to the survey in the previous year adjusted to take account of the likely change in the value of trading over the period.

Regional Estimation

Regional Estimation

The business unit to which ABS questionnaires are sent is called the reporting unit. For ABS, the reporting unit represents an enterprise, which may consist of one or more sub-units (called local units). For example, an enterprise might be the head office for a group of shops. An enterprise may therefore have local units at different locations, and may carry out more than one type of economic activity. 

To produce the regional estimates, the reporting unit data returned by each business are divided amongst its local units. Each local unit’s allocation depends on the size of its employment, the industry it is in and its geographical location. This is achieved using a standard statistical modelling technique called regression analysis. 

Local unit employment is obtained from the Business Register and Employment Survey (BRES), which collects data from local units, rather than enterprises. Results are then aggregated for each region /country and industry, using the industry classification of the local units.  Each local unit is assigned a single SIC code, which corresponds to the unit’s principal activity.  Where more than one type of economic activity is carried out by a local unit or enterprise, its principal activity is the activity which contributes most to the value of the unit. Hence, although the sum of the regional results for the whole business economy will match the total for the national results, the sum of the regional results by industry will not necessarily match the UK industry totals, as local units might not all share the same industry classification as their parent units. 

Changes to the regional weighting methodology were introduced to ABS from the 2009 regional results onwards.  Further information on the methodology of the approach and analysis of the impact can be found in the ONS published note, ‘Weighting in the Regional System  - September 2011’, available  at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/quality-and-methods/index.html

Note that, as BRES is not carried out at the same time as ABS, differences in the timing of responses from ABS and BRES can lead to some reduction in the quality of the apportionment method.

For more information on the methodology used to compile regional ABS statistics, please consider the ONS background and technical documents available on-line at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/quality-and-methods/index.html

Total Employees/Employment and Per Employee/Per Head variables

Total Employees/Employment and Per Employee/Per Head variables 

For 2008 data onwards, Scottish Government analysts have merged BRES (employment survey) and ABS (financial survey) results in order to produce consistent "per employment" totals (e.g. GVA per Head). However, the BRES and ABS are sampled at different times of the year so where a BRES employee/employment estimate cannot be found for a business within the ABS, employee/employment totals are set to their values from the Inter-Departmental Business Register (IDBR).

The Total Employees/Employment variables included in SABS are based on a head count and not a Full Time Equivalent (FTE) measure. This distinction is particularly important for sectors with high levels of part time employment (e.g. Retail and Accommodation & Food Service activities) especially when comparing Per Head figures 3

Employees in BRES are defined as: An employee is anyone aged 16 years or over that an organisation directly pays from its payroll(s), in return for carrying out a full-time or part-time job or being on a training scheme. It excludes voluntary workers, self-employed, working owners who are not paid via PAYE.

Employment in BRES is defined as: Employees + Working owners who are not paid via PAYE.

Please note that SABS 2011 leads with providing “per employment” figures for the productivity measures – previously SABS led with “per employee” figures.  This change has been made due to a change in the treatment of working owners, in the underlying BRES data (used in SABS).  From the 2011 survey, BRES treats working owners of limited companies as employees rather than working owners (as was previously the case) – and as part of this change in the BRES survey it was identified that in the past there was some double counting of working owners of limited companies (i.e. they were being counted as working owners and employees).  The 2011 and 2010 BRES employment and employee data used in SABS have been adjusted to take account of these changes – however, this presents a break in the series with the latest employee/employment data for 2010/2011 not being strictly comparable to the 2008/2009 employee/employment data.   Although the employee and employment data have both been affected by these changes, the impact was larger for the employee data than it was for the employment data - and therefore to maintain as consistent a time series as possible the SABS publication is now to leading with “per employment” measures of productivity.  

Please note that both "per employment" and "per employee" figures have been provided to allow for comparison in latest SABS release. However, it is likely that only "per employment" figures will appear in future releases.

[3] The ONS publish sub-regional labour productivity figures in terms of GVA per hour worked and GVA per filled job. Both sets of figures are published at a NUTS 2 and NUTS 3 sub-regional geographies. Data is available at: http://www.ons.gov.uk/ons/publications/all-releases.html?definition=tcm%3A77-233093.  However, note that results are not available broken down by industry group.      

Data Reliability

Data Reliability 

SABS figures are based on an annual survey of businesses. In the context of overall Scottish figures, year-on-year differences are sometimes less obvious as they can be compensated for by other changes. However, at a more disaggregate level, such as sectoral or local authority area, changes in a small number of large companies can have a have a very marked effect on figures from one year to the next.

Structural changes

The business economy is constantly evolving as businesses merge, are taken over, or simply change the main focus of their business. These changes can result in the industry classification of a business changing. For example, if a business undertakes both manufacturing and wholesale activities, but most of its employment is within manufacturing, it will be classified to manufacturing. If the employment were to change substantially so that the majority worked in wholesale then the industry classification would change and the whole of the businesses turnover, for example, would move from manufacturing to wholesale. In industries where movements are common, or where large businesses are involved, these changes can themselves sometimes cause large changes in ABS estimates. This should be taken in to consideration when changes over time are being assessed.

Quality Measures

Estimates derived from samples invariably produce results which differ from those that would have been obtained from a complete census of all businesses. If a number of different samples were selected then each would produce a different result. Sampling errors measure the extent to which these estimates can be expected to differ from the 'true' value. The standard error is the estimated value of the sampling error – the closer the standard error to zero, the more reliable the estimate. UK level standard errors for the main variables are made available by ONS at: http://www.ons.gov.uk/ons/rel/abs/annual-business-survey/2011-revised-results/abs-2011r---abs-quality-measures--june-2013-.xls

Standard errors for the regional or local estimates are not currently available.  Therefore, to give users an indication of data quality and reliability, the SABS publication includes information on the percentage of selected data (business units, turnover, GVA, labour costs) that is from actual survey returns as opposed to estimated data.  For example, if a Local Authority area has an estimate of £X Turnover in the Manufacturing sector, from the associated quality measure table, users will be able to see that Y% of the Turnover figure is produced from actual returns and by deduction Z% from estimated data.  Data quality measures for SABS can be found at:

http://www.scotland.gov.uk/Topics/Statistics/Browse/Business/SABS/QualityMeasures

The actual survey returns proportions also include constructed returns; this is where returns for the few large non-responders are estimated for individually. This estimation is normally based on summary data received from the business, or on the business's return to the inquiry in the previous year adjusted to take account of the likely change in the value of trading over the period.

Note that SABS data quality measures have not been provided for the employment or employee variables.  The employment and employee estimates are largely based on Business Register and Employment Survey (BRES) data, and sampling errors for BRES estimates are provided at a regional and local level, by ONS, at:  http://www.ons.gov.uk/ons/publications/all-releases.html?definition=tcm:77-230512

In addition to sampling errors there is the potential for non-statistical errors which cannot be easily quantified. Examples where these errors may occur are deficiencies in the sampling frame (IDBR) and errors made by respondents in completing the inquiry forms.

For more information on ABS data reliability, please consider the ONS background and technical documents available on-line at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/quality-and-methods/index.html

Revisions

Revisions Policy 

In general, SABS follows the Revisions Policy for the ONS ABS results i.e. the latest results are provisional until the following year when they may be revised as a result of late returns or information received in the course of the following year's inquiry. So, for example, within SABS 2011 the latest results for 2011 are provisional and will be made final when they are re-published within SABS 2012 - at which point they may be revised due to late returns. Likewise the results for 2010 within SABS 2011, have been revised since SABS 2010 and are now final.

Although the general rule is to only revise back one year, if revisions have a significant impact on estimates for Scotland, then we may revise back the entire time series. Significant revisions of this sort, and their treatment within SABS, will be highlighted at the time of the release.

Latest Revisions

SABS 2011

Please note that validation of data returns for 2011 highlighted that a small number of businesses within the Insurance and Reinsurance sector (SIC 65.1 and 65.2) were returning global figures rather than UK only. A revised 2010 estimate (together with new 2011 data) are now available in this publication. However, any global figures reported will remain in 2008 and 2009 published data in line with current Annual Business Survey (ABS) revisions policy. This can have a significant impact on Insurance, reinsurance, professional, scientific and technical activities (Section KM) time series data, as well as overall Totals, in particular local authority areas. Results for this sector are experimental and any comparisons between years should be undertaken with caution.

Major Historical Revisions

SABS 2010

Within industry 46.3 (Wholesale of food, beverages and tobacco), there has been a significant revision to the 2009 data.  This revision was expected as it was identified in the analysis of SABS 2009 that there was an under-reporting of data within the Scottish results for 2008 and 2009.  This under-reporting was a result of business data being inadvertently excluded from the Scottish results in both years.  This error has now been corrected in the 2009 results contained in SABS 2010 – but the 2008 data remain erroneous given the overarching ABS revisions policy of revising back the previous year only. 

SABS 2009

Within industry 20.14 (Manufacture of other organic basic chemicals), a significant downwards revision has been made to the 2008 data, which has an impact on turnover and GVA for this group. This revision was required as it became apparent that previous data submitted was incorrect as it included turnover generated in other European countries. This error has been corrected for the 2008 data onwards.

Within industry 46.3 (Wholesale of food, beverages and tobacco), there is a significant under-reporting of data within the Scottish results for 2008 and 2009. This under-reporting is a result some business data being inadvertently excluded from the Scottish results in both years. This data is included in the overall UK results but not the Scottish results. This error in the Scottish results cannot be amended until the 2010 data and revised 2009 data are published in summer 2012

SABS 2007

Within industry 92.20 (Radio and television activities) a significant revision has been made to 2006 Turnover and GVA. The revision is identified due to changes in the nature of the reporting within the Industry for 2006 onwards. Note that the entire time series for Creative Industries was redefined from SABS 2007 onwards to incorporate this change.

SABS 2006

Within industry 23.20 (Manufacture of refined petroleum products) and 24.14 (Manufacture of other basic organic chemicals) there have been significant revisions to Turnover, Purchases and GVA for both 2005 and 2006. This is due to a large reclassification of a business from Class 23.20 to Class 24.14 that came to light during the processing of the 2006 ABI inquiry. Further, for both 2005 and 2006, there has been an additional upward revision to Class 24.14 to correct underestimation.

Within industry 92.20 (Radio and television activities) a significant revision has been made to 2005 Turnover and GVA data after some overestimation was identified. The overestimation has also been identified for earlier years but in conjunction with current Annual Business Inquiry (ABI) revision policy there will be no revision to published data for years prior to 2005. However, note that the entire time series for Creative Industries was revised back to adjust for this over estimation.

Comparable Data

Comparable Data  

Statistics for the UK, English Government Office Regions, Scotland, Wales and Northern Ireland are available at:

http://www.ons.gov.uk/ons/rel/abs/annual-business-survey/index.html

Other Sources of Economic and Business Statistics

Other Sources of Economic and Business Statistics 

Gross Value Added (GVA)

The SABS results include approximate GVA at 'basic prices'. Gross Value Added (GVA) at basic prices is the output at basic prices minus intermediate consumption at purchaser prices.

There are differences between the ABS approximate measure of Gross Value Added and the GVA measures published in UK and Scottish National Accounts data. It is important to emphasise that ABS GVA does not cover the whole economy and that it does not include all the National Accounting adjustments that reconcile the ABS data with other data sources (especially taxes and subsidies, margins and the 'mixed income' economies).

The quarterly GDP index is the Scottish Government's preferred source for measuring real (inflation-adjusted) GVA change over time – for the Scottish economy as a whole and for broad sectors of the Scottish economy: http://www.scotland.gov.uk/Topics/Statistics/Browse/Economy/PubGDP

The Scottish National Account Project published data series, which incorporates the National Accounting adjustments, is the Scottish Government’s preferred source for current price (non-inflation-adjusted) GVA change over time - for the Scottish economy as a whole and for broad sectors of the Scottish economy: http://www.scotland.gov.uk/Topics/Statistics/Browse/Economy/SNAP

Note that nominal (non-inflation-adjusted) regional GVA estimates are also published by ONS Regional Accounts: http://www.ons.gov.uk/ons/taxonomy/index.html?nscl=Regional+Accounts

ONS has published an article on A Comparison between Annual Business Survey and National Accounts Measures of Value Added at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/quality-and-methods/a-comparison-between-abs-and-national-accounts-measures-of-value-added.pdf

Information on the differences between ABS approximate GVA at 'basic prices' and National Accounts/Regional Accounts GVA is available in the ABS Technical Report published by ONS at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/quality-and-methods/abs-technical-report.pdf

Business Register and Employment Survey

Employee jobs/employment data, largely sourced from the Business Register and Employment Survey (BRES), are provided in the SABS results. These employment estimates are provided in SABS to enable consistent productivity measures to be calculated.  The employee jobs/ employment estimates in SABS will tend to be lower than those published in BRES since BRES has wider industrial coverage than the ABS.  There will also be differences between the employment estimates in BRES and the employment estimates as published in SABS as a result of differences in the samples selected for each survey. 

If employee jobs/employment data by industry only is required (and so not to construct labour productivity measures), then the BRES is the preferred source for Scotland and local areas within Scotland.  The latest BRES data is available at: http://www.ons.gov.uk/ons/publications/all-releases.html?definition=tcm%3A77-230512

Businesses in Scotland

Businesses in Scotland (formerly Scottish Corporate Sector Statistics) is another annual business statistics publication, released by the Scottish Government – the source of which is the IDBR.  The main purpose of this publication is to provide information about the number of enterprises operating in Scotland.  Like SABS, Businesses in Scotland provides estimates of employment and turnover by industry, local authority area and ownership.  However, the employment and turnover estimates are provided in Businesses in Scotland publication as auxiliary variables that enable users to determine what proportion of employment/turnover generated in the economy can be attributed to businesses of different size.  Employment and turnover, as published via Businesses in Scotland, do not relate to a single point in time and can be out of date for some small firms.  For this reason, it is not advisable to compare employment and turnover estimates from Businesses in Scotland over time.  More information on the key differences between Scottish Annual Business Statistics and Businesses in Scotland is available at: http://www.scotland.gov.uk/Topics/Statistics/Browse/Business/SourcesandSuitability/KeyDifferences

ONS Interactive Guide

ONS has published an interactive guide to help statistics users to find statistics on UK businesses. By selecting your topics of interest, the tool will pinpoint publications that should be of interest to you, and provide you with links to more detailed information and the relevant statistical releases.  The interactive guide is available at:

http://www.ons.gov.uk/ons/guide-method/understanding-ons-statistics/business-statistics---interactive-user-guide/index.html 

Regional Capital Expenditure

Regional Capital Expenditure 

It has been established that the estimation of regional capital expenditure is unreliable, and therefore Net Capital Expenditure figures are not now available on Scottish Annual Business Statistics website.

Office for National Statistics (ONS) has provided the following information:

Regional Capital Expenditure

Figures on regional capital expenditure are no longer made available on the ABS website pages. Accurate estimation of regional capital expenditure is dependent on there being a strong correlation between the variable on which any estimation is based, in this case local employment, and the variable for which we are attempting to produce estimates, here regional capital expenditure. It has been established that the relationship between regional employment and regional capital expenditure is, in fact, unreliable.

It will still be possible to obtain regional capital expenditure figures by requesting either standard extracts, for which there is no charge, or special analyses, for which a charge will be made. ONS does not recommend the use of these regional capital expenditure figures but recognises that some users will, nevertheless, wish to have them.

For more information about either of these services, please either email abs@ons.gov.uk or telephone +44 (0)1633 456592

Further information on the regional methodology is contained in an article published in the November 2000 edition of Economic Trends: http://www.ons.gov.uk/ons/rel/elmr/economic-trends--discontinued-/no--564--november-2000/the-development-of-the-annual-business-inquiry.pdf.  Refinements to the methodology have taken place since this article was written; methodological information given on these pages supersedes the Economic Trends article.

If you require Scottish Capital Expenditure figures only, you can alternatively contact the Scottish Government.

Code of Practice

Code of Practice for Official Statistics

This is a National Statistics publication. It has been produced to the high professional standards set out in the Code of Practice for Official Statistics 4 and the Pre-release Access to Official Statistics (Scotland) Order 2008 5

In 2012, the Scottish Annual Business Statistics publication was assessed by the United Kingdom Statistics Authority (UKSA) for compliance against the Code of Practice for Official Statistics. Details of the assessment are available at: Assessment Report 189 - Statistics on Scottish Businesses and Research and Development (96.4 Kb, Pdf document)

The UKSA has designated these statistics as National Statistics, in accordance with the Statistics and Registration Service Act 2007 and signifying compliance with the Code of Practice for Official Statistics. 

Designation can be broadly interpreted to mean that the statistics:

• meet identified user needs;

• are well explained and readily accessible;

• are produced according to sound methods, and

• are managed impartially and objectively in the public interest. 

Once statistics have been designated as National Statistics it is a statutory requirement that the Code of Practice shall continue to be observed. 

A UKSA assessment has also been carried out for the ONS Annual Business Survey statistical publications. Details of the assessment are available at:

Assessment Report 180 - Statistics from the Annual Business Survey (126.8 Kb, Pdf document)

[4] Code of Practice for Official Statistics: http://www.statisticsauthority.gov.uk/assessment/code-of-practice/code-of-practice-for-official-statistics.pdf

[5] Pre-release Access to Official Statistics (Scotland) Order 2008: http://www.opsi.gov.uk/legislation/scotland/ssi2008/pdf/ssi_20080399_en.pdf

Future Developments

Future developments regarding the quality of the ABS data and up-coming SABS data releases are as follows:   

  • The Scottish Government continues to work with ONS to explore what could be done to improve the methodology used to estimate regional net capital expenditure. The historical methodology for estimating regional net capital expenditure is known to be unreliable, leading to its continued exclusion from the ABS regional publications. This topic was discussed at the ABS User Group meeting held in May 2013. Minutes for this meeting to be published at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/management-and-user-engagement/user-group-minutes/index.html
  • The Scottish Government continues to work with ONS to look at whether the constituent purchases breakdown variables (e.g. Purchases of water) could be estimated for Scotland in such a way that they sum at Regional level to overall Total Purchases figure – currently the constituent parts of purchases do not sum to the total. We are looking to rectify this anomaly so that more detailed ABS data can be made available for Scotland on a consistent basis
  • One of the key actions following the UKSA assessments, of the SABS and the ONS ABS publications, is to improve the timeliness of the ABS publications.  SABS data are currently published 20 months after the reference period covered by the data.  The Scottish Government continues to work with the ONS on changing the publication process to reduce this time lag for future SABS releases. ONS have published a progress note on this work available at: http://www.ons.gov.uk/ons/guide-method/method-quality/specific/business-and-energy/annual-business-survey/quality-and-methods/review-of-abs-timeliness/index.html
  • ONS is currently undertaking analysis to calculate regional standard errors. Updates on progress will be provided to users in due course. 

User Engagement

User Engagement 

If you would like to be kept informed about ongoing developments with regards to the SABS publication and future releases of SABS data, please register to receive updates via Scotstat (under Economy topic pick Business and Industry and/or Productivity).

There is also the ScotStat Scottish Economic Statistics Consultation Group (SESCG) – more information on the group is available at: http://www.scotland.gov.uk/Topics/Statistics/Browse/Economy/ScotStat/comms. If you would like to join SESCG or provide feedback on the SABS publication, please contact us at:

Business and Enterprise Statistics
Office of the Chief Economic Adviser
5 Atlantic Quay
150 Broomielaw
Glasgow G2 8LU

Telephone: 0300 244 6802

e-mail: industrystatistics@scotland.gsi.gov.uk

There are also ONS-led user communities that may be of interest to SABS users, details of these are available at: http://www.scotland.gov.uk/Topics/Statistics/Browse/Business/scotstat