Reference metadata describe statistical concepts and methodologies used for the collection and generation of data. They provide information on data quality and, since they are strongly content-oriented, assist users in interpreting the data. Reference metadata, unlike structural metadata, can be decoupled from the data.
Annual Business Survey - Surveys and Economic Indicators Division
1.3. Contact name
Confidential because of GDPR
1.4. Contact person function
Confidential because of GDPR
1.5. Contact mail address
Office for National Statistics Government Buildings Cardiff Road Newport NP10 8XG
1.6. Contact email address
Confidential because of GDPR
1.7. Contact phone number
Confidential because of GDPR
1.8. Contact fax number
Confidential because of GDPR
2.1. Metadata last certified
10 February 2020
2.2. Metadata last posted
10 February 2020
2.3. Metadata last update
10 February 2020
3.1. Data description
Structural business statistics (SBS) describes the structure, conduct and performance of economic activities, down to the most detailed activity level (several hundred economic sectors).
SBS covers all activities of the non-financial business economy with the exception of agricultural activities and personal services. Limited information is available on banking, insurance and pension funds.
Main characteristics (variables) of the SBS data category:
Business demographic variables (e.g. Number of enterprises)
"Output related" variables (e.g. Turnover, Value added)
"Input related" variables: labour input (e.g. Employment, Hours worked); goods and services input (e.g. Total of purchases); capital input (e.g. Material investments)
3.2. Classification system
Statistical Classification of Economic Activities in the European Community (NACE): NACE Rev.1 was used until 2001, NACE Rev. 1.1 since 2002, and NACE Rev 2 is used from 2008 onwards. Key data were double reported in NACE Rev.1.1 and NACE Rev.2 for 2008. From 2009 onwards, only NACE Rev.2 data are available.
The regional breakdown of the EU Member States is based on the Nomenclature of Territorial Units for Statistics (NUTS). Detailed information about the consecutive NUTS Regulations can be found at Eurostat's website
The SBS coverage was limited to Sections C to K of NACE Rev.1.1 until 2007. Starting from the reference year 2008 data is available for Sections B to N and Division S95 of NACE Rev.2. With 2013 as the first reference year information is published on NACE codes K6411, K6419 and K65 and its breakdown.
ONS sampling is done at Respondent Unit (RU) level rather than at Enterprise Unit (EU) level. This is due to historic reasons and is a process that ONS are unable to change due to the current systems and technology used in holding company/businesses information on the business register. The ONS business register is the Inter-Departmental Business Register (IDBR). The IDBR holds all business information and has a large and experienced team of business profilers who make changes to business structures on a regular basis based on current knowledge and meetings with businesses. These are often the large Multi-National Enterprises (MNEs) that have complex structures in place for reporting purposes.
When analysing whether the data held at RU level corresponds to EU level it was assessed that this was true for 98% of the businesses held on the IDBR – the 2% mismatch represented those large MNEs where multiple RUs where held for one Enterprise.
As an example we can consider a large supermarket chain where they typically have separate RUs for Retail, Wholesale, Distribution, Transport, Catering services, financial services and mobile services etc. All data would be reported according to their management information and company accounts – at an RU or activity/SIC level. In order to obtain data for the Enterprise a bespoke process was implemented in a special analysis system whereby all RU level data were aggregated up to the Enterprise level based on the dominant employment – so in the case of our large supermarket the majority of employees work in the Retail sector. All data would therefore be reported under SIC 47 retail. This was repeated for each MNE where there was no a like for like match at RU to EU level.
The introduction of the Large Cases Unit means that better information can be obtained on MNEs reporting structures and changes can be made to the IDBR on an on-going basis to ensure better quality data are collected on the Enterprise as a whole.
3.6. Statistical population
All United Kingdom businesses registered for either Value Added Tax (VAT) or Pay as You Earn (PAYE).
3.7. Reference area
United Kingdom - Regions of England, Scotland, Wales and Northern Ireland.
3.8. Coverage - Time
2001-2017
3.9. Base period
Not applicable.
Number of enterprises and number of local units are expressed in units.
Monetary data are expressed in millions of €.
Employment variables are expressed in units.
Per head values are expressed in thousands of € per head.
Ratios are expressed in percentages.
2017
6.1. Institutional Mandate - legal acts and other agreements
Business surveys operating within the United Kingdom are governed under the Statistics of Trade Act (1947). This states that tables should not be published that would disclose any information relating to an individual business, unless there is expressed consent in writing from that business.
7.2. Confidentiality - data treatment
For tables of total values published by ABS, there are two criteria which must be met in order for the published value to be deemed non-disclosive:
minimum threshold rule: this rule states that there must be at least n enterprise groups in a cell
p% rule: this rules state that the total contribution of the largest contributor(s) to the cell aggregated total must be less than p% of the total in that cell.
8.1. Release calendar
Annual Business Survey releases for any given survey year;
Access to results via an online database is not available at the current time.
10.4. Dissemination format - microdata access
The Approved Researcher Scheme is used by the Office for National Statistics (ONS) to grant access to data that cannot be published openly, for statistical research purposes, as permitted by the Statistics and Registration Service Act 2007 (SRSA).
To access data in this way, an individual must hold ONS Researcher Accreditation and have their research proposal approved by the ONS Microdata Release Panel, on behalf of the National Statistician. The processes and criteria used within the Approved Researcher Scheme were revised in 2016.
10.5. Dissemination format - other
None
10.6. Documentation on methodology
The Annual Business Survey (ABS) - Technical Report is available on the ONS Website (electronic version).
Annual Business Survey data used to create the SBSR submission meets the main quality requirements for:
Concept 12. Relevance
Concept 13. Accuracy
Concept 14. Timeliness and punctuality
Concept 15. Coherence and comparability
More detailed information is described under the appropriate concept (12 to 15).
There are no principal quality problems.
12.1. Relevance - User Needs
Internal users
National and Regional Accounts
The production of current and constant price Supply Use tables, which show the sales and purchases relationships between consumers and producers by industry; estimation of GDP on a regional basis.
External users
Eurostat
In order to meet the Structural Business Statistics Regulation requirements for annual structural statistics to inform and monitor European Union policy; contribution to articles on SBSR.
In order to meet the Structure and Activity of Foreign Affiliates Regulation requirements for annual inwards FATS statistics to inform and monitor European Union policy;
Scottish Executive
Scottish Annual Business Statistics; Scottish Government policy and use made of ABS in Scottish Input-Output Tables which in turn contributes to calculation of Scottish GVA weights.
Department of Finance and Personnel Northern Ireland (DFPNI)
GVA per head compared to other areas of the UK; tracking performance of the NI economy; calculating the cost of doing business in NI.
Department for Business, Innovation and Skills (BIS)
To compare efficiency of companies who apply for grants; if problems occur within a particular industry; when new government interest arises within a particular sector; to distinguish bought-in goods from own production; Regional Economic Indicators Publication
Department of Work and Pensions (DWP)
To measure the impact of 2010 Pensions legislation at wages costs/profits/investment. DWP wish to measure the way businesses change strategies to cover the new legislation. i.e. whether they absorb the costs or pass on costs to the customer etc.; to analyse looking at the traditionally low pension participation companies.
Department for Environment, Food and Rural Affairs (DEFRA)
Rural Payments Agency (RPA)
Analysis of industry trends by using aGVA for the part of Agriculture covered by ABS (in proportion to the total GVA figure for Agriculture published in the Blue Book).
National Fraud Authority (Home Office)
ABS private sector total purchases was used in relation to producing a fraud loss estimate on procurement fraud for inclusion in the publication of the Annual Fraud Indicator (AFI) 2012
Retail -British Retail Consortium
Assessing the market conditions.
Business Advisors and Consultancy
Understanding trends in industry sectors and companies in Scotland in comparison to GB and the UK; sizing IT expenditure; information for a report; number of enterprises and outlets at a detailed industry level; GVA per employee data by sector.
12.2. Relevance - User Satisfaction
Users are generally satisfied with the range of variables and industry coverage which goes beyond that required by the SBS.
We have been collecting feedback from a wide range of users (researchers, policy makers, central government, local government, academia), through a range of activities. Feedback responses contained both praise and areas where the users believed improvements could be made. In particular, positive comments were received regarding the ABS team, deeming them both responsive and helpful, with the team adjusting processes in order to meet users' specific needs.
12.3. Completeness
Data is complete apart from the non-supply of V18110 in Series 4A - the UK does not collect this variable for the construction sector.
13.1. Accuracy - overall
The Annual Business Survey (ABS) meets its legal requirements for statistical accuracy. However, as in all surveys, the estimates from the ABS are subject to various sources of error. Provisional data are published at t+10 and Revised at t+17.
13.2. Sampling error
The results obtained for any single sample may, by chance, vary from the true values for the population but the variation would be expected to be zero on average over a number of repeats of the survey.
We expect 95% of our estimates for a variable to be within two standard errors of the true unknown value for the population. The closer the standard error to zero, the more precise the estimate.
Sampling errors for the ABS are available down to 4-digit Standard Industrial Classification 2007 class level for the following variables:
Total turnover
Approximate gross value added
Total purchases of goods and services
Total net capital expenditure
13.3. Non-sampling error
Imputation techniques are used to estimate the value of the missing data due to non-response.
Imputations are done mainly for large businesses such as those in size band 6 (250 or more employment) and businesses with low employment but high turnover. Imputation is generally for businesses in these groups that do not respond to any part of the survey.
For non-responding small businesses, such as those in size bands 1 (0-9 employment), 2 (10-19 employment), and 3 (20-49 employment), imputation is not carried out, and totals are estimated using adjusted weights.
A manual exercise is also undertaken at certain points throughout the data collection cycle to identify industries with a low response. Non-responding businesses in these industries are identified as critical responders and are contacted.
If businesses who have received questionnaires have not responded by the deadline, up to three reminder letters can be sent.
Businesses are encouraged to complete ONS surveys to enable the production of quality outputs. This is achieved through effective response chasing, and by addressing respondents’ issues in a timely and efficient manner. The ONS has a strategy in place which targets the economically most important businesses selected.
Responses are followed up in the following order of priority:
businesses with employment of more than 1,000
businesses with an expected turnover of more than £150 million - this ensures that businesses with smaller employment and large turnover are covered
businesses sent long questionnaires - this ensures good coverage for the expansion of the short questionnaires
short questionnaires
ABS carries out enforcement action under the Statistics of Trade Act 1947. Enforcement action is used to maintain response rates, and hence the quality of the survey. It is used as a last resort, after attempts to encourage businesses to complete the survey through telephone calls have been made, and a reminder or Chief Executive Letter has been sent.
Weights are not used for calculating non-response rate.
The procedure used for estimation and non-response is thought to have very little effect on bias.
We consider our estimates to be based on sound methodology and have no plans for change in the near future.
Out of scope units are identified during universe checks carried out following survey sampling. Once identified they are deleted from the survey universe.
14.1. Timeliness
Data-collection phase
From 12/2017
Post-collection phase
Provisional results - 10/2018
Revised results - 03/2019
Dissemination
Provisional results – 11/2018
Revised results – 05/2019
14.2. Punctuality
No delays
15.1. Comparability - geographical
Differences between Great Britain and Northern Ireland methodology.
The Department for Finance and Personnel Northern Ireland (DFPNI), rather than ONS, conduct the ABS in Northern Ireland. The survey process in Northern Ireland is similar but not exactly the same as that for Great Britain. For example, DFPNI despatch questionnaires in March, after ONS despatch to businesses in Great Britain in January/February. ONS receive reporting unit and local unit level data for businesses sampled by DFPNI in September and February of each survey year. These Northern Ireland reporting unit data are then processed together with the Great Britain data collected by ABS to produce estimates for the whole of the UK at various industry aggregations, as well as producing regional estimates. DFPNI also process the data to produce their own estimates for Northern Ireland. These differ from the ONS estimates for Northern Ireland for a number of reasons:
Calculation of the a-weights The ONS National Results System computes the a-weights (design weights) for all United Kingdom data using the sample design of the Great Britain sample; and while the DFPNI sample design used to have the same design as ONS prior to 2008, DFPNI changed their design in 2008, and again in 2009. The new DFPNI sample design is quite different from that used by the ABS Great Britain - it is similar to that used in the Business Register and Employment Survey. Therefore, the design weights computed in the ONS system for Northern Ireland units can be quite different from those computed in the DFPNI system.
Calculation of the g-weights
The ONS National Results System computes two sets of g-weights: one based on register turnover and another based on register employment. The latter is used for employment costs, whereas the former is used for all the other variables. The Regional System computes g-weights based on local unit employment. In the Northern Ireland methodology, register employment is used for all variables in the calibration in their national system. In their regional system, the g-weights are computed with respect to local unit register employment but using a different calibration method to that used in the ONS regional system.
Regional apportionment
ONS collects all ABS data at reporting unit level; the regional system apportions reporting unit returns between local units using factors obtained from multiple regression models. DFPNI collects turnover data at local unit level, but does not use these data in their apportionment; their current apportionment is based on the median of per head returns. When Northern Ireland data are processed in the ONS system, new apportioned local unit values, based on the ONS methodology, are obtained and used to produce estimates. Also, ONS and DFPNI use different methods to deal with local units operating in industries that are out of scope.
DFPNI does not collect data for all the variables included in the Great Britain questionnaire; in the ONS system, values are derived for the missing variables using a model, and these values contribute towards the estimation of derived variables.
15.2. Comparability - over time
Comparable time series – 1996-2007 ; 2008-2015 ; 2016-2017
The UK believes there should be breaks within the time series shown above.
The change in the NACE rev 2 code resulted in data for 2008 onwards being reported on a slightly different structure to that of NACE rev 1.2 (from 1996 – 2007)
Data for 1996-2015 were supplied at the UK Reporting Unit level, from 2016 data was supplied at the UK Enterprise level.
15.3. Coherence - cross domain
Differences between UK regional data and national data are due to UK regional data being based on local unit NACE classification and national data on reporting/enterprise unit classification.
15.4. Coherence - internal
Aggregates are consistent with their main sub-aggregates (e.g. the total for different size classes, NACE, NUTS, CPA etc.)
Not available
17.1. Data revision - policy
The UK’s revision policy is not to revise beyond the original delivery to Eurostat however, if a major error has been detected and will affect the overall data quality the UK will consider revision.
17.2. Data revision - practice
Not applicable
18.1. Source data
The Annual Business Survey (ABS) is a sample is designed as a stratified random sample from the sampling frame held on the Inter-Departmental Business Register (IDBR). The IDBR is composed of legal units registered for Value Added Tax (VAT) or Pay As You Earn (PAYE) schemes. The inquiry population is stratified by NACE rev 2, employment, and country using the information from the register. The survey results are grossed up to the register population, so that they relate to all active UK businesses on the IDBR for the sectors covered.
Stratification criteria; Activity,Employment size class, Region
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 sample is selected using the Neyman Optimal allocation scheme.
For most businesses with employment of 0-9 Osmotherly rules apply. These rules state that when a business with 0-9 employment has been selected in a survey, it will only be selected for a single year, and it will not be reselected for at least three years following selection.
The sample design is constructed so that a sample for a cell will be selected for two years only, and the units in that sample will largely not be re-selected for at least two years after that selection. The random sample selection uses the permanent random number (PRN), the unique nine digit identifier which is randomly assigned to each unit when it is added to the IDBR. The sample from each cell is constructed from the required number of units with consecutive PRNs in that cell. For ABS, each sample is selected for two years, and there is a year-to-year overlap of half the sample. That is, in any year, half of the sample will be newly-selected, and half will have been selected in the previous year as well.
For 2017 the sample for sectors covered by the SBSR was 61500.
Other than for a minority of larger business or businesses which have a more complex structure, the reporting unit is the same as the enterprise. For this reason, ABS reporting unit counts are presented as enterprise counts.
The dominant activity of a reporting unit is based on employment and calculated using a 'top down' method on a digit by digit basis for multiple activity enterprises. For example, the following four local units have SIC codes and employment as listed:
Section/ SIC 2007
Employment
C 18 20 1
50
C 26 11 0
20
C 26 12 0
10
C 26 40 0
25
The largest employment appears to be in SIC 18201 (50), but the IDBR first compares at section (letter “C”), then division (first two digits) and so on. In this case division 26 is largest (55). This comparison cascades further through group (261 has 30 employment, compared to 264 having 25) and finally class and sub-class to give a dominant SIC of 26110 (20).
The classification of businesses on the Inter-Departmental Business Register (IDBR) is updated annually. The Business Employment Register Survey (BRES) provides a ‘future local unit results’ file to the Business Register Unit (BRU) containing employees and classification data, which is loaded onto the IDBR in July of each year. In addition to this, classification details for the production sector are provided by PRODCOM (Products of the European Community) and also files are received from the Annual Business Survey (ABS), this data is also loaded onto the IDBR. For Classifications updating there are certain priority rules to be followed. Except for BRES the other updating sources are bottom down, starting at the Enterprise. The priority for classifications updating is as follows:
BPT – Business Profiling Team
Prodcom / Retail Surveys / Financial Surveys
ABS - Annual Business Survey
BRES – Business Register Employment Survey
MPS – Monthly Production Survey
Other ONS surveys
CISTATS – Construction Industry Statistics Address File
VAT – Value Added Tax
PAYE – Pay-As-You-Earn
18.2. Frequency of data collection
Annual data collection
18.3. Data collection
The Annual Business Survey (ABS) sample selection for Great Britain for a given year is carried out in November of that year. Questionnaires are then printed for a staggered despatch between January and February the following year. The questionnaires are required to be returned to the Office for National Statistics (ONS) within the two months following the respondents business year end.
In order to meet the minimum accuracy standards required by its users, the ABS questionnaire response rate target is at least 64% of businesses by the end of August and 74% by the end of October.
The Department for Finance and Personnel Northern Ireland (DFPNI), rather than ONS, conduct the ABS in Northern Ireland. The survey process in Northern Ireland is similar but not exactly the same as that for Great Britain. For example, DFPNI despatch questionnaires in March, after ONS despatch to businesses in Great Britain in January/February. ONS receive reporting unit and local unit level data for businesses sampled by DFPNI in September and February of each survey year. These Northern Ireland reporting unit data are then processed together with the Great Britain data collected by ABS to produce estimates for the whole of the UK at various industry aggregations, as well as producing regional estimates.
Businesses are encouraged to complete ONS surveys to enable the production of quality outputs. This is achieved through effective response chasing, and by addressing respondents‟ issues in a timely and efficient manner. If businesses who have received questionnaires have not responded by the deadline, up to three reminder letters can be sent.
The ONS has a strategy in place which targets the economically most important businesses selected. A manual exercise is also undertaken at certain points throughout the data collection cycle to identify industries with a low response.
ABS carries out enforcement action under the Statistics of Trade Act 1947. Enforcement action is used to maintain response rates, and hence the quality of the survey.
18.4. Data validation
The following checks are applied to the data;
completeness checks (data integrity rules)
validity checks (internal consistency)
plausibility checks
When responses are received, they are entered into the processing system electronically.
Step 1: Questionnaires are electronically scanned into the data store.
Step 2: data are then transferred to the processing system. Initial validation checks are carried out on the returned data.
Step 3: After the initial validation further editing, outlined below, is carried out.
These include:
automatic totalling: for the key variables total turnover, total employment, and total purchases, the sum of the breakdown components on the long questionnaire are checked against the total values entered.
automatic rounding: total turnover is requested to the nearest thousand pounds. Where an actual (that is, non-rounded) total turnover is returned, it is common for the responses to other questions to also be returned as actual values, and these are then automatically rounded to the nearest thousand pounds.
The automatic correction tests described above are only possible if previous period data are available, and corrections are within tolerated limits compared to previous data.
Date tests are then carried out.
Selective editing (SELEKT Tool): SELEKT is a generic selective editing tool. It allows each response to be scored according to a set of agreed criteria which attempts to high scores to the errors that will have the largest influence on estimates, and 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 score can be split into three parts:
Suspicion of an error/mistake
Potential impact on estimate
Importance of the variable, for example, issues with key variables such as turnover, purchases and employment costs will be given a higher score than those less important variables such as stocks and capital expenditure
Step 4: When all the data have passed the required tests, and validation failures have been edited, the data set is considered "clean", and industry estimates for publication can be calculated.
Step 5: The industry estimates are then subject to further quality checks.
Contact is made with the customer and if necessary amendments made and/or data confirmed.
18.5. Data compilation
The imputation approach was determined through simulation, by suppressing real data and running imputation using median ratios which result in imputed values close to the corresponding true values.
The imputation method used is based upon the principle of ratio imputation where an imputation link is calculated using information from similar business within the same industry and size band. There are various constraints which are applied to calculating these links. The constraints on the responders (in the industry concerned) used to calculate the links are that they must have:
employment of more than 100
returned turnover greater than 0
data available for the previous and current periods
Case 1: businesses that have responded in the previous period
For example, if business X has not returned a value for total turnover in the current period, but did in the previous period, businesses in the same sector that have returned a value for total turnover in the current period are considered.
Of these, those who have returned a value for total turnover for both the current and the previous periods are identified. The ratio of the current value of total turnover to the previous value for total turnover is then calculated.
For each responding business to both periods:
The median ratio value, referred to as the imputation link, is then calculated and applied to the returned value for the non-responding business in the previous period.
Case 2: businesses that are first-time responders
In the example below, business X is a first-time responder and so does not have any returned value for the previous period. In these cases the IDBR turnover of businesses is used in the calculation of the imputed value for X.
When calculating median ratios as described above, the calculation routine will attempt to identify respondents at a 4-digit SIC level. Should for some reason (e.g. insufficient number of businesses) there be no median at this level, the routine will try to use a median calculated at 3-digit SIC level. If this fails to find a median, the routine will try at the 2-digit SIC level.
In order to calculate the estimates for an entire population from data collected from a sample, ABS uses standard statistical weighting methods. Essentially the results received from the sample are multiplied by two weights:
the a-weight, also known as the design weight, which accounts for the sample design so that a business’s probability of selection is properly reflected. So, for example, a business with a small probability of being selected for the survey will have a large design weight.
the g-weight, or calibration factor, makes a correction for any potential bias in the selected sample. For example, in a random selection of five businesses out of a population of ten, it is possible that the five businesses selected have, by chance, higher values for the variables of interest than the non-sampled businesses. If no correction is made, the population total would be over-estimated. Auxiliary information, i.e. information not collected by the survey, which acts as a proxy for the variable of interest, is used to correct for this effect. The ratio of the actual population total for the auxiliary variable to the population total estimated from the sample’s auxiliary variables is calculated, and this is called the g-weight. For ABS, the auxiliary variables are the IDBR employment and turnover, with the choice dependent on the variable being estimated.
The weighted value is then:
weighted value = returned value of the variable * a-weight * g-weight
Estimates of population totals are then found by simply summing the weighted values over the whole sample
18.6. Adjustment
No correction is applied to convert reference year data to calendar year.
No further comments
Structural business statistics (SBS) describes the structure, conduct and performance of economic activities, down to the most detailed activity level (several hundred economic sectors).
SBS covers all activities of the non-financial business economy with the exception of agricultural activities and personal services. Limited information is available on banking, insurance and pension funds.
Main characteristics (variables) of the SBS data category:
Business demographic variables (e.g. Number of enterprises)
"Output related" variables (e.g. Turnover, Value added)
"Input related" variables: labour input (e.g. Employment, Hours worked); goods and services input (e.g. Total of purchases); capital input (e.g. Material investments)
ONS sampling is done at Respondent Unit (RU) level rather than at Enterprise Unit (EU) level. This is due to historic reasons and is a process that ONS are unable to change due to the current systems and technology used in holding company/businesses information on the business register. The ONS business register is the Inter-Departmental Business Register (IDBR). The IDBR holds all business information and has a large and experienced team of business profilers who make changes to business structures on a regular basis based on current knowledge and meetings with businesses. These are often the large Multi-National Enterprises (MNEs) that have complex structures in place for reporting purposes.
When analysing whether the data held at RU level corresponds to EU level it was assessed that this was true for 98% of the businesses held on the IDBR – the 2% mismatch represented those large MNEs where multiple RUs where held for one Enterprise.
As an example we can consider a large supermarket chain where they typically have separate RUs for Retail, Wholesale, Distribution, Transport, Catering services, financial services and mobile services etc. All data would be reported according to their management information and company accounts – at an RU or activity/SIC level. In order to obtain data for the Enterprise a bespoke process was implemented in a special analysis system whereby all RU level data were aggregated up to the Enterprise level based on the dominant employment – so in the case of our large supermarket the majority of employees work in the Retail sector. All data would therefore be reported under SIC 47 retail. This was repeated for each MNE where there was no a like for like match at RU to EU level.
The introduction of the Large Cases Unit means that better information can be obtained on MNEs reporting structures and changes can be made to the IDBR on an on-going basis to ensure better quality data are collected on the Enterprise as a whole.
All United Kingdom businesses registered for either Value Added Tax (VAT) or Pay as You Earn (PAYE).
United Kingdom - Regions of England, Scotland, Wales and Northern Ireland.
2017
The Annual Business Survey (ABS) meets its legal requirements for statistical accuracy. However, as in all surveys, the estimates from the ABS are subject to various sources of error. Provisional data are published at t+10 and Revised at t+17.
Number of enterprises and number of local units are expressed in units.
Monetary data are expressed in millions of €.
Employment variables are expressed in units.
Per head values are expressed in thousands of € per head.
Ratios are expressed in percentages.
The imputation approach was determined through simulation, by suppressing real data and running imputation using median ratios which result in imputed values close to the corresponding true values.
The imputation method used is based upon the principle of ratio imputation where an imputation link is calculated using information from similar business within the same industry and size band. There are various constraints which are applied to calculating these links. The constraints on the responders (in the industry concerned) used to calculate the links are that they must have:
employment of more than 100
returned turnover greater than 0
data available for the previous and current periods
Case 1: businesses that have responded in the previous period
For example, if business X has not returned a value for total turnover in the current period, but did in the previous period, businesses in the same sector that have returned a value for total turnover in the current period are considered.
Of these, those who have returned a value for total turnover for both the current and the previous periods are identified. The ratio of the current value of total turnover to the previous value for total turnover is then calculated.
For each responding business to both periods:
The median ratio value, referred to as the imputation link, is then calculated and applied to the returned value for the non-responding business in the previous period.
Case 2: businesses that are first-time responders
In the example below, business X is a first-time responder and so does not have any returned value for the previous period. In these cases the IDBR turnover of businesses is used in the calculation of the imputed value for X.
When calculating median ratios as described above, the calculation routine will attempt to identify respondents at a 4-digit SIC level. Should for some reason (e.g. insufficient number of businesses) there be no median at this level, the routine will try to use a median calculated at 3-digit SIC level. If this fails to find a median, the routine will try at the 2-digit SIC level.
In order to calculate the estimates for an entire population from data collected from a sample, ABS uses standard statistical weighting methods. Essentially the results received from the sample are multiplied by two weights:
the a-weight, also known as the design weight, which accounts for the sample design so that a business’s probability of selection is properly reflected. So, for example, a business with a small probability of being selected for the survey will have a large design weight.
the g-weight, or calibration factor, makes a correction for any potential bias in the selected sample. For example, in a random selection of five businesses out of a population of ten, it is possible that the five businesses selected have, by chance, higher values for the variables of interest than the non-sampled businesses. If no correction is made, the population total would be over-estimated. Auxiliary information, i.e. information not collected by the survey, which acts as a proxy for the variable of interest, is used to correct for this effect. The ratio of the actual population total for the auxiliary variable to the population total estimated from the sample’s auxiliary variables is calculated, and this is called the g-weight. For ABS, the auxiliary variables are the IDBR employment and turnover, with the choice dependent on the variable being estimated.
The weighted value is then:
weighted value = returned value of the variable * a-weight * g-weight
Estimates of population totals are then found by simply summing the weighted values over the whole sample
The Annual Business Survey (ABS) is a sample is designed as a stratified random sample from the sampling frame held on the Inter-Departmental Business Register (IDBR). The IDBR is composed of legal units registered for Value Added Tax (VAT) or Pay As You Earn (PAYE) schemes. The inquiry population is stratified by NACE rev 2, employment, and country using the information from the register. The survey results are grossed up to the register population, so that they relate to all active UK businesses on the IDBR for the sectors covered.
Stratification criteria; Activity,Employment size class, Region
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 sample is selected using the Neyman Optimal allocation scheme.
For most businesses with employment of 0-9 Osmotherly rules apply. These rules state that when a business with 0-9 employment has been selected in a survey, it will only be selected for a single year, and it will not be reselected for at least three years following selection.
The sample design is constructed so that a sample for a cell will be selected for two years only, and the units in that sample will largely not be re-selected for at least two years after that selection. The random sample selection uses the permanent random number (PRN), the unique nine digit identifier which is randomly assigned to each unit when it is added to the IDBR. The sample from each cell is constructed from the required number of units with consecutive PRNs in that cell. For ABS, each sample is selected for two years, and there is a year-to-year overlap of half the sample. That is, in any year, half of the sample will be newly-selected, and half will have been selected in the previous year as well.
For 2017 the sample for sectors covered by the SBSR was 61500.
Other than for a minority of larger business or businesses which have a more complex structure, the reporting unit is the same as the enterprise. For this reason, ABS reporting unit counts are presented as enterprise counts.
The dominant activity of a reporting unit is based on employment and calculated using a 'top down' method on a digit by digit basis for multiple activity enterprises. For example, the following four local units have SIC codes and employment as listed:
Section/ SIC 2007
Employment
C 18 20 1
50
C 26 11 0
20
C 26 12 0
10
C 26 40 0
25
The largest employment appears to be in SIC 18201 (50), but the IDBR first compares at section (letter “C”), then division (first two digits) and so on. In this case division 26 is largest (55). This comparison cascades further through group (261 has 30 employment, compared to 264 having 25) and finally class and sub-class to give a dominant SIC of 26110 (20).
The classification of businesses on the Inter-Departmental Business Register (IDBR) is updated annually. The Business Employment Register Survey (BRES) provides a ‘future local unit results’ file to the Business Register Unit (BRU) containing employees and classification data, which is loaded onto the IDBR in July of each year. In addition to this, classification details for the production sector are provided by PRODCOM (Products of the European Community) and also files are received from the Annual Business Survey (ABS), this data is also loaded onto the IDBR. For Classifications updating there are certain priority rules to be followed. Except for BRES the other updating sources are bottom down, starting at the Enterprise. The priority for classifications updating is as follows:
BPT – Business Profiling Team
Prodcom / Retail Surveys / Financial Surveys
ABS - Annual Business Survey
BRES – Business Register Employment Survey
MPS – Monthly Production Survey
Other ONS surveys
CISTATS – Construction Industry Statistics Address File
VAT – Value Added Tax
PAYE – Pay-As-You-Earn
Annual
Data-collection phase
From 12/2017
Post-collection phase
Provisional results - 10/2018
Revised results - 03/2019
Dissemination
Provisional results – 11/2018
Revised results – 05/2019
Differences between Great Britain and Northern Ireland methodology.
The Department for Finance and Personnel Northern Ireland (DFPNI), rather than ONS, conduct the ABS in Northern Ireland. The survey process in Northern Ireland is similar but not exactly the same as that for Great Britain. For example, DFPNI despatch questionnaires in March, after ONS despatch to businesses in Great Britain in January/February. ONS receive reporting unit and local unit level data for businesses sampled by DFPNI in September and February of each survey year. These Northern Ireland reporting unit data are then processed together with the Great Britain data collected by ABS to produce estimates for the whole of the UK at various industry aggregations, as well as producing regional estimates. DFPNI also process the data to produce their own estimates for Northern Ireland. These differ from the ONS estimates for Northern Ireland for a number of reasons:
Calculation of the a-weights The ONS National Results System computes the a-weights (design weights) for all United Kingdom data using the sample design of the Great Britain sample; and while the DFPNI sample design used to have the same design as ONS prior to 2008, DFPNI changed their design in 2008, and again in 2009. The new DFPNI sample design is quite different from that used by the ABS Great Britain - it is similar to that used in the Business Register and Employment Survey. Therefore, the design weights computed in the ONS system for Northern Ireland units can be quite different from those computed in the DFPNI system.
Calculation of the g-weights
The ONS National Results System computes two sets of g-weights: one based on register turnover and another based on register employment. The latter is used for employment costs, whereas the former is used for all the other variables. The Regional System computes g-weights based on local unit employment. In the Northern Ireland methodology, register employment is used for all variables in the calibration in their national system. In their regional system, the g-weights are computed with respect to local unit register employment but using a different calibration method to that used in the ONS regional system.
Regional apportionment
ONS collects all ABS data at reporting unit level; the regional system apportions reporting unit returns between local units using factors obtained from multiple regression models. DFPNI collects turnover data at local unit level, but does not use these data in their apportionment; their current apportionment is based on the median of per head returns. When Northern Ireland data are processed in the ONS system, new apportioned local unit values, based on the ONS methodology, are obtained and used to produce estimates. Also, ONS and DFPNI use different methods to deal with local units operating in industries that are out of scope.
DFPNI does not collect data for all the variables included in the Great Britain questionnaire; in the ONS system, values are derived for the missing variables using a model, and these values contribute towards the estimation of derived variables.
Comparable time series – 1996-2007 ; 2008-2015 ; 2016-2017
The UK believes there should be breaks within the time series shown above.
The change in the NACE rev 2 code resulted in data for 2008 onwards being reported on a slightly different structure to that of NACE rev 1.2 (from 1996 – 2007)
Data for 1996-2015 were supplied at the UK Reporting Unit level, from 2016 data was supplied at the UK Enterprise level.
