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.
The administrative placement of these statistics are in the division of Short Term Statistics. The person responsible is Bastian Bygvraa Schultz, tel. +45 39 17 33 65, e-mail: bbs@dst.dk
1.1. Contact organisation
Statistics Denmark
1.2. Contact organisation unit
Short Term Statistics, Business Statistics
1.3. Contact name
Restricted from publication
1.4. Contact person function
Restricted from publication
1.5. Contact mail address
Sankt Kjelds Plads 11, DK-2100 Copenhagen Ø
1.6. Contact email address
Restricted from publication
1.7. Contact phone number
Restricted from publication
1.8. Contact fax number
Restricted from publication
2.1. Metadata last certified
14 June 2024
2.2. Metadata last posted
14 June 2024
2.3. Metadata last update
14 June 2024
3.1. Data description
G: Data for G is a weighted combination of G45, G46 and G47. G45 and G46: Data for the calculation of the indeces are based on the VAT report made by national enterprises. Eurostat also receives seasonally adjusted data
G47: The value indices show the development of the turnover in current prices. The volume index is calculated indirectly by dividing the value index with a corresponding price index. In addition, the three main commodity groups are seasonally adjusted as well as the total. This includes adjustment for the effects of moving holidays (Easter), number of working days and trading days. Eurostat also receives seasonally adjusted data as well as data adjusted for working day and trading day effects only.
3.2. Classification system
The industry coding follows the Danish industrial classifications, Dansk Branchekode 2007 (DB07), which is the national version of NACE rev. 2. A complete overview can be found at the DB07 site.
An overview of the retail trade industries covered can be found in the industry appendix.
G47: For some smaller retail trade industries, no figures are published, either due to confidentiality issues or because of a potential lack of accuracy. The turnover of these industries, however, is included in the aggregated figures.
The main commodity groups used for national publications are as follows:
Food and other convenience goods cover all turnovers at grocery stores and specialised food stores, as well as the sales of these commodities at supermarkets, discount stores and department stores. In addition to this, the non-fuel sales at service stations are included in this group.
Clothing etc. covers all turnover in stores specialised in clothing and footwear, as well as the sales of these commodities at supermarkets, discount stores and department stores.
Other consumer goods cover primarily the turnover in shops selling furnishings, electronics leisure equipment, as well as DIY centres and pharmacies. It also includes the sales of these commodities at supermarkets, discount stores and department stores. In addition to this, the fuel sales at service stations are included in this group.
A detailed overview of the relations between industries and commodity groups can be found in the appendix industry groupings.
You will find a detailed overview of the grouping of commodities in the appendix commodity groupings (only in Danish).
The industry coding follows the Danish industrial classifications, Dansk Branchekode 2007 (DB07), which is the national version of NACE rev. 2. A complete overview can be found at the DB07 site.
For some smaller retail trade industries, no figures are published, either due to confidentiality issues or because of a potential lack of accuracy. The turnover of these industries, however, is included in the aggregated figures.
The main commodity groups used for national publications are as follows:
Food and other convenience goods cover all turnovers at grocery stores and specialised food stores, as well as the sales of these commodities at supermarkets, discount stores and department stores. In addition to this, the non-fuel sales at service stations are included in this group.
Clothing etc. covers all turnover in stores specialised in clothing and footwear, as well as the sales of these commodities at supermarkets, discount stores and department stores.
Other consumer goods cover primarily the turnover in shops selling furnishings, electronics leisure equipment, as well as DIY centres and pharmacies. It also includes the sales of these commodities at supermarkets, discount stores and department stores. In addition to this, the fuel sales at service stations are included in this group.
You will find a detailed overview of the grouping of commodities in the appendix commodity groupings (only in Danish).
3.3. Coverage - sector
Turnover and volume of sales in wholesale and retail trade.
3.4. Statistical concepts and definitions
Retail Trade: Sales of commodities to private individuals.
Retail Trade Enterprise: Enterprise mainly engaged in distributive sales of commodities to private individuals, here excluding sales of motorised vehicles.
Food and Other Everyday Commodities: Convenience goods are consumer goods that are consumed relatively quickly by a consumer and that cease to exist when consumed. Convenience goods are primarily foods and products for personal hygiene, but also tobacco.
Clothing etc.: Clothes, footwear and leather goods, incl. baby clothes and baby things.
Other Consumer Goods: Commodities not categorized as convenience goods or clothing etc. E.g. household appliances, leisure goods, medicine and fuel.
3.5. Statistical unit
G, G45 and G46: KAU
G47: The units of the retail trade index are enterprises, each enterprise being a KAU combined with a legal unit. In the Statistical Business Register of Statistics Denmark, legal units are identified by their CVR-numbers, i.e. their numbers in the Central Business Register.
In isolated cases, a unit can be different from an enterprise. It could be an enterprise with shops having significant turnover within several retail trade industries, in which case the enterprise can be accordingly divided in several statistical units. The reverse example also exists, where more enterprises within the same industry are merged to one statistical unit, e.g. if they have a common administration that would in any case report for all the enterprises in question.
3.6. Statistical population
G: Data for G is a weighted combination of G45, G46 and G47
G45 and G46: Data is from a total count, there for no Non-sampling error.
G47: The statistics covers the population consisting of all enterprises with main activity, or in a few rare cases secondary activity within retail trade, with the exception of retail trade of motor vehicles. Furthermore, bakeries with their own production are also included in the population. The population consists altogether of approximately 18.500 enterprises cf General enterprise statistics by industry (www.statistikbanken.dk/GF01).
3.7. Reference area
The statistics cover retail trade in Denmark by Danish retail trade enterprises, excluding Greenland and Faroe Islands. Foreign enterprises with retail trade with Danish consumers (e.g. near-border enterprises or foreign internet shops) are not included in the statistics.
3.8. Coverage - Time
The statistics cover the period from 2000 and forward. Older time series are described under Comparability over time.
3.9. Base period
The base year for the Retail Trade Index is 2021=100.
The unit of measure is index points. Value indices as well as volume indices are published. Read more about indices in this publication (only in Danish).
The reference period (t) for the monthly figures is the entire month.
G, G45 and G46: t+2 month
G47: The enterprises thus report the turnover of the entire month. A few enterprises have 4- or 5-weeks accounting periods and many normally only make up their accounts on a quarterly basis, which can cause the monthly turnover reports to be somewhat inaccurate. This, however, is not assessed as a significant quality issue. The population used for estimation usually has a reference time that is the previous year. This does not significantly affect the calculations of the monthly growth rates, due to the use of month-on-month linking where the actual and the previous month turnover is always estimated using the same population.
6.1. Institutional Mandate - legal acts and other agreements
The legal authority to collect data is provided by the Act on Statistics Denmark, section 8, as subsequently amended (most recently by Act no. 610 of 30th May, 2018).
The statistics fall under Council Regulation (EF) no. 2019/2152 of 27. November 2019 on European Business Statistics followed by the Commission Implementing Regulation 2020/1197 laying down technical specifications and arrangements pursuant to the mentioned EBS Regulation (General Implementing Act).”
In the compilation of the retail trade index, the Confidentiality Policy at Statistics Denmark is applied. I case a detailed industry figure is affected by confidentiality issues, no figures are published directly, but they are included in overlying aggregates.
8.1. Release calendar
The publication date appears in the release calendar. The date is confirmed in the weeks before.
8.2. Release calendar access
The Release Calender can be accessed on our English website: Release Calender.
8.3. Release policy - user access
Statistics are always published at 8:00 a.m. at the day announced in the release calendar. No one outside of Statistics Denmark can access the statistics before they are published.
These statistics are published monthly.
10.1. Dissemination format - News release
These statistics are published in a Danish news release.
10.2. Dissemination format - Publications
Publications only in Danish.
10.3. Dissemination format - online database
These statistics are published in the StatBank under Retail Trade Index i the tables:
DETA211: Retail Trade Index (2021=100) by industry (DB07)
DETA212: Retail Trade Index (2021=100) by commodity group and index type
Further documentation on methodology only in Danish.
10.7. Quality management - documentation
Results from the quality evaluation of products and selected processes are available in detail for each statistics and in summary reports for the Working Group on Quality.
11.1. Quality assurance
Statistics Denmark follows the principles in the Code of Practice for European Statistics (CoP) and uses the Quality Assurance Framework of the European Statistical System (QAF) for the implementation of the principles. This involves continuous decentralized and central control of products and processes based on documentation following international standards. The central quality assurance function reports to the Working Group on Quality. Reports include suggestions for improvement that are assessed, decided and subsequently implemented.
11.2. Quality management - assessment
The general assessment is that the quality of the statistics is high, with a few reservations. Using the time series for long-term analysis can be problematic. This is because of the way the retail trade index is designed and calculated, where not all structural changes in the population and sample are reflected in the figures (e.g. changes in the activity codes causing units to enter or leave the retail trade sector), which is why chaining is used in the calculation of growth rates for the value indices (see data compilation).
Moreover, there will typically be a slight underestimation of the volume index in periods where consumers are buying less expensive goods and in low-priced stores, and correspondingly there will be an overestimation in periods where consumers choose high-end goods and stores. This is caused by the use of CPI sub-indices as deflators for calculating the volume indices. The quality of the volume indices is generally very dependent on the composition of these deflators. In periods with changing consumption patterns, the deflation, and hence the volume indices, are less accurate, because CPI does not reflect all the constant changes in the consumption pattern.
A provisional analysis shows that the lack of consideration of the above-mentioned substitution effects in recent years have had a combined effect on the volume index causing an underestimation of the yearly growth rates of approximately 0.2-0.4 percent points.
To state the overall accuracy one must distinguish between the accuracy of the estimated totals and the accuracy of the monthly growth rates, which is the prime focus of these statistics.
The overall uncertainty of the total index is estimated to be less than 1 per cent. On commodity group level, the uncertainty of the group Food and other convenience goods is about the same, whereas for Clothing etc. it can be up to 3 per cent and for Other consumer goods up to 2 per cent.
The accuracy of the monthly growth rate is very high. For the total index the uncertainty is estimated to be less than 0.2 per cent, while it can be a little higher on commodity group level.
In a few cases, non-response from highly essential enterprises (units) can cause slightly higher uncertainty in the first publication of figures for a particular month.
12.1. Relevance - User Needs
The retail trade statistics is of great interest to many enterprises within the retail trade sector, as publications allow them to compare their own sales development to the general trend of their trade industry.
Some users have a need for more commodity-based figures. The detailed industry figures are based solely on industry activity, thus enterprises with a broad commodity selection, in reality covering more industries, struggle with comparability. Since more commodity based statistics would greatly increase the workload on respondents, we are currently unable to meet this user need.
12.2. Relevance - User Satisfaction
The users in general view the retail trade index as an important and easy to use short term indicator. The statistics are often cited in the media and widely used by other professional users. The detailed industry figures are used to monitor the development in the individual industries, but in some instances a more commodity-oriented approach has been requested, because some large enterprises in reality spread over several industries.
12.3. Completeness
For some industries, no detailed index figures are published due to confidentiality or quality issues.
These statistics are subject to EU requirements. In terms of the completeness of data, all these requirements are fully met.
13.1. Accuracy - overall
The general assessment is that the quality of the statistics is high, with a few reservations. Using the time series for long-term analysis can be problematic. This is because of the way the retail trade index is designed and calculated, where not all structural changes in the population and sample are reflected in the figures (e.g. changes in the activity codes causing units to enter or leave the retail trade sector), which is why chaining is used in the calculation of growth rates for the value indices (see data compilation).
Moreover, there will typically be a slight underestimation of the volume index in periods where consumers are buying less expensive goods and in low-priced stores, and correspondingly there will be a slight overestimation in periods where consumers choose high-end goods and stores. This is caused by the use of CPI sub-indices as deflators for calculating the volume indices. The quality of the volume indices is generally very dependent on the composition of these deflators used in the conversion from value index to volume index. In periods with changing consumption patterns, the deflation, and hence the volume indices, are less accurate, because CPI does not reflect all the changes.
A provisional analysis shows that the lack of consideration of the above-mentioned substitution effects have had an effect on the volume index in recent years causing an underestimation of the yearly growth rates of approximately 0.2-0.4 percentage points.
To state the overall accuracy, one must distinguish between the accuracy of the estimated totals and the accuracy if the monthly growth rates, which is the prime focus of these statistics.
The overall uncertainty of the total index is estimated to be less than 1 per cent. On commodity group level, the uncertainty of the group Food and other convenience goods is about the same, whereas for Clothing etc. it can be as high as 3 per cent and for Other consumer goods up to 2 per cent.
The accuracy of the monthly growth rate is generally very high. For the total index, the uncertainty is estimated to be less than 0.2 percentage points, while it can be a little higher on commodity group level. In a few cases, non-response from highly essential enterprises can cause slightly lower accuracy in the first publication of figures for a particular month.
13.2. Sampling error
G: Data for G is a weighted combination of G45, G46 and G47.
G45 and G46: Data is from a total count, there for no sampling error.
G47: Sampling error, is measured by the CV-values for the estimated turnover totals behind the retail trade index. For the total was on average 0.2 pct this year. This is below the accepted threshold of 10 pct. and therefore, considered acceptable. On industry level, the sampling error can be somewhat higher. For the largest industries it is normally below 2 percent, for medium-sized industries it is less than 5 percent., and for the small industries it can be as high as 8 per cent. The average for all industries this year was 2,92 pct.
13.3. Non-sampling error
G: data for G is a weighted combination of G45, G46 and G47
G45 and G46: Data is from a total count, there for no Non-sampling error.
G47: The overall accuracy is affected by sampling error and non-sampling error combined. Non-sampling error includes measurement error and non-response error.
The overall uncertainty of the monthly total retail trade index was 0.95 percent in this year. In 2023 the non-response rate was 12,1 pct.
On commodity group level, the uncertainty of the group Food and other convenience goods is about the same, whereas for Clothing etc. it can be up to 11 per cent and for other consumer goods up to 5 per cent. Approximately half of this uncertainty is due to non-sampling error such as bankruptcies or changes in sector classification.
14.1. Timeliness
G47: The first published figures for a given month are published 20-22 days after the end of the reference period and only include figures on the three main commodity groups (not industries). On industry level, the first publication is one month later. At the same time, the first published figures on commodity groups are revised. Hence, these figures are published 50-52 days after the end of the reference period.
One month later, the final revision of the figures is made for both the commodity groups and the figures on industry level (which are thus only revised once). Hence, the final figures are published 70-72 days after the end of the reference month.
14.2. Punctuality
The punctuality is very high with delays happening very rarely.
15.1. Comparability - geographical
Every month, figures are submitted to the statistical office of EU, Eurostat. These include special industry aggregates which are not published nationally. Data for all EU countries can be found in the Eurostat database. The statistics are produced following the common guidelines and principles of an EU regulation, so the results are comparable.
15.2. Comparability - over time
The statistics have been compiled since 1939, but they are not suited for long term time series analysis because of structural changes in the retail trade sector. The sample design and the calculation methods have been adjusted several times, last time in May 2012, where the time series back to 2000 where recalculated using new methods. More on that complete revision can be found in this publication (in Danish)
In Statbank Denmark historical time series going back to 1979 can be found, but due to differences in methodology and classifications, comparisons to the current time series going back to 2000 is not advisable.
15.3. Coherence - cross domain
Other short term statistics also covers the turnover development in the retail trade sector. Below, a list is included, describing the relationship between the retail trade index and the other statistics.
Purchases and sales by enterprises Apart from being a register-based set of statistics with complete coverage (in theory), the VAT statistics are different from the retail trade index when it comes to the turnover definition. The turnover in the VAT statistics includes all sales subject to VAT, whereas the turnover submitted for the retail trade statistics only includes turnover from sales to private persons (retail trade turnover). The fact that VAT statistics are based on the continuous VAT payments from the enterprises in principle means that any changes in the population have immediate effect on the figures. The same cannot be said of the retail trade index. Moreover, small and medium sized retail trade enterprises do not submit VAT payments monthly, so the survey-based retail trade index will have more data for calculation of the monthly growth rates.
Consumption of goods in national accounts The quarterly national accounts include figures on the consumption broken down by types of goods. The private consumption of certain types of goods is sold in retail trade enterprises, but the two indicators do not show the same development, since other sources than the retail trade index are incorporated in the private consumption figures.
Other statistics In addition to the above-mentioned statistics covering the development in total retail trade turnover, there are other indicators covering the development in parts of the private consumption:
Monthly statistics on purchased cars based on registrations
Monthly tendency survey on retail trade
A number of trade organisations in retail trade prepare statistics based on turnover reports for the relevant industries submitted by members
15.4. Coherence - internal
Seasonal adjustment is performed indirectly, which results in consistency between seasonally adjusted aggregates and their subcomponents. There are no other sources of possible internal inconsistency.
G, G45, G46: The workload on the respondents is estimated at 2 full-time equivalents.
G47: The workload on the respondents is estimated at 2.8 full-time equivalents.
17.1. Data revision - policy
Statistics Denmark revises published figures in accordance with the Revision Policy for Statistics Denmark. The common procedures and principles of the Revision Policy are for some statistics supplemented by a specific revision practice. The national revision policy is the same as for Eurostat data.
G, G45, G46: Revision until the data series is more than three years old.
G47: The first published figures for a given month are published 23-28 days after the end of the reference period and only include figures on commodity groups (not industries). On industry level, the first publication is one month later. At the same time, the first published figures on commodity groups are revised. Hence, these figures are published 53-58 days after the end of the reference period.
One month later, the second and final revision of the figures is made on commodity group level, and the figures on industry level are revised for the first and only time. Hence, the final figures are published 73-78 days after the end of the reference month.
In case of major changes in methodology or in case of errors, the figures can be revised further back. In 2021, there were the grossing up model did not handle missing observations that resulted from restrictions against COVID-19 well. Therefore, in the fall of 2021 the whole year were recalculated using improved grossing up methods. These revisions were significant for individual branches but not retail trade as a whole. This type of revision is rare; there have been no other major revisions in the past 5 years.
17.2. Data revision - practice
G, G45, G46: Data has only been published in 2024, providing too few data points to calculate these values.
G47: The accuracy of the monthly growth rate is very high. For the final version of the total index, the uncertainty as measured by relative mean absolute revision (R-Mar) was 0,035 percent this year. While the mean absolute revision (MAR) for the final version of the index was a little higher with a value of 0.191 percent. Here too, approximately half of this uncertainty is due to non-sampling error.
18.1. Source data
G45 and G46: VAT declarations, i.e., monthly, quarterly or semi-annual reports (forms) submitted to the Central Customs and Tax Administration in connection with the payment of VAT. Background information from the Danish Business Register is also used.
G47: The survey is based on a sample of Danish retail trade enterprises. The sample includes approximately 2,200 enterprises, and at the time of the first publication, the figures for a month are based on responses from approximately 2,200 of these enterprises.
The sample consist of 42 subgroups and enterprises are sampled based on their share of the yearly turnover for the given subgroup. The companies are ranked from largest to smallest and the companies, whose rank constitutes the bottom 10 pct. of turnover for their subgroup when summed, are never selected to participate. The companies whose rank lies between 11 and 49 pct. of the subgroup’s yearly summed turnover, are randomly selected. Lastly, the larger firms whose turnover altogether lies in the top 50 pct. of the yearly turnover for their subgroup are always included in the sample. The companies are selected based on VAT-declarations to the Danish tax administration.
18.2. Frequency of data collection
Data is collected monthly.
18.3. Data collection
G45 and G46: The turnover i estimated from the VAT declarations submitted to the Tax Administration
G47: The turnover figures are reported by the enterprises in the sample either via a dial-in phone solution or an online questionnaire. Completion of the questionnaires is mandatory.
Supermarkets, discount stores, department stores as well as service stations sell a very wide variety of goods. In order to be able to estimate the turnover index for three main commodity groups, the enterprises of these four industries are requested to break down their turnover in three main commodity groups: Food and other convenience goods, Clothing etc. and Other consumer goods. If the enterprise is unable to submit an accurate breakdown, it is requested to estimate the share of sales stemming from each group.
Online form and instructions can be found on the information page (only in Danish).
18.4. Data validation
The submitted data undergo troubleshooting. If the reported turnover deviates considerably from earlier records or from that of similar enterprises for the relevant period, then the enterprise in question is asked to investigate the correctness of the returned turnover figures. It is assumed that not all errors in submitted forms are detected, and therefore the statistics are subject to some uncertainty connected to reporting errors. The troubleshooting focuses on the reports with most impact on the results, and the uncertainty connected to reporting errors is therefore normally considered quite low, especially when it comes to the monthly growth rates on an aggregate level.
18.5. Data compilation
G47: Totals are estimated from grossing up the reported data to the full population of retail trade enterprises, although enterprises below the cut-off limit are disregarded. For most industries, this limit is DKK 2.5 million in yearly turnover, and 1 million for a few industries, and the enterprises below the cut-off account for less than 5 per cent of the total retail trade turnover. In case of non-response amongst the largest enterprises, imputation is used. Usually, it is only necessary to impute values for less than 5 enterprises, corresponding to an imputation rate below 0.2 per cent.
In the estimation process, bias in the non-response pattern as well as in the sample is corrected by applying a ratio estimate, which includes information about the turnover subject to VAT for the previous year for the entire population of retail trade enterprises. This full population including information on the turnover subject to VAT is called the estimation population.
The calculation of the turnover totals behind the index figures is based on inter-monthly chaining. This means that every month growth rates are calculated by estimating totals for the month of interest and at the same time recalculating the previous month applying the same estimation population for both months. The ratio between these two totals is the growth rate for the month of interest. These growth rates are used to calculate turnover totals on which the index calculations are based, chaining on the actual estimated turnover totals for a single month. This month is currently January 2016.
The turnover is calculated by chaining on industry level. For the industries with turnover broken down by commodity groups, the chaining is performed on the level of commodity groups after which the industry totals are calculated by adding up the commodity group totals for each of these industries. The aggregate commodity group totals are calculated by adding up the relevant industry and commodity group totals.
Index values for a given month are calculated as the turnover of that month divided by the average monthly turnover of the base year (currently 2015). Consequently, turnovers are aggregated on industry level as well as commodity group and total level prior to the calculation of indices. In this way, no explicit weights are applied for calculation of aggregated indices. Instead, there is an implied use of internal weights, which are the turnover shares of the total turnover in the base year.
Only indices are published, not absolute turnover figures. For an idea of the level of absolute retail trade turnover of the individual industries, refer to the statistics on Purchases and sales by enterprises, which are based on VAT statements broken down by industries.
The volume indices for the commodity groups are calculated by deflating the value indices. This is done by dividing the turnover totals with appropriate price indices from the Consumer Price Index (CPI). The deflation is performed on the level of the commodity groups with the exception of the turnover of other consumer goods for the Service stations industry, which is deflated separately by means of a fuel price index. The deflated turnover totals are used for index calculations, and the result is a so-called indirect volume index.
More details on the calculations can be found in this methodology document (only in Danish).
18.6. Adjustment
To improve and harmonise the description of adjustment we answer the following questions:
Software used and version: JDemetra+, ver. 2.2.2 The model/filter selection (manual vs. automatic): Automatic How often are the models and the respective parameters re-estimated: Every two years The horizon of revisions (how often are the seasonally adjusted time series revised and how far backwards): From 2005, at every update (monthly) Seasonal adjustment decomposition (additive vs. multiplicative): Multiplicative The model used: X13-ARIMA, [(0,1,1)(0,1,1)] The critical value for outlier detection: Automatically, determined by the number of observations in the (full) series span The filter length (automatically chosen vs. user-defined): Automatically The date of seasonal breaks in the series: None Indicate if indirect adjustment via components is used: Direct adjustment Indicate whether residual seasonality is checked and from which level of detail the aggregation is started: Not applicable Indicate the consistency amongst the different levels of breakdown: Not applicable
Further information can be found at the subject-page for the Retail Trade Index or by contacting Statistics Denmark directly.
G: Data for G is a weighted combination of G45, G46 and G47. G45 and G46: Data for the calculation of the indeces are based on the VAT report made by national enterprises. Eurostat also receives seasonally adjusted data
G47: The value indices show the development of the turnover in current prices. The volume index is calculated indirectly by dividing the value index with a corresponding price index. In addition, the three main commodity groups are seasonally adjusted as well as the total. This includes adjustment for the effects of moving holidays (Easter), number of working days and trading days. Eurostat also receives seasonally adjusted data as well as data adjusted for working day and trading day effects only.
14 June 2024
Retail Trade: Sales of commodities to private individuals.
Retail Trade Enterprise: Enterprise mainly engaged in distributive sales of commodities to private individuals, here excluding sales of motorised vehicles.
Food and Other Everyday Commodities: Convenience goods are consumer goods that are consumed relatively quickly by a consumer and that cease to exist when consumed. Convenience goods are primarily foods and products for personal hygiene, but also tobacco.
Clothing etc.: Clothes, footwear and leather goods, incl. baby clothes and baby things.
Other Consumer Goods: Commodities not categorized as convenience goods or clothing etc. E.g. household appliances, leisure goods, medicine and fuel.
G, G45 and G46: KAU
G47: The units of the retail trade index are enterprises, each enterprise being a KAU combined with a legal unit. In the Statistical Business Register of Statistics Denmark, legal units are identified by their CVR-numbers, i.e. their numbers in the Central Business Register.
In isolated cases, a unit can be different from an enterprise. It could be an enterprise with shops having significant turnover within several retail trade industries, in which case the enterprise can be accordingly divided in several statistical units. The reverse example also exists, where more enterprises within the same industry are merged to one statistical unit, e.g. if they have a common administration that would in any case report for all the enterprises in question.
G: Data for G is a weighted combination of G45, G46 and G47
G45 and G46: Data is from a total count, there for no Non-sampling error.
G47: The statistics covers the population consisting of all enterprises with main activity, or in a few rare cases secondary activity within retail trade, with the exception of retail trade of motor vehicles. Furthermore, bakeries with their own production are also included in the population. The population consists altogether of approximately 18.500 enterprises cf General enterprise statistics by industry (www.statistikbanken.dk/GF01).
The statistics cover retail trade in Denmark by Danish retail trade enterprises, excluding Greenland and Faroe Islands. Foreign enterprises with retail trade with Danish consumers (e.g. near-border enterprises or foreign internet shops) are not included in the statistics.
The reference period (t) for the monthly figures is the entire month.
G, G45 and G46: t+2 month
G47: The enterprises thus report the turnover of the entire month. A few enterprises have 4- or 5-weeks accounting periods and many normally only make up their accounts on a quarterly basis, which can cause the monthly turnover reports to be somewhat inaccurate. This, however, is not assessed as a significant quality issue. The population used for estimation usually has a reference time that is the previous year. This does not significantly affect the calculations of the monthly growth rates, due to the use of month-on-month linking where the actual and the previous month turnover is always estimated using the same population.
The general assessment is that the quality of the statistics is high, with a few reservations. Using the time series for long-term analysis can be problematic. This is because of the way the retail trade index is designed and calculated, where not all structural changes in the population and sample are reflected in the figures (e.g. changes in the activity codes causing units to enter or leave the retail trade sector), which is why chaining is used in the calculation of growth rates for the value indices (see data compilation).
Moreover, there will typically be a slight underestimation of the volume index in periods where consumers are buying less expensive goods and in low-priced stores, and correspondingly there will be a slight overestimation in periods where consumers choose high-end goods and stores. This is caused by the use of CPI sub-indices as deflators for calculating the volume indices. The quality of the volume indices is generally very dependent on the composition of these deflators used in the conversion from value index to volume index. In periods with changing consumption patterns, the deflation, and hence the volume indices, are less accurate, because CPI does not reflect all the changes.
A provisional analysis shows that the lack of consideration of the above-mentioned substitution effects have had an effect on the volume index in recent years causing an underestimation of the yearly growth rates of approximately 0.2-0.4 percentage points.
To state the overall accuracy, one must distinguish between the accuracy of the estimated totals and the accuracy if the monthly growth rates, which is the prime focus of these statistics.
The overall uncertainty of the total index is estimated to be less than 1 per cent. On commodity group level, the uncertainty of the group Food and other convenience goods is about the same, whereas for Clothing etc. it can be as high as 3 per cent and for Other consumer goods up to 2 per cent.
The accuracy of the monthly growth rate is generally very high. For the total index, the uncertainty is estimated to be less than 0.2 percentage points, while it can be a little higher on commodity group level. In a few cases, non-response from highly essential enterprises can cause slightly lower accuracy in the first publication of figures for a particular month.
The unit of measure is index points. Value indices as well as volume indices are published. Read more about indices in this publication (only in Danish).
G47: Totals are estimated from grossing up the reported data to the full population of retail trade enterprises, although enterprises below the cut-off limit are disregarded. For most industries, this limit is DKK 2.5 million in yearly turnover, and 1 million for a few industries, and the enterprises below the cut-off account for less than 5 per cent of the total retail trade turnover. In case of non-response amongst the largest enterprises, imputation is used. Usually, it is only necessary to impute values for less than 5 enterprises, corresponding to an imputation rate below 0.2 per cent.
In the estimation process, bias in the non-response pattern as well as in the sample is corrected by applying a ratio estimate, which includes information about the turnover subject to VAT for the previous year for the entire population of retail trade enterprises. This full population including information on the turnover subject to VAT is called the estimation population.
The calculation of the turnover totals behind the index figures is based on inter-monthly chaining. This means that every month growth rates are calculated by estimating totals for the month of interest and at the same time recalculating the previous month applying the same estimation population for both months. The ratio between these two totals is the growth rate for the month of interest. These growth rates are used to calculate turnover totals on which the index calculations are based, chaining on the actual estimated turnover totals for a single month. This month is currently January 2016.
The turnover is calculated by chaining on industry level. For the industries with turnover broken down by commodity groups, the chaining is performed on the level of commodity groups after which the industry totals are calculated by adding up the commodity group totals for each of these industries. The aggregate commodity group totals are calculated by adding up the relevant industry and commodity group totals.
Index values for a given month are calculated as the turnover of that month divided by the average monthly turnover of the base year (currently 2015). Consequently, turnovers are aggregated on industry level as well as commodity group and total level prior to the calculation of indices. In this way, no explicit weights are applied for calculation of aggregated indices. Instead, there is an implied use of internal weights, which are the turnover shares of the total turnover in the base year.
Only indices are published, not absolute turnover figures. For an idea of the level of absolute retail trade turnover of the individual industries, refer to the statistics on Purchases and sales by enterprises, which are based on VAT statements broken down by industries.
The volume indices for the commodity groups are calculated by deflating the value indices. This is done by dividing the turnover totals with appropriate price indices from the Consumer Price Index (CPI). The deflation is performed on the level of the commodity groups with the exception of the turnover of other consumer goods for the Service stations industry, which is deflated separately by means of a fuel price index. The deflated turnover totals are used for index calculations, and the result is a so-called indirect volume index.
More details on the calculations can be found in this methodology document (only in Danish).
G45 and G46: VAT declarations, i.e., monthly, quarterly or semi-annual reports (forms) submitted to the Central Customs and Tax Administration in connection with the payment of VAT. Background information from the Danish Business Register is also used.
G47: The survey is based on a sample of Danish retail trade enterprises. The sample includes approximately 2,200 enterprises, and at the time of the first publication, the figures for a month are based on responses from approximately 2,200 of these enterprises.
The sample consist of 42 subgroups and enterprises are sampled based on their share of the yearly turnover for the given subgroup. The companies are ranked from largest to smallest and the companies, whose rank constitutes the bottom 10 pct. of turnover for their subgroup when summed, are never selected to participate. The companies whose rank lies between 11 and 49 pct. of the subgroup’s yearly summed turnover, are randomly selected. Lastly, the larger firms whose turnover altogether lies in the top 50 pct. of the yearly turnover for their subgroup are always included in the sample. The companies are selected based on VAT-declarations to the Danish tax administration.
These statistics are published monthly.
G47: The first published figures for a given month are published 20-22 days after the end of the reference period and only include figures on the three main commodity groups (not industries). On industry level, the first publication is one month later. At the same time, the first published figures on commodity groups are revised. Hence, these figures are published 50-52 days after the end of the reference period.
One month later, the final revision of the figures is made for both the commodity groups and the figures on industry level (which are thus only revised once). Hence, the final figures are published 70-72 days after the end of the reference month.
Every month, figures are submitted to the statistical office of EU, Eurostat. These include special industry aggregates which are not published nationally. Data for all EU countries can be found in the Eurostat database. The statistics are produced following the common guidelines and principles of an EU regulation, so the results are comparable.
The statistics have been compiled since 1939, but they are not suited for long term time series analysis because of structural changes in the retail trade sector. The sample design and the calculation methods have been adjusted several times, last time in May 2012, where the time series back to 2000 where recalculated using new methods. More on that complete revision can be found in this publication (in Danish)
In Statbank Denmark historical time series going back to 1979 can be found, but due to differences in methodology and classifications, comparisons to the current time series going back to 2000 is not advisable.
