Harmonised index of consumer prices (HICP) (prc_hicp)

National Reference Metadata in Euro SDMX Metadata Structure (ESMS)

Compiling agency: Statistics Denmark

Time Dimension: 2017-A0

Data Provider: DK1

Data Flow: HICP_ESMS_A


Eurostat metadata
Reference metadata
1. Contact
2. Metadata update
3. Statistical presentation
4. Unit of measure
5. Reference Period
6. Institutional Mandate
7. Confidentiality
8. Release policy
9. Frequency of dissemination
10. Accessibility and clarity
11. Quality management
12. Relevance
13. Accuracy
14. Timeliness and punctuality
15. Coherence and comparability
16. Cost and Burden
17. Data revision
18. Statistical processing
19. Comment
Related Metadata
Annexes (including footnotes)
 



For any question on data and metadata, please contact: EUROPEAN STATISTICAL DATA SUPPORT

Download


1. Contact Top
1.1. Contact organisation

Statistics Denmark

1.2. Contact organisation unit

Prices and Consumption

1.5. Contact mail address

Sejroegade 11, 2100 København Ø, Denmark


2. Metadata update Top
2.1. Metadata last certified 22/03/2017
2.2. Metadata last posted 22/03/2017
2.3. Metadata last update 22/03/2017


3. Statistical presentation Top
3.1. Data description

Harmonised indices of consumer prices (HICPs) give comparable measures of inflation for the countries and country groups they are produced. They are economic indicators that measure the change over time of the prices of consumer goods and services acquired by households. In other words they are a set of consumer price indices (CPIs) calculated according to a harmonised approach and a single set of definitions.

3.2. Classification system

ECOICOP (European Classification of Individual Consumption by Purpose ). 5-digit level is accesible from December 2009 onwards at Eurostats homepage. Higher levels are accesible from 1996 onwards.

3.3. Coverage - sector

HICPs cover the whole household sector, more precisely the goods and services that are acquired by households.

3.4. Statistical concepts and definitions

The published data is as follows:
1. Monthly data:

  • Indices (HICP 2015=100, HICP at constant taxes 2015=100)
  • Annual rates of change
  • Monthly rates of change
  • 12-month average rate of change

2. Annual data:

  • Average index and rate of change
  • Country weights
  • Item weights
3.5. Statistical unit

Each published index or rate of change refers to the 'final monetary consumption expenditure' of the whole household sector of Denmark.

3.6. Statistical population

The target statistical universe is the 'household final monetary consumption expenditure' (HFMCE) within the economic territories of the countries compiling the HICP. The household sector to which the definition refers includes all individuals or groups of individuals irrespective of, in particular, the type of area in which they live, their position in the income distribution and their nationality or residence status. These definitions follow the national accounts concepts in the European System of Accounts.
HICPs comprise all purchases by households within the territory of a country; those by both resident and non-resident households (i.e. 'domestic concept'). HICPs cover the prices paid for goods and services in monetary transactions. The prices measured are those actually faced by consumers. The HICPs exclude interest and credit charges, regarding them as financing costs rather than consumption expenditure.

3.7. Reference area

Private household consumption within the economic area of Denmark is included in the HICP. No part of the economic territory of Denmark is excluded and prices are collected in the entire country. Prices for fresh food and clothing are mainly collected from outlets located in towns, since these prices are collected by price collectors. Prices from the biggest supermartket chains are covered by scanner data for COICOP groups 1 and 2.

3.8. Coverage - Time

Monthly HICPs for Denmark are available from 1995 (earlier data are estimated on the basis of the national CPI).

3.9. Base period

The index reference period is 2015=100.


4. Unit of measure Top

Following units are used:

  • Index (actually unitless, i.e. it is the ratio of the price of the basket in a given year to the price in the base year multiplied by 100. However, the HICP can be thought of as the amount the average consumer would have to spend in a given year to buy the same basic goods and services that one would have to pay 100 monetary units for in the base period);
  • Percentage change on the same period of the previous year (rates);
  • Percentage change on the previous period (rates);
  • Percentage share of the total (weights).


5. Reference Period Top

Month.


6. Institutional Mandate Top
6.1. Institutional Mandate - legal acts and other agreements

Harmonised Indices of Consumer Prices (HICPs) are harmonised inflation figures required under the Treaty on the Functioning of the European Union. Council Regulation (EC) no 2494/95 first set the legal basis for establishing a harmonised methodology for the compilation of the HICPs, the MUICP and the EICP.

A new framework regulation, Council regulation (EC) No 2016/792, has recently been agreed upon.

The Commission has brought forward detailed Regulations establishing the specific rules governing the production of harmonised indices. To date, 22 specific regulations governing issues as quality of weights, transmission and dissemination of sub-indices, coverage of goods and services, geographical and population coverage, minimum standards for the treatment of tariffs, insurance, health, education and social protection services, timing of entering prices, treatment of price reductions, treatment of service charges, revisions policy,  new index reference period, temporal coverage of price collection and sampling, replacement and quality adjustment procedures, and seasonal items as well as weight updates,Owner-occupied housing, HICP at constant taxes, have been adopted. A recommendation on the treatment of health care has also been published.

All relevant regulations as well as further methodological details can be found in the HICP section on Eurostat's website under Methodology => Legislation.

6.2. Institutional Mandate - data sharing

None.


7. Confidentiality Top
7.1. Confidentiality - policy

Regulation (EC) No 223/2009 of the European Parliament and of the Council, of 11 March 2009, on the transmission of data subject to statistical confidentiality to the Statistical Office of the European Communities.
'Persondataloven' gives restrictions regarding publication and sharing of data that can be attributed to individual persons. 'Forvaltningsloven' rules that data collected for statistical purposes cannot be shared with other public authorities for other purposes.

7.2. Confidentiality - data treatment

Statistics Denmark will never publish data that can be attributed to an individual person or a single company. Only aggregated data will be published.


8. Release policy Top
8.1. Release calendar

The Danish HICP are always released simultaneously to all interested parties at 9:00 a.m. on the 10th of the month or the first working day thereafter following the month in which the data were collected.

8.2. Release calendar access

Release dates of all countries HICP's at Eurostat can be found at Eurostats homepage.

8.3. Release policy - user access

The Danish HICP is released to all users at the same time. No one outside Statistics Denmark gets access to the data before publication.


9. Frequency of dissemination Top

Harmonised consumer price indices are produced monthly.


10. Accessibility and clarity Top
10.1. Dissemination format - News release

The data are released simultaneously to all interested parties at 9:00 a.m. on the 10th of the month or the first working day thereafter following the month in which the data were collected, by issuing the news release 'Nyt fra Danmarks Statistik' at www.dst.dk. The data are also released at the same time in www.statistikbanken.dk.

10.2. Dissemination format - Publications

Overall indices and sub-groups are published at www.statistikbanken.dk 

10.3. Dissemination format - online database

The Danish HICP can be accessed directly at www.statbank.dk/pris117 . The Danish HICP-CT can be accessed directly at www.statbank.dk/pris118.

10.4. Dissemination format - microdata access

Researchers wishing access to Danish HICP micro data should contact Statistics Denmark to enquire whether it will be possible to get access to the data given the specific circumstances. Micro data will always be made anonymous so that it cannot be attributed to a single individual company.

10.5. Dissemination format - other

The Internet web site (http://www.dst.dk/da/Statistik/emner/priser-og-forbrug/forbrugerpriser) disseminates time series for the overall CPI, the net price index and the Danish Harmonised Index of Consumer Prices (HICP). Furthermore different documentation and the weights used in the calculations are also presented here.

10.6. Documentation on methodology

The methodology is described in a 'Statistical documentation' which can be found at http://www.dst.dk/da/Statistik/emner/priser-og-forbrug/forbrugerpriser/forbrugerprisindeks and documentation (in Danish) is available on the homepage as well.

10.7. Quality management - documentation

See Eurostat's Compliance Monitoring Report of 2010.


11. Quality management Top
11.1. Quality assurance

Controls on the quality of the data

When data are entered into the database they are checked manually for obvious errors. Before calculating the HICP, the consistency of the data is checked automatically. Checks are made to see whether there is a price match between the current and previous month for all observations and to detect decimal errors.

Extremes are detected automatically by the Hidiroglou-Berthelot (HB) model for product groups with more than five price changes. For product groups with less than five price changes, extremes are identified as price changes of more than 10 percent. The extremes are checked manually and included or excluded accordingly.

When the indices have been calculated, they are checked manually for unusual changes.

11.2. Quality management - assessment

The edited HICP data is considered to be of good quality.
Furthermore see Eurostat's Compliance Monitoring Report of 2010.


12. Relevance Top
12.1. Relevance - User Needs

The users of the HICP are primarily the European Central Bank, the European Commission, the Ministry of Economic and Business Affairs, and the Danish National Central Bank. As HICP has been calculated on a comparable basis in all EU countries, the figures are primarily used where there is a need for comparing development in consumer prices.

12.2. Relevance - User Satisfaction

User satisfaction surveys are not performed but the general view is that quality of the Danish HICP is satisfactory. Once a year a meeting is held with main Danish users of price statistics and this is the usual response to the HICP.

12.3. Completeness

The ECOICOP indices at 5-digit level being produced can be seen in the weights table availible at http://www.dst.dk/da/Statistik/emner/priser-og-forbrug/forbrugerpriser/forbrugerprisindeks


13. Accuracy Top
13.1. Accuracy - overall

Overall accuracy
The overall reliability of the HICP is considered to be high.

 

Sources of inaccuracy
The sample
The HICP is calculated on the basis of a sample of approx. 24 500 prices collected from some 1 500 shops, companies and institutions throughout Denmark. Most prices are by far collected monthly. For goods and services, where the prices typically change less frequently, prices are collected more rarely, for instance quarterly or biannually. For clothing and fresh food etc. prices are collected by price collectors who visit the individual shops.For the biggest supermarket chains for COICOP groups 1 and 2, they are also covered by scanner data. For the remaining groups of goods and services, prices are mainly obtained from digital questionnaries, list prices from supermarkets outside COICOP group 1 and 2 are also used. Finally, Statistics Denmark obtains information on prices on a number of selected goods and services by telephone or via the Internet. The weights are created on the basis of the information about the composition of consumption expenditure according to the national accounts and the Household Budget Survey.
No calculation has been made of the uncertainty connected with sampling in the HICP. The statistical uncertainty inherent in the weights affects the uncertainty in the HICP, but the effect is very limited. The non-response in the sample is estimated to be less than 1 pct.
In addition to the 'general' uncertainty connected with sampling, there are a number of sources of potential bias in the HICP, which can be grouped as follows:

Substitution between goods
Bias due to substitution between goods is a result of the fact that for different reasons (changes in income and in relative prices or preferences), consumers substitute between different goods, although an unchanged composition of consumption is assumed in the calculation of the price index. The HICP is calculated as the weighted arithmetic average of the most detailed price indices (elementary aggregate indices) with their respective budget shares used as weights. At this level of the index calculation no allowances are therefore made for the consumers' substitution between different groups of goods and services (elementary aggregates). However, the elementary aggregate indices are calculated as geometrical indices. Thereby it is assumed that the consumers hold unchanged budget shares. This means that if the price of a commodity rises by x pct., the consumers are assumed to reduce their consumption of the commodity by x pct. For these groups a certain substitution has thus been recognised in the index.

Substitution between shops
This type of bias arises when the consumers for the same commodity change from shops with high prices to shops with lower prices. The HICP is calculated monthly on the basis of price information from the same shops. If, e.g. greater shares of the consumers' expenditure from July until August is accounted for by discount shops with lower prices, this will not in itself have an impact on the index. Only when a shop has been included for at least two months in succession are the prices from there included in the index calculation.

Changes in quality
In calculating a price index it is assumed that the baskets of goods that are compared are identical, also with respect to the quality of the goods. Consequently, in the case of changes in quality the prices should, in principle, be adjusted for this. As the value of the actual changes in quality is not known, it is naturally difficult to calculate estimates for bias, due to lack of quality adjustment.

New commodities
The sample for the HICP is continuously updated, but for practical reasons often with a certain time lag. This means that new products are frequently not included in the compilation of the index x when they are first introduced on the market, and not until prices have been available for two months in succession. Furthermore, at the beginning of a product's lifetime it is often impossible to obtain any information about sales. Finally, a great deal of uncertainty is associated with the task of defining whether it is actually a new product or just improved versions/varieties of already existing products.

Calculation formula
The first step in the index calculation consists of calculating the elementary aggregate index from the prices collected (and any weights for these prices). To the extent that the index calculated on this basis deviates from the 'true' price rise, it is a formula bias. Frequent updates of the weights and the sample can reduce the potential bias as a result of the consumers' substitution between goods and shops and the appearance of new goods.

13.2. Sampling error

Statistics Denmark does not produce numerical estimates of HICP sampling errors because they are difficult to quantify due to the complexity of price index structures and due to use of non-probability sampling.

13.3. Non-sampling error

Non-sampling errors are not quantified.


14. Timeliness and punctuality Top
14.1. Timeliness

The Danish HICP are always released simultaneously to all interested parties at 9:00 a.m. on the 10th of the month or the first working day thereafter following the month in which the data were collected.

14.2. Punctuality

The Danish HICP has always been published on time.


15. Coherence and comparability Top
15.1. Comparability - geographical

The comparability of HICP across countries is regarded to be high. Definitions and classifications have been harmonised in a series of legal acts that have resolved conceptual disparities. HICPs are produced based on minimum standards, which may be applied with some flexibility as long as the effect on the value of the indicator remains below 0.1%.
The work carried out for the harmonisation of quality adjustment and sampling methods across EU countries is expected to further improve the comparability of the HICP.

15.2. Comparability - over time

HICP data are fully comparable over time. There have been several improvements in methodology since HICP was introduced with the aim of improving reliability and comparability of the HICP. These changes may have introduced breaks in time series. However back calculations under the newer standards were performed when appropriate basic data was available.

15.3. Coherence - cross domain

Differences between the HICP and national CPI

The national CPI and the HICP are based on exactly the same price observations for the same items collected from the same outlets. Gross prices are used in both cases. There is also no difference between the methods of calculating the national CPI and the HICP. The only difference is the coverage.

All expenditure consumption included in the HICP is also included in the national CPI, but owner-occupied dwellings and insurance in connection with owner-occupied dwellings are not included in the HICP; they are included in the national CPI instead.

15.4. Coherence - internal

HICPs are internal coherent. Higher level aggregations are derived from detailed indices according to well-defined procedures.


16. Cost and Burden Top

Approximately 6 persons are working on compiling the HICP as well as other consumer price indices in Statistics Denmark. This includes all aspects of the statistical production from data collection, validation, calculations and publications. Furthermore approximately 16 persons are working as price collectors 2 days a month.
The response burden has been estimated at 2 048 hours.


17. Data revision Top
17.1. Data revision - policy

HICP series, including back data, are revisable under the terms set in Commission Regulation (EC) No 1921/2001 of 28 September 2001. The published HICP data may be revised for mistakes, new or improved information, and changes in the system of harmonised rules.

17.2. Data revision - practice

Data are considered final when published and are not revised.


18. Statistical processing Top
18.1. Source data

Sample size (reference year 2017)

Approximately 24500 price observations are collected every month.

 

Number of representative items at the lowest classification level: 
All-items: 904

01 Food and non-alcoholic beverages: 182 02 Alcoholic beverages, tobacco: 25
03 Clothing and footwear: 74
04 Housing, water, electricity, gas and other fuels: 55
05 Furnishings, household equip. and routine maintenance of the house: 79
06 Health: 23
07 Transport: 144
08 Communications: 29
09 Recreation and culture: 127
10 Education: 12
11 Restaurants and hotels: 24
12 Miscellaneous goods and services: 130 

18.2. Frequency of data collection

Timing of price observation
Most prices are collected between the 7th and 15th of every month. No prices for the same goods and services from the same outlet are collected more than once during the month. For fresh foods the prices are collected between the 7th and 18th of every month to make sure that prices for different fresh foods are collected from at least to different working weeks. Energy prices are collected up to three times a month throughout the month.

18.3. Data collection

Outlet selection
Prices are collected from approximately 1 500 retail outlets every month. The outlet sample is in principle updated every month. If an outlet leaves the sample it is immediately replaced. Likewise new outlets can be included in the sample any given month.  The outlets are sampled using purposive sampling taking into account the outlet turnover (Cut-off sampling). The aspects taken into account when sampling outlets is included are geographical coverage and consumer shopping habits (representativity).

 

Techniques of products selection and specification
The representative goods and services in the sample are selected using purposive sampling. The specific brand etc. of an item is then mainly chosen by the outlets in the sample. For instance, Statistics Denmark decides that prices for smart phones should be sampled. It is then for the outlets in the sample to select which smart phone to report a price for. The outlets are instructed to choose the most representative smart phone according to sales, for example. When prices are collected by price collectors, it is the price collector that selects the brand etc.
The item/product specifications used for all the representative goods and services are relatively broad (e.g. smart phone or refrigerator without freezer).
Prices for clothing and fresh food are collected by price collectors visiting the outlets. Prices for the major supermarkets are collected via scanner data for COICOP groups 1 and 2. The majority of prices are collected by a digital questionnaire sent to the outlets in the sample. The remaining prices are collected from price lists (outside COICOP 1 and 2) and the like, and via the internet (telecommunications, computers, petrol and others).  

18.4. Data validation

Controls on the quality of the data
When data are entered into the database they are checked manually for obvious errors. Before calculating the HICP, the consistency of the data is checked automatically. Checks are made to see whether there is a price match between the current and previous month for all observations and to detect decimal errors.
Extremes are detected automatically by the Hidiroglou-Berthelot (HB) model for product groups with more than five price changes. For product groups with less than five price changes, extremes are identified as price changes of more than 10 percent. The extremes are checked manually and included or excluded accordingly.
When the indices have been calculated, they are checked manually for unusual changes.

18.5. Data compilation

Weights
The sources of the weights are the National Accounts at the highest level and the Household Budgetary Survey at the lowest level. There are 454 national weights at the elementary aggregate level. Furthermore, in some cases product and outlet weights are used in the compilation of the HICP. The present weights reference period is the year 2015 and the price reference period is December 2016. The weights are updated every year, which has been the case since Janaury 2012.

 

Computation of the lowest-level indices
Almost all elementary aggregate (EA) indices are calculated as the geometric mean of price relatives. Only the EAs for rents and medicines are calculated as the ratio of the arithmetic mean. Weights for outlets and type of product are used for some specific EA. The EA indices are calculated as monthly chained indices.
All higher-level indices are calculated as the weighted arithmetic mean of the elementary aggregate indices of which they consist. The weights correspond to the relative share of total consumer expenditure in the different elementary aggregates

 

Treatment of missing items and replacements
When a product leaves the market, and therefore the sample, outlets and price collectors have been instructed to select a replacement immediately. The nearest substitute or the product with largest sale is chosen, depending on the circumstances.
When a price observation is missing it is usually estimated based on changes in prices from the previous month of the same group of products. If the price is expected to be missing for only a short period (a month), the previous price is sometimes carried forward.
Product prices for replacements are compared with the prices of the products leaving the sample after quality adjustment, if necessary.

 

Introduction of newly significant goods and services
Every month a 'quality meeting' is held with participation of the HICP staff. At these meetings the sample is scrutinized and potential newly significant goods and services are identified. Different data sources are then used to check whether the potentially significant goods should be included in the HICP.
Newly significant goods and services can be introduced into the sample every month as long as they belong to the existing elementary aggregates.

 

Treatment of price reductions
All sales prices are included in the HICP. However, the first price observation included in the HICP for a new good or service most not be a sales price. If a product leaves the sample at a sales price and there is no replacement available, a price increase from the sales price to the 'typical' price of the product is included in the HICP the following month.

 

Treatment of seasonal items
Seasonal items in the Danish HICP are clothing, footwear, potatoes, holiday packages, cut flowers, garden plants and amusement parks. For fresh fruits and vegetables other than potatoes, only products that can be found the whole year are followed.
In the first month of the out-of-season period the price of an out-of-season product is estimated using a 'typical' price observed in the in-season period. The following months the price is estimated using the average price change of a group of similar products. For instance, two sets of clothing, for summer and winter respectively, are used: only the summer clothing enters into the index in the summer period and vice versa in the winter period. When the summer clothes are out-of-season, prices are estimated using the price changes in winter clothing. 

18.6. Adjustment

Adjustment for quality differences
When the quality is assessed not to have changed significantly, the whole of the price difference is taken into the index. When the quality change is assessed to be significant, the price change between items leaving and entering the sample is usually imputed by the average price change in the corresponding elementary aggregate. The rest of the price difference between the items leaving and entering the sample is implicitly assumed to be due to a quality difference. Otherwise overlapping prices or 'monthly matched model and chaining' (computers) are used if possible and appropriate. Explicit quality adjustments are made for rented dwellings.


19. Comment Top

None.


Related metadata Top


Annexes Top