1. Methodology background

 National Statistic   
 Survey name  Monthly Business Survey (Retail Sales Index)
 Frequency  Monthly
 How compiled  Sample based survey
 Geographic coverage  Great Britain
 Sample size  5,000 retailers
 Last revised  11 January 2017

Back to table of contents

2. Important points about RSI data:

  • The Retail Sales Index (RSI) is compiled using data from the Monthly Business Survey – Retail Sales Index (MBS-RSI).

  • It covers businesses which are engaged in retail trade and which operate in Great Britain (England, Scotland and Wales); it does not include Northern Ireland, the Isle of Man or the Channel Islands.

  • Retail sales data are collected from a sample of approximately 5,000 retailers across Great Britain; the sample represents the whole retail sector and includes all large retailers and a representative sample of smaller businesses; the known retail industry population is approximately 200,000 businesses and while the sample represents 2.5% of this population, in terms of the number of businesses the sample covers approximately 93% of all known turnover in the retail industry.

  • Retailers provide total retail turnover inclusive of VAT, including sales from stores via the internet, mail orders, stalls and markets, door-to-door and telephone sales; a separate question is asked for total retail sales generated via the internet only.

Back to table of contents

3. Overview of the output

The primary purpose of the Retail Sales Index (RSI) is to produce a short-term measure of the changes in the volume and value of sales of goods by retail businesses in Great Britain, providing a timely indicator of economic performance and strength of consumer spending. The industries included in the Retail Sales Inquiry are defined by the UK Standard Industrial Classification (SIC 2007). Retail Sales statistics published in the Retail Sales Statistical release are presented for all retailing, both including and excluding automotive fuel and in 4 retail sector groupings:

  • Predominantly food

  • Non-food

  • Non-store retailing

  • Automotive fuel

The non-food sector is broken down further to provide statistics on:

  • Non-specialised stores or department stores

  • Textiles, clothing and footwear

  • Household goods stores

  • Other specialised stores

At this level statistics on volume and value of retail sales, seasonally adjusted, are published.

Retail Sales statistics published in the Retail Sales Tables on a monthly basis are presented by retail sector groupings and more detailed industry sub-groups. At this level, non-disclosive statistics covering small and large businesses, non-seasonally adjusted, are provided.

The main output measures include value and volume estimates, in both seasonally adjusted and non-seasonally adjusted forms. The value estimates reflect the total turnover that businesses have collected over a standard period, while the volume estimates are calculated by taking the value estimates and adjusting to remove the impact of price changes.

Back to table of contents

4. Output quality

This page provides a range of information that describes the quality of the output and details any points that should be noted when using the output.

We have developed Guidelines for Measuring Statistical Quality; these are based upon the 5 European Statistical System (ESS) quality dimensions. This page addresses these quality dimensions and other important quality characteristics, which are:

  • relevance

  • timeliness and punctuality

  • coherence and comparability

  • accuracy

  • output quality trade-offs

  • assessment of user needs and perceptions

  • accessibility and clarity

More information is provided about these quality dimensions in the sections below.

Back to table of contents

5. About the output


(The degree to which the statistical outputs meet users’ needs.)

The value and volume measures of retail sales estimates are widely used in private and public sector institutions, particularly by the Bank of England (BoE) and Her Majesty’s Treasury (HMT). Their primary use of the data is to assist in informed decision and policy making. Other users include business and research communities, economic and financial organisations, the media and the general public.

We regularly review our statistical outputs to ensure they continue to meet users’ needs. Several changes have been made to the statistical bulletins to make them more relevant for users. In a recent survey users found the Retail Sales Index statistics important to their work. It was found crucial for financial modelling of sectors and recognised as a timely indicator for the economy. It has been used as a comparative tool with British Retail Consortium (BRC) and other market sources to boost context. Practically, it has been utilised as a comparative tool for business performance and the ability to access internet retail sales has been particularly beneficial to some. On a non-industry level, the RSI was perceived as important for informing political opinions or simply for curiosity by individuals who were not necessarily utilising it as a reference for work purposes.

The Retail Sales Index feeds into estimates of gross domestic product (GDP) in 2 ways. Firstly, it feeds into the services industries when GDP is measured from the output approach. Secondly, it is a data source used to measure household final consumption expenditure, which feeds into GDP estimates when measured from the expenditure approach.

Timeliness and punctuality

(Timeliness refers to the lapse of time between publication and the period to which the data refer. Punctuality refers to the gap between planned and actual publication dates.)

The monthly Retail Sales Index (RSI) is released in a timely manner, 18 or 19 days after the reference period, and is an important early economic indicator. Data are collected for standard trading periods that follow a 4 week, 4 week, 5 week cycle. For the reference period 28 August to the 1 October 2016, the RSI was released on the 20 October 2016. The exception to this is for the release of February data, which are 25 working days after the reference period as price data which are used for deflation are released later than usual to allow for the basket of goods to be updated.

For more details on related releases, the release calendar is available online from the GOV.UK website and provides 12 months’ advance notice of release dates. If there are any changes to the pre-announced release schedule, public attention will be drawn to the change and the reasons for the change will be explained fully at the same time, as set out in the Code of Practice for Official Statistics.

Back to table of contents

6. How the output is created

The following provides a summary for how the Retail Sales Index (RSI) and retail internet sales are calculated.

The RSI output provides an estimate of the value and volume of retail sales in Great Britain on a monthly basis. This incorporates the retail internet sales data but these are also published alongside to provide more detailed information for this sector.


The population of interest is all businesses whose principal activity is retailing and are therefore classified to retail under UK Standard Industrial Classification 2007 (SIC 2007) and are resident within Great Britain. There are an estimated 200,000 retailers listed within the target population or sampling frame which is taken from the Inter-Departmental Business Register (IDBR).

Retail sales data are collected from a sample of approximately 5,000 retailers across Great Britain. The sample represents the whole retail sector and includes all large retailers and a representative sample of smaller businesses. The known retail industry population is approximately 200,000 businesses and while the sample represents 2.5% of this population, in terms of the number of businesses, the sample covers approximately 93% of all known turnover in the retail industry.

The IDBR is used as the sampling frame for the Monthly Business Survey – Retail Sales Index (MBS-RSI). A sampling frame is a list of all units in the population of interest, in this case a list of all businesses in the UK that we can obtain information from.

A stratified random sample is used to ensure small and large businesses are represented according to the retail trade population structure. First retailers are classified to their industrial grouping as defined by SIC 2007. Five bands or strata are then created based on employment size:

  • Band 1, 0 to 4 employment

  • Band 2, 5 to 9 employment

  • Band 3, 10 to 99 employment

  • Band 4, 100 and more employment

  • Band 5, employment between 10 to 99 with turnover greater than £60 million a year

A random sample is taken from bands 1, 2 and 3. Retailers in bands 4 and 5 are continuously sampled.

Data collection

The RSI is compiled using data from the Monthly Business Survey – Retail Sales Index (MBS-RSI). The MBS-RSI covers businesses which are engaged in retail trade and which operate in Great Britain; that is England, Scotland and Wales. It does not include Northern Ireland, the Isle of Man or the Channel Islands.

Retail sales covers spending on goods such as food, clothing and footwear and household goods. Spending on services such as holidays, air fares and train tickets, insurance and banking are not covered and retailers are asked to separate out turnover from services from their return.

When using Retail Sales Index (RSI) as an estimate of the performance of the high street, users should note that these services plus services such as hotels and restaurants and other catering services are also not included. Estimates of the performance of these services can be found in the Index of Services (IoS).


Retailers are asked to provide total retail turnover inclusive of VAT, including sales from stores via the internet, mail orders, stalls and markets, door-to-door and telephone sales. A separate question is asked for total retail sales generated via the internet only.

There is a small sub-sample of the RSI which forms the panel for the Monthly Commodity Survey (MCS). The panel consists of 31 large retailers that are asked to provide the same data as the main retail sales sample and also total turnover generated for the following:

  • Food

  • Alcohol, tobacco and confectionery

  • Clothing and footwear

  • Household goods

  • Other

  • Automotive fuel

The accounting period follows a 4-4-5 week pattern. As a result, over the course of a 365 day calendar year (or 366 days in a leap year), 1 (or 2) trading days a year is lost. To compensate, every 5 or 6 years an extra week is added to the cycle, usually in January. The most recent 5-week January was in 2014.

Most businesses are able to report data for these accounting periods, however, some provide data on a calendar month basis. The questionnaire asks respondents to indicate the dates to which the returned turnover data relates, that is, the accounting period or calendar month.

In addition, each quarter a sub-sample of 2,100 small retailers and all large retailers are asked to provide information on employment including male and female, and full and part time splits. These data are then used in the workforce jobs section of the Labour Market Statistics. The average monthly response rate for this survey has been 61%, which accounts for approximately 87% of all retail turnover.

Mode of collection

For the main retail sample, data are collected using electronic data collection (EDC). Respondents are sent an email specifying the questions and instructions on how to return their data via the EDC system.

For the Monthly Commodity Survey (MCS), respondent’s data are also collected through EDC.

In order to ensure a good response rate, approximately 64% each month, response chasing is conducted by trained staff and allows respondents to return data over the phone.


Returned data are passed through a series of validation checks. The MBS-RSI uses an editing and validation approach known as selective editing. Selective editing is an internationally recognised method that uses a data-based approach to assess the influence of business estimates on the aggregate outputs.

The selective editing approach means that the editing process should be more efficient and effective since it will only edit potential errors that have a significant impact on final outputs. Under selective editing, key variables on the questionnaire are defined and scores derived for these. The scores compare the value provided on the questionnaire with expected values, where the expected values are generally estimated using past data or other available information related to the variable, for example, from administrative sources. The scores from “main” variables are then combined to derive a score for every questionnaire. This derived, single score for the business’s return is then tested against a methodologically set threshold. If the score is higher than the defined threshold then the questionnaire will fail and be flagged for manual editing. Returns that fail selective editing are passed to the editing and validation team for manual checking.

Thresholds have been derived and set to ensure minimum bias is introduced from not editing values that may have been edited under the previous edit all returns system. Thus selective editing does result in an adverse impact on output quality. In order to ensure that all errors are captured, before questionnaires pass through selective editing they are subjected to automatic editing and then a number of user defined checks. For example, these will include checks to detect changes in reporting periods and implausible returns such as turnover being less than zero.

In turn, data are analysed at a macro level to determine the contributing factors to the movement in the value index and its published categories. Together, this micro and macro approach to editing identifies outliers and anomalies within the returned data.


Each month approximately 64% of respondents complete and return the MBS-RSI questionnaire, equating to approximately 93% coverage by turnover. Ratio imputation, explained below, is used to provide estimates for non-responders.

For those respondents who do not return their data in time for publication of the retail sales aggregates, the total turnover and total internet sales are imputed using a ratio imputation method known as a ratio of means.


Estimation is the process of approximating some characteristic of a population, in this case Retail Sales in Great Britain, when information is available only for a sample of the population. From the returned and imputed data a population total is estimated using ratio estimation. Ratio estimation is used when the ratio between the returned turnover over the registered turnover variable on IDBR is roughly constant and the variance of the returned turnover can be assumed to be proportional to the registered turnover. The estimate for Retail sales in Great Britain is then given by multiplying the estimate of the ratio by the number of retail business on the IDBR. This gives the value of retail sales in pounds (thousands) (£’000s) and retail internet sales in pounds (millions) (£’000,000s) for average weekly sales and for the month. These data are published via our website where the retail sales value estimates are produced in index form using the reference year of 2013. The reference period is the year for which the index is scaled to equal 100. To keep RSI in line with the UK National Accounts, the reference year is updated each year when weights are available from the Blue Book. The change to the reference year is a simple calculation and does not impact on the movements of the series.

Unlike the method used to estimate the full retail sector and expansion or number raised estimator is used to estimate the value of internet retail sales. Number raised estimation works by ”expanding” the sample total up to the size of the population by multiplying the sample total by the ration of the number of retailers on the IDBR divided by the number of businesses within the sample.


Estimates of retail sales are published in index form rather than in monetary form. There are 2 types of index published in the form of value indices and chain volume measures. From this value index, the chained volume index is calculated by adjusting for price movements using a process called deflation. Value and chain volume indices are seasonally adjusted using X-13-ARIMA-SEATS.


Value estimates of retail sales reflect both price and volume changes. To remove the direct effects of prices changes, value data are deflated to produce RSI volume measures. A separate price deflator is used for each RSI industry at 4-digit SIC.

Industry price deflators are calculated from commodity price indices using weights appropriate to the relevant industry derived from the Annual Business Survey (ABS) data on the value of turnover. Currently, 2013 ABS commodity weights are used along with price indices derived from the Consumer Price Index (CPI).

Chained volume measures

The chained volume measures of retail sales are annual re-weighted chain Laspeyres indices referenced to current price values, currently 2013. For each year the values for each good in current prices and previous years' prices are calculated. These values are then aggregated using weights for each retail industry derived from the RSI.

Each year the series is re-referenced and comparability with previous years is achieved by chain linking the series together to form a continuous time series. An average of the values for October, November and December is used to provide the link factor.

Chain linking starts at the lowest possible level of aggregation. For RSI this means that aggregation uses the small and medium businesses combined with the large businesses for each industry within each retail sector. These estimates are used to create a chain-linked estimate for all businesses for each industry. Higher level chain-linked aggregate are derived in a similar way.

The chain-linking method used is consistent with the standard National Accounts method.

Time series analysis

Seasonally adjusted estimates are derived by estimating and removing calendar effects (for example Easter moving between March and April) and seasonal effects (for example increased spending in December as a result of Christmas) from the non-seasonally adjusted (NSA) estimates. Seasonal adjustment is performed each month and reviewed each year using the standard, widely used software, X-13-ARIMA. Before adjusting for seasonality prior adjustments are made for calendar effects (where statistically significant) such as: returns that do not comply with the standard trading period, bank holidays, Easter and the day of the week Christmas occurs.

While the number of trading days in a set period remains the same, the standard reporting periods 4-4-5 weeks introduce a “phase-shift” effect, associated with the fact that the standard periods do not match calendar months and move slightly each year relative to the calendar month. In a typical year the standard periods total 52 weeks or 364 days. As a result the standard periods fall back 1 day each year (or 2 days for a leap year).

Every 5 or 6 years, the reporting year is brought back into line with calendar year by adding an extra week, normally to January.

The seasonally adjusted estimates also have corrections for bank holidays; Easter effects which are caused when Easter falls late in March or early in April and the day of the week Christmas occurs. Prior connections are applied as necessary. Corrections are estimated and applied where there is a statistically significant effect.

The calculation of the RSI has an adjustment to compensate for calendar effects which arise for the difference in the reporting periods.

Confidentiality and disclosure

Before publication all data are tested for disclosure and, where there is a risk of disclosure of individual businesses, steps are taken to minimise this risk for example by aggregating similar industry sectors.

The Retail Sales Index (RSI) is compliant with the Code of Practice for Official Statistics, Principle 5.

Principle 5, Practice1, states:

Ensure that official statistics do not reveal the identity of an individual or organisation or any private information relating to them, taking into account other relevant sources of information.

All necessary steps are taken to protect the confidentiality of data collected from retail businesses. This includes statistical disclosure controls to ensure that individual businesses are not identified in the published statistics.

When data are shares with other bodies, for example Eurostat and Scottish government it is done so under legislation and using secure electronic file transfer methods.

Back to table of contents

7. Validation and quality assurance


(The degree of closeness between an estimate and the true value.)

There are 2 possible types of error in estimates of retail sales, sampling error and non-sampling error.

  • Sampling error occurs because a sample, rather than the entire population, is surveyed, it is the difference between the true value of the population and the estimated value; one way of measuring this difference is through standard errors.

  • Non-sampling errors arises from inaccuracies in collecting, recording and processing the data. The most significant of these errors are: misreporting of data items, deficiencies in coverage, non-response and processing errors. Every effort is made to minimise reporting error for example, all Monthly Business Survey – Retail Sales Index (MBS-RSI) respondents that do not return data by the stated deadline are response chased in order to reduce the non-response rate. Non-response error is minimised through the use of imputation. The careful design of questionnaires, intensive training and supervision of editing and validation staff and efficient data processing procedures are also used to minimise reporting errors.

A report on Retail Sales Index (RSI) standard errors and response rates titled Improving quality information for the Retail Sales Index was published in January 2015. The report shows that the median year-on-year standard error is estimated at 0.9% and the month-on-month standard error is estimated at 0.5%.

The RSI is first published using a 61% response rate, this equates with approximately 87% of sampled turnover. The sample of 5,000 from a population of nearly 200,000 may seem small but together these 5,000 retailers cover approximately 95% of all retailing turnover captured on the Inter-Departmental Business Register (IDBR).

A form of measurement error arises from respondents reporting turnover in pounds (thousands) (£’000s), when actual pounds are required. Where this is the case, the figure is corrected and respondents are informed as to which figures they need to provide.

Processing errors can be introduced where data are inputted manually by data analysts in £’000s rather than actual pounds. Training is provided to minimise this processing error.

Coverage error is introduced where businesses are not classified to retail or are not registered for VAT or PAYE and are therefore not listed on the IDBR.


Retail Sales non-seasonally adjusted data is revised as needed. Revisions and sampling variations are a consequence of the trade-off between timeliness and accuracy. All estimates are subject to statistical error which refers to the uncertainty inherent in any process or calculation that uses sampling, estimation or modelling. Estimates for the most recent month are provisional and subject to revision because of:

  • late responses to the Monthly Business Survey - Retail Sales Index

  • revisions to seasonal adjustment factors which are re-estimated every month and reviewed annually

  • changes from the annual seasonal adjustment review
  • annual updating of the business register that forms the basis for the sample for the RSI (usually occurring in January)

  • other methodological improvements

Changes are not made to any non-seasonally adjusted data prior to 2001. Revisions to non-seasonally adjusted data will directly impact on the seasonally adjusted estimates.

Revisions to all published seasonally adjusted estimates are not constrained or restricted as they are for other short-term indicators and the national accounts. Revisions are allowed to occur naturally each month along the full length of each time series as a consequence of the direct seasonal adjustment of the component time series. Aggregate seasonally adjusted estimates will then be derived. Any revisions from the directly seasonally adjusted time series will then occur as part of the higher level aggregation. This approach ensures that the RSI uses all available information and provides the most up-to-date estimates for recent periods.

A report on Revisions to Retail Sales Index and the RSI revisions policy are published on our website.

Coherence and comparability

(Coherence is the degrees to which data that are derived from different sources or methods, but refer to the same topic, are similar. Comparability is the degree to which data can be compared over time and domain for example, geographic level.)

Other statistics on retail sales are available. We also produce retail sales statistics as part of the Annual Business Survey (ABS). There are differences between the RSI and ABS retail figures for the following reasons:

  • the ABS collects and produces statistics on the UK whereas RSI covers Great Britain, resulting in differences in total sales values

  • reporting periods can vary, the ABS allows respondents to provide information on either a calendar year or financial calendar year. In comparison the RSI asks respondents to provide information based on a 4 - 4 - 5 week reporting period

  • for the food sector, the ABS includes automotive fuel sales by supermarkets, for the RSI these are extracted and used for the calculation of the automotive fuel series

  • for chemists the ABS includes National Health Service receipts, these are excluded from the RSI

There are other indicators of retail sales available. These include the British Retail Consortium (BRC) which produces the Retail Sales Monitor in collaboration with KPMG; and also from the Confederation of British Industry which produce retail trade statistics as part of their Distributive Trade Survey. The data produced by both are regularly used along with the RSI as important indicators of retail sales growth. However, there are differences between the indicators in relation to coverage and compilation that can lead to discrepancies between the published figures. More information on the differences between these 2 indicators and the RSI can be found in the article Retail Sales Index (RSI) and Other Surveys.

BRC United Kingdom Retail Sales Monitor (RSM)

The Retail Sales Monitor (RSM) is produced using data supplied by retailers from across the UK’s retail industry. Sales values from a range of 12 product categories are provided weekly to KPMG who then aggregate them into annual growth rates for each month on a total and like-for-like basis. The like-for-like figure strips out the effects of expansions and store openings and closures and is presented as a measure of retail industry performance. The total figure reflects retail industry growth. The headline growth rates are published in the second week after end of the month reported on.

From the Retail Sales Statistical Bulletin, the most appropriate measure to compare with the RSM total sales series is the RSI value of retail sales excluding automotive fuel for large stores, non-seasonally adjusted.

CBI Distributive Trade’s Survey (DTS)

The DTS is a qualitative survey which looks to capture short and medium-term trends in the UK Retail Sector. On average 68 retailers, who account for approximately a third of total employment in the retail sector, respond to the survey. Respondents are required to answer a series of questions regarding sales volumes using a scale of up, down or same as last year.

Comparable time series are available going back to 1988 for the following headline aggregates and their sub-sector series:

  • All retailing excluding automotive fuel

  • Predominantly food stores

  • Predominantly non-food stores

  • Non-store retailing

For the following aggregates, comparable time series are available going back to 1996:

  • All retailing including automotive fuel

  • Automotive fuel

Back to table of contents

8. Concepts and definitions

Concepts and definitions describe the legislation governing the output, and a description of the classifications used in the output.)

The industries included in the Monthly Business Survey – Retail Sales Index are as defined by the SIC 2007, the detailed structure of this classification and categories used by RSI can be found in A quick Guide to Retail Sales Index.

Retail sales is compliant with the Eurostat short-term business statistics regulation.

Other information

Output quality trade-offs

(Trade-offs are the extent to which different dimensions of quality are balanced against each other.)

The main quality trade off in producing the Retail Sales Index (RSI) occurs between timeliness and response rate. By publishing 18 days after the month’s end, the RSI typically has a 61% response rate. One month later this response rate will have risen to approximately 74%. The difference in coverage is smaller, with results published on approximately 87% sampled turnover which rises to approximately 96% sampled turnover a month later.

Assessment of user needs and perceptions

(The processes for finding out about uses and users, and their views on the statistical products.)

The Retail Sales Work Plan 2014 highlights the methodological work plan for retail sales and internet retail sales statistics. The plan includes a list of all regular updates that take place on an annual basis and, as well as describing the change, provides the user with an assessment of the impact on the time series data. Users are encouraged to provide comments on the work plan.

Methods reviews and updates

The methodology used to produce retail sales statistics is reviewed periodically by the Methodology Directorate (MD) within ONS. In 2008, MD conducted a review of the methodology and systems used in the calculation of the RSI, the systems were all found to be working correctly. For the methodology, recommendations were made regarding the chain-linking methodology planned for implementation on RSI in 2009. The main recommendations of this review were:

  • use CPIs for deflation rather than RPIs (which is closer to the requirement for a Laspeyres volume index)

  • using an annual benchmark derived from the RSI responses and not one from the ABI (reduces revisions and recognises difference in concept between RSI and ABI)

  • annual updating (and consequent revision) of deflation weights for the latest ABI (again closer to the requirement for a Laspeyres volume index)

These recommendations were implemented and are described in the paper “Changes to the retail sales methodology”, McLaren, C. Economic and Labour Market Review, vol 3, no16. The latest review of the RSI methodology was conducted through 2010 where a review of the methodology used for editing and validation was conducted. The result of this review was the implementation of selective editing. Also reviewed in 2010 were the weights used for annual chain linking and the annual seasonal adjustment review which was conducted for the first time in X-12-ARIMA (now in X-13-ARIMA).

Seasonal adjustment reviews will continue to take place yearly and re-referencing of the chain volume indices will take place at the same time as the national accounts are re-referenced, that is when a consistent set of weights is available.

All other reviews of the RSI methodology will be discussed with users, for example at user engagement events where they will be given the opportunity to feed into the review and methodology changes. Any proposed changes will go through a consultation process and when made will be disseminated to users. This page will also be updated when a new review begins and when changes are made to the methodology.

Back to table of contents

9. Sources for further information or advice

Accessibility and clarity

(Accessibility is the ease with which users are able to access the data, also reflecting the format in which the data are available and the availability of supporting information. Clarity refers to the quality and sufficiency of the release details, illustrations and accompanying advice.)

Our recommended format for accessible content is a combination of HTML web pages for narrative, charts and graphs, with data being provided in usable formats such as CSV and Excel. Our 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. A recent announcement was made that government departments should move to open standards for documents. Future business plans will incorporate the adoption of these standards where appropriate. For further information please refer to the contact details at the beginning of this page.

For information regarding conditions of access to data, please refer to the links below:

In addition to this Quality and Methodology Information, quality information relevant to each release is available in the RSI Statistical Bulletin.

Back to table of contents

Contact details for this Methodology