| National Statistic
| Survey name
||Annual Purchases Survey|
| Data collection
||Sample of around 31,000 businesses selected from the Inter-Departmental Business Register|
| How compiled
| Geographic coverage
This quality and methodology report contains information on the quality characteristics of the data (including the five European Statistical System dimensions of quality) as well as the methods used to create it.
The information in this report will help you to:
understand the strengths and limitations of the data
learn about existing uses and users of the data
reduce the risk of misusing data
help you to decide suitable uses for the data
understand the methods used to create the data
The Annual Purchases Survey (APS) provides detail on the energy, services, goods and materials used up or transformed in the production process and running of UK businesses, otherwise referred to as intermediate consumption.
The APS specifically excludes capital investment (including fixed assets), staff costs, goods and services bought for resale without further processing.
The original Purchases Survey ran from the 1950s to 2006 (with the final reference period being 2004); it was reintroduced from the 2015 reference period.
The APS product-level information is used in supply and use tables (SUTs), which are an integral part of the measurement of gross domestic product (GDP); data from the reintroduced survey will be included for the first time in Blue Book 2019.
The APS covers a large element of the economy, with some notable exceptions such as public administration.
The Annual Purchases Survey (APS) was reinstated by Office for National Statistics (ONS) in 2015 to meet a range of user demands and to fulfil the recommendations for its reinstatement from two independent reviews; one by Dame Kate Barker and Art Ridgeway (PDF, 570KB) and the other by Professor Sir Charles Bean. A previous survey, entitled the Purchases Inquiry, was suspended in 2006 to reduce ONS costs and burden on UK businesses (final reference period being 2004). However, given the survey provides important information on the products that UK businesses purchase, it was decided that it should be reintroduced.
The primary aim of the APS is to provide detail on the goods and services used in the production process and running of UK businesses, otherwise referred to as intermediate consumption. This product-level information is used in supply and use tables (SUTs), which are an integral part of the measurement of gross domestic product (GDP). The reintroduction of this survey will help ONS to adhere to international best practice outlined in European System of Accounts: ESA 2010 and Balance of Payments Manual: BPM6. The APS collects information on companies’ intermediate consumption, a national accounts concept defined within the ESA 2010 manual as:
“Intermediate consumption consists of goods and services consumed as inputs by a process of production, excluding fixed assets whose consumption is recorded as consumption of fixed capital. The goods and services are either transformed or used up by the production process.”
History of the Annual Purchases Survey
The original Purchases Inquiry ran from the 1950s to 2006. Data were collected at five-yearly intervals, then annually from 1999 onwards. The sample size and industry coverage was expanded between 1999 and 2001, from 3,000 businesses (covering partial production, distribution and sales industries) to 28,000 (covering full production, construction, distribution and services industries).
In 2006, the Purchases Inquiry sample size was cut by 50% to reduce costs and burden on businesses. Consequently, the results collected were considered to be of insufficient quality and the survey was suspended. The last dataset dates from 2005 and covers reference year 2004. In the absence of a Purchases Inquiry from 2006 onwards, patterns from the 2004 reference year have been used to apportion total industry data from the Annual Business Survey (ABS).
The industry totals used in the supply and use tables are provided by the ABS. However, product-level estimates in the supply and use tables are apportioned using the patterns of the 2004 Purchases Inquiry data. The re-introduction of the Annual Purchases Survey is designed to collect detailed up-to-date product-level information to replace the outdated 2004 proportions.
Uses and users
Intermediate consumption is required as part of the process to set the annual level of GDP, which is an essential statistic for informing fiscal and monetary policy decisions. The data collected from the APS feeds into the supply and use framework, which is a central component of the national accounts balancing process and sets the annual level of nominal GDP. The Eurostat Manual of Supply Use and Input-Output Tables recommends that benchmarked supply and use tables are produced at least every five years based on updated source data. These source data should also be updated periodically to reflect the changing composition of business intermediate consumption in various industries.
There was a strong demand for up-to-date data on purchasing patterns between industries as this helps users understand inter-dependencies between, and characteristics of, UK businesses. This is vital for understanding how the economy is likely to respond to economic policy and economic shocks.
Additional uses include detailed coverage of water and energy as well as the proportion of total purchases as imports.
There are a wide range of users for APS data. Users include those from government, both internal within ONS and external in other government departments such as:
the Department for Business, Energy and Industrial Strategy (BEIS)
the Department for International Trade (DIT)
the Department for Digital, Culture, Media and Sport (DCMS)
the Department for the Environment, Food and Rural Affairs (Defra)
Devolved administrations such as the Scottish and Welsh Governments, as well as local authorities, also constitute main users of the Annual Purchases Survey outputs.
Strengths and limitations
The main strengths of the APS include:
the survey is very comprehensive, covering many products purchased at a much greater level of detail than other ONS surveys
the APS response rate is consistently above 80% at the publication of results
the APS tailors questionnaires to each industry, minimising respondent burden
the high level of detail in APS data permits a thorough insight into the purchasing patterns of businesses
The main limitations of the survey include:
as the APS is an annual survey, there are restrictions on the timeliness of the data available
the APS requires a high level of product detail, and some businesses find it difficult to provide this level of detail, often due to differences in accounting systems
the APS is a new survey, so is subject to continuing development and improvement work
As this is a new survey, significant development and improvement has been undertaken over several years, using quantitative and qualitative mechanisms. Wide consultation both internally within ONS and with other government departments and main stakeholders has taken place.
Following collection of the first year of data, the methods systems have been subject to thorough review, with changes and improvements made to survey processes. The most notable recent improvement was a review of the imputation method.
Throughout 2017 to 2018, the questionnaire has undergone significant development, with cognitive interviews with businesses establishing improvements to the questionnaire design, to be implemented for the 2018 reference period. This work has been part of wider comparison analysis with the ABS, discussed under the Coherence and comparability section.Back to table of contents
The Annual Purchases Survey (APS) was reinstated by Office for National Statistics (ONS) in 2015 to meet a range of user demands and to fulfil the recommendations for its reinstatement from two independent reviews, one by Dame Kate Barker and Art Ridgeway (PDF, 570KB) and the other by Professor Sir Charles Bean.
APS outputs will be used as part of the national accounts supply and use tables, an integral part of the measurement of gross domestic product (GDP). GDP is the primary measure of the overall state of a country’s economy; it is extensively reported in the media to track the UK’s economic performance.
The total error in a survey estimate is the difference between the estimate derived from the data collected and the true (unknown) value for the population. The total error consists of two main elements: sampling error and non-sampling error.
The error that arises because the estimate is based on a survey rather than a census of the population. The results obtained for any single sample may 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.
The estimated value of the average magnitude of the sampling error. Our estimate for a variable, plus and minus the standard error for the variable, gives the range in which the true unknown value for the population should lie.
Coefficient of variation (CV)
This is estimated by the standard error of a variable divided by the survey estimate. This is used to compare the relative precision across surveys or variables. The closer the CV is to zero, the less uncertainty there is in the estimate. To minimise the burden on businesses and to complete the survey within allocated resources, the sample size is limited, which can lead to large CVs and some uncertainty around detailed product estimates.
Non-sampling errors cover all errors unrelated to sampling methodology. These can be difficult to quantify and relate to errors in coverage, measurement, processing and non-response.
The response rate gives an indication of the likely impact of non-response error on the survey estimates and are published as part of the statistical bulletins. The response rates for the first years of data are over 80%, comparable with other ONS surveys.
It is difficult to accurately quantify the effect of response inaccuracy. Work has been undertaken through questionnaire design and development to explore any respondents’ concerns around terminology and data availability (as detailed in the Coherence and comparability section).
Industry classification on the Inter-Departmental Business Register
Industry reclassification (a business moving from one Standard Industrial Classification (SIC) to another) can occur due to a relatively small change in the way the business operates, but can have a significant effect on APS estimates. When a survey does not cover the whole business population, as with the APS, reclassification can lead to units moving in and out of scope of the sample. We minimise this error by ensuring that the main respondents remain in the sample where possible.
In addition, the correction of misclassified businesses can lead to bias, particularly when there is systematic movement from one industry to another. This is because, where classification updates are identified via survey returns, it is only units in the survey sample that are updated.
Reliability and output quality
Assessing the difference between the first published estimate and the final revised figure provides an indication of reliability. APS statistics are currently experimental, as we work towards achieving National Statistics status. Part of this work will be to establish and publish a full publication schedule, comparable to those of other annual ONS outputs.
Coherence and comparability
Coherence with the Annual Business Survey
The estimates of industries’ total intermediate consumption used in the supply and use tables (SUTs) are derived in part from the Annual Business Survey (ABS). The ABS is a well-established survey providing information on turnover, amongst other variables, to help inform and feed into SUTs and national accounts.
Although the ABS does not specifically collect intermediate consumption, it does ask businesses for their total purchases and contains a number of questions that can be used to derive an estimated total figure. Figures from the APS are benchmarked to the ABS estimates to ensure consistency and comparability, as it has a larger sample frame and gives a better aggregate estimate of intermediate consumption.
It is important to understand the reasons for any differences between the APS results for intermediate consumption and the derived equivalent on the ABS. This comparison also forms part of the validation process. It is not expected that these figures will be the same, as there are notable differences between the surveys, such as coverage, definitions and methodology.
Differences between the populations for both the APS and the ABS will have an impact on estimates, at an overall level and for specific industries, as it will affect weights and estimation. The main differences are:
the APS excludes all public sector organisations, whereas the ABS includes public sector organisations that are outside the public administration, education and health industries
the APS has a greater coverage of the financial industries and dental practices
There is also an important difference in the methodology used to calculate the weighted estimates. The APS uses employment as the auxiliary variable for calculating the calibration weights, whereas the ABS uses turnover, taken from the Inter-Departmental Business Register (IDBR).
Further, the ABS has long and short versions of questionnaires, to reduce respondent burden where appropriate. The short version only asks for totals, including the total purchases figure, whereas the corresponding long version asks for a more detailed breakdown of these totals. The figures from the long version are then used to derive intermediate consumption. Many of the smaller businesses (employing fewer than 250 persons) are only sent a short version, which asks for total purchases. The breakdown of this overall value is then estimated using component proportions of businesses returning the long version. The APS has only one version of their questionnaire.
Coherence across time series
Work is underway to explore the validity of providing a time series between the end of the previous Purchases Inquiry in 2004 and its reintroduction in 2015.
Accessibility and clarity
Our recommended format for accessible content is a combination of HTML webpages for narrative, charts and graphs, with data being provided in usable formats such as CVS, XML and Excel. The ONS website also offers users the option to download the narrative in PDF format. In some instances, other software may be used or may be available on request. Available formats for content published on our website, but not produced by us or referenced on our website but stored elsewhere, may vary.
For information regarding conditions of access to data, please refer to the links:
Timeliness and punctuality
The time lag between collection and publication reflects the complexity of the survey and the detail of the published product-level estimates. The publications will feed into the timetable for Blue Book publications.
For more details on related releases, the release calendar is available online and provides 12 months’ notice of release dates. If there are any changes to the pre-announced release schedule, public attention will be drawn to the change alongside full explanation of the reasoning behind it, as set out in the Code of Practice for Statistics. This itself has been recently updated, with a greater focus on statistical context and recommended usage.
Why you can trust our data
ONS is the UK’s largest independent producer of statistics and its national statistics institute. The Data Policies and Information Charter, available on the ONS website, detail how data is collected, secured and used in the publication of statistics. We treat the data that we hold with respect, keeping it secure and confidential. We use statistical methods that are professional, ethical and transparent. You can find more about our data policies on our website.
The Annual Purchases Survey data are currently experimental; we are working within the core principles of the Code of Practice for Statistics, with a view to achieving National Statistics status, as designated by the UK Statistics Authority in accordance with the Statistics and Registration Service Act 2007.
We are keen to get your views on the methods and work to date to help inform and make improvements to the APS. If you have any comments, please email us at firstname.lastname@example.org.Back to table of contents
The Annual Purchases Survey (APS) sample frame is the Inter-Departmental Business Register (IDBR).
The IDBR covers businesses in all parts of the economy, except those that are not registered for Value Added Tax (VAT) or Pay As You Earn (PAYE), for example, very small businesses, the self-employed, those without employees and those with low turnover. Some non-profit making organisations are also not registered on the IDBR. The IDBR has details of approximately 2.4 million businesses and covers approximately 97% of UK economic activity. The IDBR is used by government departments, including Office for National Statistics (ONS), as the sampling frame for most business surveys.
The APS uses a stratified random sample design. This is grouped by:
six employment size bands: 0 to 9, 10 to 19, 20 to 49, 50 to 99, 100 to 249, and 250 and over
industry class: four-digit UK Standard Industrial Classification 2007: SIC 2007
country: England, Scotland, Wales and Northern Ireland
All businesses with more than 250 employees will automatically be included in the sample. Each of the industries has a cut-off threshold that has been calculated with respect to the product contribution within each stratum. For the businesses with employment below the threshold, a simple random sampling method based on a permanent random number (PRN) is used for selection.
The APS has a sample size of approximately 31,000 businesses across the UK.
Data are collected from businesses primarily through tailored paper questionnaires, with the option to include additional products where appropriate, to minimise respondent burden. Questionnaires are dispatched in February, with a deadline for receipt by the end of April.
Reminders are dispatched for non-responses. In addition, a telephone exercise is conducted by a dedicated respondent relations team. When questionnaires are received, they are scanned and transferred to a data validation team for processing.
The APS currently has 109 questionnaire types with an average of 53 questions on each. The survey questions were produced using the question library for the APS, which was created using the Statistical Classification of Products by Activity (CPA) version 2.1.
The CPA is the classification of products (goods and services) at the level of the European Union (EU). Product classifications are designed to categorise products that have common characteristics. They provide the basis for collecting and calculating statistics on the production, distributive trade, consumption, international trade and transport of such products.
The primary aim of the APS is to provide detail on the products purchased in the production process and running of UK businesses, otherwise referred to as intermediate consumption. This product-level information is used in supply and use tables (SUTs), which are an integral part of the measurement of gross domestic product (GDP).
The survey collects information about businesses’ expenditure on energy, services, goods and materials that are used up or transformed by the business activity. It includes raw materials, power and fuel, rental on buildings, and business services such as advertising, recruitment consultancy and cleaning. It specifically excludes fixed assets or capital investment, staff costs, and goods and services bought for resale without further processing.
The APS covers a large element of the economy with some notable exceptions such as public administration. This information is collected through other sources, primarily administrative data complemented by other ONS surveys. The exact inclusions and exclusions of industries are detailed in this section.
Agriculture, forestry and fishing (section A) (Standard Industrial Classification 01.6 to 01.7)
Mining and quarrying (section B)
Manufacturing (section C)
Electricity, gas, steam and air conditioning supply (section D)
Water supply; sewerage, waste management and remediation activities (section E)
Construction (section F)
Wholesale and retail trade; repair of motor vehicles and motor cycles (section G)
Transport and storage (section H)
Accommodation and food service activities (section I)
Information and communication (section J)
Financial and insurance activities (section K)
Real estate activities (section L)
Professional, scientific and technical activities (section M)
Administrative and support service activities (section N)
Education (section P)
Human health and social work activities (section Q)
Arts, entertainment and recreation (section R)
Other service activities (section S)
Agriculture, forestry and fishing (section A) (Standard Industrial Classification 01.1 to 01.5)
Public administration and defence; compulsory social security (section O) (note that the Annual Business Survey (ABS) covers all legal statuses, but excludes the public sector, while the APS covers only legal statuses 1 to 3: company, sole proprietor and partnership)
Activities of households as employers; undifferentiated goods – and services – producing activities of households for own use (section T)
Activities of extraterritorial organisations and bodies (section U)
How we process and analyse the data
Once the data are collected, the ONS Integrated Annual Unit initially analyses responses and will contact businesses where substantial data changes are identified (for example, if their total intermediate consumption figure increases or decreases by 20% from one year to the next). The data are then aggregated and the ONS Results and Processing Team conduct further phases of validation checks. These represent thorough micro-level investigations, and respondents may receive further queries if important changes are highlighted, which would have an impact on product or industry-level data.
The following procedures are used for non-responders or non-sampled businesses, alongside atypical responses.
The imputation methods for the 2015 reference year, and the 2016 reference year and onwards are different. During the first year of data collection (2015) it was not possible to conduct unit non-response imputation as there were no previous data in which to compare. The item non-response imputation methods were also revised for the 2016 reference period onwards.
Automatic imputation using ratio of means imputation is used when unit non-response occurs to a business of employment greater than or equal to 250 employees. This is when a business does not respond to the survey in year t. Imputation takes place at product level by calculating an average year-on-year growth (at section total level) by imputation class (industry classification and size-band) for all businesses that have responded in both years (year t and year t-1). The missing value can then be imputed by multiplying the average growth by the previous response from year t-1.
Automatic imputation using component breakdown imputation is used when item non-response occurs to all businesses. This is when a business provides only a partial breakdown of products, but a full section total (for example, total expenditure on energy) figure. An average pattern will be calculated using the breakdown of other businesses that have responded in the current year. This pattern will be used to allocate the section total to its product breakdown.
For the data collected in the 2015 reference period, the imputation method for a business with item non-response was to choose a random, similar, business and base the product breakdowns of a section off this random business.
An influential responder (a business that is known to make a significant contribution to the product estimates) has its data (section totals and breakdowns) manually constructed if it does not respond. This construction is based on previously provided product breakdowns and specialist knowledge of survey analysis.
Estimation is carried out using standard statistical techniques for stratified random sampling. Each sampled business is weighted by its design weight (a-weight) and a calibration factor, which is calculated using ratio estimation (g-weight). The a-weight represents the number of similar businesses that each sampled business represents. The g-weight improves the precision of the estimates and corrects for any imbalance in the selected sample by taking account of characteristics of the businesses that were randomly selected. Weights are updated annually.
Businesses with atypical values compared with other businesses in their industry and employment size are treated as outliers, using a post-stratification method. Product values returned by businesses that are automatically identified as outliers have dampened weights, which means they represent less of the universe than they would originally. Businesses that are manually found as outliers are given a weight of one in estimation calculations – that is, they represent only themselves.
How we quality assure the data
Data are quality assured throughout the data collection, processing and analysis through regular consistency checks, investigation of anomalies, ensuring disclosure procedures and reviewing data sources. These checks are presented at regular curiosity meetings, where important internal stakeholders interrogate the data and explore any anomalies or interesting findings. External stakeholders, for example, other government departments, also have regular opportunities to analyse the data and share feedback with ONS colleagues.
How we disseminate the data
The APS data are disseminated primarily through publication of statistical bulletins and ad-hoc releases on the ONS website. The publication schedule is detailed in the Timeliness and punctuality section. The APS publishes regular statistical bulletins, with releases increasingly promoted using ONS social media accounts. External stakeholders receive data ahead of release as part of the quality assurance process.
We employ consistent disclosure control procedures ahead of publication. The Government Statistical Service defines statistical disclosure control as follows:
“Statistical disclosure control (SDC) is the term used to cover the many methods of safeguarding the confidentiality of the information about individuals and businesses. Information obtained from surveys or administrative data is usually given in confidence. SDC is applied to ensure that individuals, businesses or other statistical units cannot be identified from published data, whether record-level data or tables. This will involve modifying data so that the risk of identification is reduced to an acceptable level.”
The APS is conducted under the Statistics of Trade Act 1947. This Act imposes restrictions on the way that data collected during the survey may be used, to ensure that information that can be attributed to an individual organisation is not disclosed in any publication.
Disclosure is a particularly sensitive issue in business surveys, given the commercial confidentiality of the data collected. The following rules are applied to the APS estimates (except where the respondent is willing to allow the data to be published):
minimum threshold rule: this rule states that there must be at least n reporting units (businesses) in a cell
P% rule: a cell is regarded as safe if the total of the cell minus the m largest contributor(s) is greater than or equal to p% of the value of the largest contributor
dominance rule: a cell is regarded as safe if the largest n contributors to the cell contribute less than k% to the cell total
Businesses whose data have been suppressed, due to the level of disclosure, may be contacted following publication of the data to request permission to publish disclosed data.
How we review the data
Future data are used to inform and revise previous reference periods, to ensure the quality of the time series. For example, if a business does not respond for one reference period, but a response is received for the following reference period, that response can be used to inform previous data.
A full analysis of the development and progress of the reintroduced APS was published in December 2017.
A technical report, containing detailed methodological information on all aspects of the survey, will be available shortly.
For further information, please contact the Annual Purchases Survey Team: email@example.com.Back to table of contents