|
For any question on data and metadata, please contact: Eurostat user support |
|
|||
1.1. Contact organisation | National Statistical Institute of Bulgaria. |
||
1.2. Contact organisation unit | Consumer Prices, Housing prices and PPP Department. |
||
1.5. Contact mail address | 2, P. Volov Str. |
|
|||
2.1. Metadata last certified | 27/08/2024 | ||
2.2. Metadata last posted | 27/08/2024 | ||
2.3. Metadata last update | 27/08/2024 |
|
|||
3.1. Data description | |||
The harmonised index of consumer prices (HICP) is a consumer price index (CPI) that is calculated according to a harmonised approach. It measures the change over time of the prices of consumer goods and services acquired by households (inflation). Due to the common methodology, the HICPs of the countries and European aggregates can be directly compared. |
|||
3.2. Classification system | |||
European classification of individual consumption according to purpose (ECOICOP) |
|||
3.3. Coverage - sector | |||
The HICP covers the final monetary consumption expenditure of the household sector. |
|||
3.4. Statistical concepts and definitions | |||
The main statistical variables are price indices. |
|||
3.5. Statistical unit | |||
The basic unit of statistical observation are prices for consumer products. |
|||
3.6. Statistical population | |||
See next points. |
|||
3.6.1. Statistical target population | |||
The target statistical universe is the 'household final monetary consumption expenditure' (HFMCE) on the economic territory of the country by both resident and non-resident households. 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. |
|||
3.6.2. Coverage error population | |||
No deviations from the target population. |
|||
3.7. Reference area | |||
See next points. |
|||
3.7.1. Geographical coverage | |||
The HICP refers to the economic territory of a country as referred to in paragraph 2.05 of Annex A to ESA 2010, with the exception that the extraterritorial enclaves situated within the boundaries of a Member State or a country are included and the territorial enclaves situated in the rest of the world are excluded. |
|||
3.7.2. Coverage error regions | |||
Bulgaria has no overseas territories. The economic territory of Bulgaria consists of the geographic territory. The HICP covers the entire economic territory consistent with NA. The NA estimates follow the definitions laid down in ESA2010. No parts of the economic territory of Bulgaria are excluded from the index. |
|||
3.8. Coverage - Time | |||
See next points. |
|||
3.8.1. Start of time series | |||
The HICP series started in January 1997. |
|||
3.8.2. Start of time series - national specifics | |||
January 1997 |
|||
3.9. Base period | |||
2015=100 |
|
|||
The following units are used:
|
|
|||
HICP is a monthly statistics. |
|
|||
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. Regulation (EU) 2016/792 of the European Parliament and the Council of 11 May 2016 (OJ L 135) sets the legal basis for establishing a harmonised methodology for the compilation of the HICP and the HICP-CT. This regulation is implemented by Commission Regulation (EU) 2020/1148 of 31 July 2020. Further methodological documentation, namely recommendations and guidelines, is available in the HICP dedicated section, under 'Methodology'. |
|||
6.2. Institutional Mandate - data sharing | |||
None. |
|
|||
7.1. Confidentiality - policy | |||
Legal basis: 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; Statistics Act | National statistical institute (nsi.bg) The confidentiality of the HICP data set is treated in respect of national legislation: Law of Statistics, Chapter Six ‘Protection of secrecy’, Articles 25, 26, 26a, 27 and 27a. Art. 25 stipulates that individual data (‘individual data’ are data about a specific statistical unit) received and collected through statistical surveys shall constitute a statistical secret and may be used only for statistical purposes. Individual data received for the purposes of statistical surveys may not be used as evidence before the bodies of the executive and the judiciary. The NSI and statistical authorities and their staff may not disclose or provide:
The individual data may be provided only if:
Individual anonymous data is provided for the purposes of scientific research to higher schools or legal entities, whose main activity is scientific research, with a permission of the Chairperson of the National Statistical Institute. According to the Law of statistics the receipt, processing, usage and storage of statistical data representing statistical secret is carried out in a procedure set out in a regulation endorsed by the President of the National Statistical Institute. The Section 3 of the Rules for Dissemination of Statistical Products and Services endorsed by the President of the NSI regulate the protection of secrecy of individual data. The Rules for Provision of Anonymised Individual Data for Scientific and Research Purposes endorsed by the President of the NSI regulate the relations in terms of provision of anonymised individual data by the NSI for scientific and research purposes and the order of their receipt by the users. |
|||
7.2. Confidentiality - data treatment | |||
Data are treated in respect of national legislation: Individual data are not published in accordance with article 25 of the Law on Statistics. The publishing of individual data can be performed only in accordance with article 26 of the same law. Statistics Act | National statistical institute (nsi.bg)
Specific rules for treating the data set with regard to statistical confidentiality are applied according to the Rules for Provision of Anonymised Individual Data for Scientific and Research Purposes endorsed by the President of the NSI.
In case of data anonymisation the following requirements are applied:
|
|
|||
In line with the Community legal framework and the European Statistics Code of Practice Eurostat disseminates European statistics on Eurostat's website (see point 10 - 'Accessibility and clarity') respecting professional independence and in an objective, professional and transparent manner in which all users are treated equitably. The detailed arrangements are governed by the Eurostat protocol on impartial access to Eurostat data for users. |
|||
8.1. Release calendar | |||
The HICP is released according to Eurostat’s Release calendar. The calendar is publically available and published at the end of the year for the full following year. |
|||
8.2. Release calendar access | |||
8.3. Release policy - user access | |||
On the release date, the press release is sent to the President of the Republic of Bulgaria, the parliament, the government and the media simultaneously. The data for consumer price indices are accessible to all users through the website of NSI and through 'Relations with Users and e-Services' Department in NSI. |
|
|||
Monthly. |
|
|||
Bulgarian HICP is disseminated monthly. HICP data is published in the following NSI’s publications in printed and/or electronic format: Monthly, in electronic format:
Quarterly, in electronic format:
Annually, in electronic and/or printed format:
The HICP rates are disseminated with one decimal. The index levels are disseminated with two decimals. The HICP metadata and methodology are available on NSI’s website: Harmonised Indices of Consumer Prices (HICP) | National statistical institute (nsi.bg)
All publications are available in both Bulgarian and English. |
|||
10.1. Dissemination format - News release | |||
The press release ‘Inflation and Consumer Price Indices’ is issued monthly and the HICP data is included together with CPI and Price Index of Small Basket (PISB) data. The press release is regularly published to a strict, pre-announced timetable - in general from 14 to 16 days after the month in a question. The HICP data included in the press release cover the price indices (2015=100), monthly indices and rates of change, annual indices and indices for the current month compared to December of the previous year. |
|||
10.2. Dissemination format - Publications | |||
HICP table data and press release are available on NSI’s website, theme Inflation and Consumer Price Indices: Inflation and Consumer Price Indices | National statistical institute (nsi.bg) HICP data are also published in the following NSI publications in printed and/or electronic format:
|
|||
10.3. Dissemination format - online database | |||
On-line database on NSI’s website, Information System INFOSTAT: |
|||
10.4. Dissemination format - microdata access | |||
In principle, there is no access to microdata. The microdata, as long as it is not confidential, could be provided to users on request without a breach of the confidentiality principle. |
|||
10.5. Dissemination format - other | |||
See also Eurostat´s HICP website: |
|||
10.6. Documentation on methodology | |||
The HICP Methodological Manual provides the reference methodology for the production of HICP. |
|||
10.6.1. Documentation on methodology - national specifics | |||
The HICP metadata and methodology are available on NSI’s website: Harmonised Indices of Consumer Prices (HICP) | National statistical institute (nsi.bg) |
|||
10.7. Quality management - documentation | |||
The HICP Quality Reports is available on NSI’s internet site: Harmonised Indices of Consumer Prices (HICP) | National statistical institute (nsi.bg) |
|
|||
The quality activities in Bulgarian National Statistical System (NSS) are built on the fifteen principles of the European Statistics Code of Practice, covering the institutional environment, statistical processes and statistical outputs. The NSS Quality Assurance Framework includes methods and tools that aim to guarantee the compliance with the requirements to the statistical processes and products, and to ensure the required statistical information quality. Documents: Strategic and methodological documents European Statistics Code of Practice Quality Declaration of the European Statistical System Commitment on Confidence in Statistics Quality and Information Security Management Policy Statement of the NSI Handbook on Internal Quality Audit in the NSI Quality assessment |
|||
11.1. Quality assurance | |||
11.1.1. Quality management - Compliance Monitoring | |||
The quality activities in Bulgarian National Statistical System (NSS) are built on the sixteen principles of the European Statistics Code of Practice - Eurostat (europa.eu), covering the institutional environment, statistical processes and statistical outputs. The NSS Quality Assurance Framework includes methods and tools that aim to guarantee the compliance with the requirements to the statistical processes and products, and to ensure the required statistical information quality. One of the main tasks of Consumer Prices, Housing prices and PPP Department is to control all processes, related to the CPI/HICP production with respect to the quality of the index results. The following processes are covered by that task:
Evaluation of the completeness and accuracy of the information and assurance of the compliance of the HICP sub-indices with comparability and quality requirements
|
|||
11.1.2. Quality assurance - national specifics | |||
The quality activities in Bulgarian National Statistical System (NSS) are built on the fifteen principles of the European Statistics Code of Practice (https://ec.europa.eu/eurostat/web/quality/european-quality-standards/european-statistics-code-of-practice), covering the institutional environment, statistical processes and statistical outputs. The NSS Quality Assurance Framework includes methods and tools that aim to guarantee the compliance with the requirements to the statistical processes and products, and to ensure the required statistical information quality. One of the main tasks of Consumer Prices, Housing prices and PPP Department is to control all processes, related to the CPI/HICP production with respect to the quality of the index results. The following processes are covered by that task:
Evaluation of the completeness and accuracy of the information and assurance of the compliance of the HICP sub-indices with comparability and quality requirements
|
|||
11.2. Quality management - assessment | |||
See next points. |
|||
11.2.1. Compliance monitoring - last report and main results | |||
Eurostat’s compliance and follow-up reports for the Bulgarian HICP can be found in the webpage 'Quality' - Harmonised Indices of Consumer Prices (HICP) - Eurostat (europa.eu). |
|||
11.2.2. Quality assessment - national specifics | |||
The CPI/HICP Quality Reports following the ESS Standard for Quality Reports Structure (ESQRS) are produced and are updated each year. The HICP Quality Reports is available on NSI’s internet site: Harmonised Indices of Consumer Prices (HICP) | National statistical institute (nsi.bg) |
|
|||
12.1. Relevance - User Needs | |||
In addition to being a general measure of inflation, the HICP is also used in the areas of:
The euro area (evolving composition) index is used by the European Central Bank (ECB) as the main indicator for monetary policy management. The ECB and the European Commission's Directorate-General for Economic and Financial Affairs (DG ECFIN) use the HICP for assessing price stability and price convergence required for entry into European Monetary Union. Other users include: National Central Banks, financial institutions, economic analysts, the media and the public at large. |
|||
12.1.1. User Needs - national specifics | |||
The main national users could be classified as follows:
HICP/CPI outcomes are mainly used as input to economic forecasting and analysis, for preparation of the convergence reports, for contract indexation, deflating other series, etc. |
|||
12.2. Relevance - User Satisfaction | |||
NSI conducts an annual online statistical survey "Users' satisfaction" which covers all statistical domains. It aims to assess user satisfaction in NSI data provision and to outline the recommendations for future development of statistical system according to the needs of the users. Analysis of the last survey conducted in 2023 are available on the following link: User satisfaction
The National Statistical Council (NSC) is established in accordance with Art.14 of Law on Statistics, as a consultative body, attached to the President of the NSI. The main tasks of NSC are: give an opinion and recommendations on the Strategy for Development of the National Statistical System for each 5-year period; discuss the proposals of the Bodies of Statistics and give recommendations for including in the draft version of the National Statistical Programme particular statistical surveys specified in kind, coverage and acting persons; support the National Statistical System activities on implementation of the National Statistical Programme; create, in case of need, constant or temporary working groups to deal with particular statistical issues in compliance with its competencies; cooperate with the European Statistical Advisory Committee (ESAC) (according to the Art. 3, Para 4 from Decision No 234/2008/EC of the European Parliament and of the Council). |
|||
12.3. Completeness | |||
No missing data. Bulgaria produces and delivers the full set of HICP and HICP-CT indices and weights. |
|
|||
13.1. Accuracy - overall | |||
Statistical data are with good accuracy. The accuracy of HICP is assured by strictly following Eurostat's methodological recommendations and regulations. The type of survey and the price collection methods ensure sufficient coverage and timeliness. |
|||
13.2. Sampling error | |||
The use of non-probability sampling (purposive sampling) makes it difficult to assess the sample error. Therefore, and due to the complexity of price index structures NSI does not produce estimates on sampling errors. Nevertheless, the NSI aims to avoid possible bias due to sample misrepresentation by using a sample of consumer prices that is as large as possible by the given resource constraints. The NSI tries to optimise the allocation of resources by indicating the number of prices that should be observed in each geographic area and each item category, in order to minimise the variance of the all-items index. |
|||
13.3. Non-sampling error | |||
For the HICP non-sampling errors are not quantified. The NSI tries to reduce non-sampling errors through continuous methodological improvements and survey process improvements. See the next points. |
|
|||
14.1. Timeliness | |||
The full set of HICPs is published each month according to a pre-announced schedule, usually between 14 and 16 days after the end of the reference month. Each year, the January news release is published at the end of February to allow for the annual update of the weights of individual product groups and the relative country weights of Members States in the country-group aggregates. The euro area flash estimate is published on the last working day of the reference month or shortly after that. |
|||
14.2. Punctuality | |||
Since the March 1997, launch of the HICP release, the HICP for the country groups aggregates has always been published on the pre-announced release dates |
|
|||
15.1. Comparability - geographical | |||
HICPs across Member States aim to be comparable. Any differences at all levels of detail should only reflect differences in price changes or expenditure patterns. To this end, concepts and methods have been harmonised by means of legislation. HICPs that deviate from these concepts and methods are deemed comparable if they result in an index that is estimated to differ systematically by less than or equal to 0.1 percentage points on average over one year against the previous year (Article 4 of Council and Parliament Regulation (EU) 2016/792). |
|||
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 and historical series were revised. The main referencing have been from 1996=100 to 2005=100 (since January 2006) and from 2005=100 to 2015=100 (since January 2016). In January 2005 there is a break in HICP series due to changes in methods. Since January 2005 the domestic concept have been implemented in construction of HICP weights. Until December 2004, domestic concept had not been fully implemented into Bulgarian HICP. |
|||
15.3. Coherence - cross domain | |||
HICP differs from national CPI in terms of population coverage – the consumption of both non-residents and institutional household are covered in HICP, while in the national CPI it is out of the index coverage. There are no differences between HICP and the national CPI in terms of the:
|
|||
15.4. Coherence - internal | |||
The HICPs are internally coherent. Higher level aggregations are derived from detailed indices according to well-defined procedures. |
|
|||
Not available |
|
|||
17.1. Data revision - policy | |||
The HICP series, including back data, is revisable under the terms set in Articles 17-20 of Commission Implementing Regulation (EU) 2020/1148. |
|||
17.1.1. Data revision - policy - national specifics | |||
In general, monthly Bulgarian HICP/CPI indices are not subject to revisions. They are final when first released. The only exception is the HICP/CPI for January that is calculated and is published as preliminary data with flag ‘p’. Each year January index is firstly released as a preliminary index with preliminary weights. The reason is that data from HBS used for construction of the weights at the lower levels of aggregation is not available for the whole previous year. The January index is firstly calculated with HBS data from October of year t-2 to September of year t-1. Index numbers for the rest of the months of the year are final when first released. |
|||
17.2. Data revision - practice | |||
The Bulgarian HICP has not been revised in past 10 years. |
|
||||||||||||||||||||||||||||
18.1. Source data | ||||||||||||||||||||||||||||
See next points. |
||||||||||||||||||||||||||||
18.1.1. Weights | ||||||||||||||||||||||||||||
1. What is the main data source to obtain the HFMCE values? At ECOICOP 5-digit level, weights used in the current year t are based on national accounts data referring to t-2 that are further adjusted using additional sources in order to make them representative for t-1. In particular, quarterly national accounts data, household budget survey data, short-term statistics (turnover index in retail trade and in services), transport statistics and tourism statistics were used to make these adjustments.
The 4thquarter of t-1 is integrated in the calculations as follows: Q4 of t-1 is estimated by applying the change in consumption between Q1-Q3 of t-2 and Q1-Q3 of t-1 to Q4 of t-2, i.e. t-2 values are multiplied by the change in consumption between Q1-Q3 of t-2 and Q1-Q3 of t-1 in order to estimate t-1 values.
Below the ECOICOP 5-digit level, various sources are used for different product groups (household budget survey data, transport, tourism and other statistics data, administrative data, etc.). The information from these additional sources is updated annually.
Price-updating is done in December each for the weights of the following year. |
||||||||||||||||||||||||||||
18.1.1.1. Compilation at elementary aggregate level | ||||||||||||||||||||||||||||
1. What is the lowest level of aggregation (number of digits) where explicit weights are introduced? The lowest level of aggregation where explicit weights are introduced is 6-digit level (EAs). Data from household budget survey (HBS) and from additional sources is used for construction of the weights at 6-digit level of aggregation. Bulgarian HICP uses national stratification and the EAs are defined at national level. No regional / outlet / product weights are used.
Annually updated data sources:
No adjustments are carried out.
The annual frequency of update of weights is applied at the elementary aggregate level. There is not a system of regional weights. There is not a system of weights for outlets. |
||||||||||||||||||||||||||||
18.1.1.2. List of elementary aggregates | ||||||||||||||||||||||||||||
At the lowest level of aggregation 464 elementary aggregates (EAs) are defined in 2024. The number of EAs by ECOICOP divisions is as follows:
A more detailed annex is available for Eurostat. |
||||||||||||||||||||||||||||
18.1.1.3. Compilation of sub-index weights | ||||||||||||||||||||||||||||
Еstimation of HFMCE for t-1 Data sources used for estimation of HFMCE for t-1:
Adjustments done for estimation of HFMCE for t-1: (1) Start from of t-2 data, as available from the national accounts, HFMCE is calculated from the individual consumption expenditure of households minus narcotics, imputed rentals for housing, games of chance, prostitution, life insurance, health insurance, FISIM, net purchases abroad, and pensions. (2) Estimation of t-1 by multiplying the t-2 values by the change in consumption between Q1-Q3 of t-2 and Q1-Q3 of t-1 for all sub-components. (3) The estimates based on NA data for t-1 are adjusted for the differences between HFMCE and the total household consumption at domestic concept in the national accounts (4) Estimate of HFMCE calculated in step (3) is compared to estimate calculated in step (2). In order to eliminate the obtained difference (within the threshold ± 5%), the expenditures of sub-components are scaled to the estimated HFMCE to eliminate any discrepancy between the total and the sub-components. Estimation of sub-index weights for t-1 Data sources used for estimation of sub-index weights for t-1:
The following procedure is used:
2.1 multiplying the value for t-2 by an indicator of the change in expenditure; or 2.2 by combining an indicator of the change in volume with an indicator of the change in price.
|
||||||||||||||||||||||||||||
18.1.1.4. Price updating | ||||||||||||||||||||||||||||
1. Are the expenditure shares price-updated between t-2 and t-1 to make them representative for t-1? The price-updating is applied between year t-2 and year t-1 in order to make the expenditure shares representative for t-1 only in cases when no data for estimation of t-1 at all available for certain segments at the detailed levels of aggregation.
2. Please describe the price-updating procedures to December t-1. The price-updating to December t-1 is applied at 5-digit COICOP level, where the index for price update is available. The estimated expenditure shares for t-1 for each index at 5-digit COICOP level are multiplied by the difference between the corresponding HICP index for the average of t-1 and December t-1. The higher levels are calculated as a sum from price updated lower levels. If price indices are not available, price-updating is carried out based on the rate of change of the index of the closest aggregation level above.
3. At which level is the price-updating applied? The price-updating is applied at 5-digit COICOP level |
||||||||||||||||||||||||||||
18.1.2. Prices | ||||||||||||||||||||||||||||
The Bulgarian HICP price data is based on the following multiple data sources:
|
||||||||||||||||||||||||||||
18.1.2.1. Prices Data Source – detailed information | ||||||||||||||||||||||||||||
Restricted from publication | ||||||||||||||||||||||||||||
18.1.2.2. Price Collection Survey | ||||||||||||||||||||||||||||
The main data source is Price Collection Survey:
Targeted web scraping – general information The main types of retailer for which the prices have been web scraped during 2024 are on-line shops of the respective retailers. The web scraped data is used for the following ECOICOP classes and groups: 07.1.1 Motor cars – the weight covered by web-scraped data is 80% 07.1.1.2 Second-hand motor cars – the weight covered by web-scraped data is 100% 08.2.0 Telephone and telefax equipment – the weight covered by web-scraped data is 82% 08.2.0.2 Mobile telephone equipment – the weight covered by web-scraped data is 82% 09.1.3 Information processing equipment – the weight covered by web-scraped data is 28% 09.1.3.1 Personal computers – the weight covered by web-scraped data is 33% 09.3.1 Games, toys and hobbies – the weight covered by web-scraped data is 4% 09.3.1.1 Games and hobbies – the weight covered by web-scraped data is 21% 09.5.1 Books – the weight covered by web-scraped data is 88% 09.5.1.1 Fiction books – the weight covered by web-scraped data is 94% The foreign websites are not web scraped. The prices of the following products collected using the web scraping fully coincide to actual purchaser prices, i.e. are equal to the prices paid in physical outlets:
The prices of the following products collected using the web scraping are used as a proxy for physical shop price collection (i.e. as a price estimate for prices paid in physical outlets):
Web scrapped data is resampled annually according to research of new available data sources.
Targeted web scraping – detailed information Main processing steps The main processing steps are: 1. Downloading of the web scraping data from the selected web sites in .csv/.xls format 2. Validation of the accuracy of the data and preparation the data in appropriate format for calculation 3. Registering the prices of the products included in the sample 4. Treatment of the missing observation, replacements and quality adjustment 5. Index calculation Verification of the availability of the products for the consumer to actually purchase The availability of the products is verified as follows:
Period of month from which web scraped data is included The period of the month from which web scraped data is included is as follows:
Classification the obtained data to ECOICOP We implement web scraped techniques for some chosen products and the ECOICOP classification is pre-determined. GTINs are not used as they are not relevant. Web scraping is used only as a new source for price collection but no new methodology for index calculation had been implemented so far. The whole web scraped database is used for analysis and experiments with the so called 'big data approach'. Selection of the products to be included in the calculation The samples for web-scraped products are defined during the annual update. The missing items are treated as follows: Electronic games (for PC), bestseller books – tops are used; no missing prices. In case of missing tops during the year the replacements are done. Children classical books, schoolbooks - direct replacement of the missing items in the first month. Tablets, desktop computers, mobile phones: prices are imputed for up to 2 months by the short term price change, in third month replacements are done. Used cars - prices are imputed for up to 1 month by the short term price change, in second month replacements are done. Replacements and quality adjustments If a product disappears for two consecutive months (for one month in case of used cars), it’s replaced in the observed sample with a new one. In case of no change of quality between replaced product and replacement direct comparison is applied, in case of quality change – appropriate QA methods are applied. Relaunches are not relevant for the all web scraped products. Calculations up to and including the elementary aggregate level, calculation of the average monthly price Desktop computers, tablets, other non-fiction books, еlectronic games (for PC), fiction books, non-fiction and children bestseller books: The average prices are calculated as geometric mean of all the chosen web sites; then the index is calculated using geometric mean formula. Children classical books - The strata are divided according to the Children Encyclopedias and Children classical tales; index is calculated using geometric mean for each product of the corresponding stratum; finally, the indices of each stratum is weighted by its corresponding weight. Educational text books - The strata are divided according to the textbooks, manuals and university textbooks; index is calculated using geometric mean for each product of the corresponding stratum; finally, the indices of each stratum is weighted by its corresponding weight. Mobile phones: The strata are divided according to the best-selling brands; Index is calculated using geometric mean for each product of the corresponding stratum; finally, the indices of each brand (stratum) is weighted by its corresponding weight; Used cars: The used cars are classified into 3 main strata: small, medium and large. Each stratum is divided into two sub-strata: petrol and diesel. Each of the sub-stratum is divided into 2 strata according to the cars’ age: up to 5 years old and from 6-10 years old. The process is as follows: each stratum by age is aggregated by geometric mean formula; then weighting of the indices for each age group to each stratum – petrol and diesel; finally, weighting the resulting indices for petrol and diesel and receiving the index for the respective main stratum (small, medium, large). Integration of the EAs into the HICP The EA’s and or weighted indices calculated in Excel files (specially designed for the purpose) are entered into main software for CPI/HICP calculation. |
||||||||||||||||||||||||||||
18.1.2.3. Administrative data sources | ||||||||||||||||||||||||||||
Not relevant. |
||||||||||||||||||||||||||||
18.1.2.4. Transaction data – general information | ||||||||||||||||||||||||||||
Not relevant. |
||||||||||||||||||||||||||||
18.1.2.5. Transaction data - detailed information | ||||||||||||||||||||||||||||
Not relevant. |
||||||||||||||||||||||||||||
18.1.2.6. Web scraping - general information | ||||||||||||||||||||||||||||
Not relevant. |
||||||||||||||||||||||||||||
18.1.3. Sampling | ||||||||||||||||||||||||||||
Geographical 1. Please describe how the sample is stratified geographically. The HICP covers the entire area of the country. All regions of Bulgaria are covered in the sample of localities where the prices for HICP are collected. The sample of localities is representative for the entire territory, the stratification of the index being national. Within the regions, the district centre (largest city) is chosen for price collection i.e. the HICP includes 27 district centres in its sampling framework. At this stage, non-probability sampling techniques (cut-off) are applied. The localities are sampled according to the number of population and according to the volume of retail sales. 2. Are regional indices published? No. Outlet 1. Please describe how the outlet sample is drawn for surveys. The sample of outlets is drawn using non-probability sampling technics (‘purposive’/‘judgmental’ sampling). The number and the structure of the observation points are done in a way that can assure the optimum number of prices collected, which are sufficient to represent national price change for any of observed groups. The number of observation points is determined proportionally to the population in the selected district centres and to the volume of retail sales. The main principle is to have different number of price observations/outlets in each district centre according to the population and to the volume of retail sales. The district centres are stratified in three groups: (1) capital, (2) ‘big’ and (3) ‘small’ centres. 2. How often is the outlet sample updated? The sample of retail outlets is deeply checked every year. In addition, when in a certain month an outlet closes or is no longer representative, it is replaced in that same month. 3. What categories of outlets are distinguished? The following main categories of outlets are covered, including supermarkets, hypermarkets, general and specialized stores and market stalls (open-air markets): hypermarket / large supermarket; small supermarket; outdoor (open-air) market (stall, stand); indoor market, bazaar, mall (stall, stand); services’ outlet; catering services’ outlet; specialised chain of stores; specialised small shop; small retail store; other. The market stalls are included in the index, while the mail order, internet shopping and petrol stations for other products than petrol are not included in the index (till now they are not relevant). Sample 1. Please describe how the sample of products is drawn. The sample of products is drawn based on the information of the HBS, which identifies the products most frequently bought by households. Procedures for specifying the representative products can be described as follows:
The definitions usually include the type of product, its major features, and relevant additional information to be recorded by the price collectors. 2. How frequently is the sample of products updated? Annually and kept updated during the year by replacements. |
||||||||||||||||||||||||||||
18.1.3.1. Sampling design: locations for survey | ||||||||||||||||||||||||||||
1. What is the methodology used for selecting locations where you carry out surveys? Within the regions, the district centre (largest city) is chosen for price collection i.e. the HICP includes 27 district centres in its sampling framework. At this stage, non-probability sampling techniques (cut-off) are applied. The localities are sampled according to the number of population and according to the volume of retail sales.
The sample is stratified between the district centres. The main principle is to have different number of price observations in each district centre according to the population in it. The district centres are stratified in three groups:
Annually. |
||||||||||||||||||||||||||||
18.1.3.2. Sampling design: outlets | ||||||||||||||||||||||||||||
1. Please describe the methodology and data sources used to draw the outlet sample for surveys. The sample of outlets is drawn using non-probability sampling technics (‘purposive’/‘judgmental’ sampling). The number and the structure of the observation points are done in a way that can assure the optimum number of prices collected, which are sufficient to represent national price change for any of observed groups. The number of observation points is determined proportionally to the population in the selected district centres and to the volume of retail sales. The main principle is to have different number of price observations/outlets in each district centre according to the population and to the volume of retail sales. The district centres are stratified in three groups: (1) capital, (2) ‘big’ and (3) ‘small’ centres. The identification where consumers do their shopping is done based on information from retail statistics and from marker researches (published on internet or in specialized magazines, newspapers, etc.). The identification and inclusion of the new outlet categories is done in central office of NSI and is defined jointly by central office and by Regional Statistical Offices (RSOs). The information from trade register and information from internet sites about tendencies of retail real estate market (form and location) is analysed and the results are shared with the price collectors in RSOs. When the criteria for inclusion of particular type of outlet are covered in separate region, the price collectors select it as point of observation. The following main categories of outlets are covered, including supermarkets, hypermarkets, general and specialized stores and market stalls (open-air markets):
The market stalls are included in the index, while the mail order, internet shopping and petrol stations for other products than petrol are not included in the index (till now they are not relevant). The outlet sample is updated annually. 2. Who selects the outlets for surveys (central office/regional offices/price collectors)? As there is no information on percentage sales at regional level, price collectors are responsible for the selection of commercial areas and concrete retail outlets, which must be representative of local consumer habits. Particular outlets’ selection of is made at regional level by price collectors in RSOs based on their knowledge and experience. They are instructed to select the outlets, which: • have a large volume of retail sales; • supply a variety of products, representative of the relevant EAs groups. 3. Please describe how the outlet sample is drawn for web scraping. Only targeted web scraping is used. 4. Have there been any changes in the past year to the outlet categories included? There have been no changes in the past year to the outlet categories included. |
||||||||||||||||||||||||||||
18.1.3.3. Sampling design: products | ||||||||||||||||||||||||||||
1. Please describe the methodology and data sources used to draw the individual product (e.g. white rice brand A) sample. The first stage is the selection of products that enter the sample, and the second stage is the selection of the individual products for which the prices will be observed. The sample of products is drawn based on information of the HBS which identifies the most bought by households. A product is selected for the price survey when its share accounts for at least 0.01 per cent in the total HFMCE. Within each product and according to the weight of expenditure several specific individual products are selected. The main criteria to determine the set of individual products for the price survey are: comparative weight of a product in the total consumption expenditure and continued availability on the market (except for seasonal products). The EAs are defined at national product level. Below the EA level (6-digit level of ECOICOP) the sample is stratified by representative products. No regional, outlet or product weights are used. Selection and specification of the products is done jointly by staff in central office and by price collectors in RSOs. Procedures for specifying the representative products can be described as follows:
The first stage is carried out in the central office to define the sample in general terms, at national level. The individual products in each outlet are selected according to their popularity and representativeness across different brands. They are chosen by local price collectors, who consult outlet managers, while always following the general instructions that have been developed by the central office. The specific individual products, whose price will be collected in the sampled outlet, is selected by price collectors. They are instructed to pick the ‘typical’ product variety:
At the end of each year during the annual CPI/HICP revision several letters with instructions for the price collectors are sent to RSOs. The procedures for selecting the particular product in outlets are covered in them. The issue is also discussed on the seminars/workshops with price collectors, which take place regularly.
Only targeted web scraping is used.
Not relevant.
Not relevant. |
||||||||||||||||||||||||||||
18.1.3.4. Sampling design: newly significant goods and services | ||||||||||||||||||||||||||||
1. Please describe how new goods and services are identified. NSI systematically seeks to identify newly significant goods and services. Both completely new products and products that have been available for some time on the market but consumed in relatively small amounts are covered in this exercise. Newly significant good and services are introduced at the end of each year (in December) during the annual revisions of consumer basket. The newly significant goods and services have been introduced into CPI/HICP by adjusting category weight or by re-assigning weight to the new product. The procedures for identification of newly significant goods and services are based on:
The significance level for new products and services are measured based on information from HBS data and on market research’ information, if it is available.
They are introduced in the index in December.
In 2023: - 12.4.0.3 ‘Services to maintain people in their private homes’ |
||||||||||||||||||||||||||||
18.2. Frequency of data collection | ||||||||||||||||||||||||||||
Price data are collected every month. |
||||||||||||||||||||||||||||
18.3. Data collection | ||||||||||||||||||||||||||||
Each month, prices are collected by price collectors in outlets throughout the country. Combined price collection is done: prices are collected using electronic devices (EDs) or paper collection forms. Approximately 40,000 individual prices are collected by price collectors in more than 6,400 outlets each month. Prices are also collected centrally for the following products:
|
||||||||||||||||||||||||||||
18.3.1. Timing of price collection | ||||||||||||||||||||||||||||
1. What is the price collection period for survey and administrative sources? Prices of the most of goods and services are collected each month and the price collection period is between 1st and 30th calendar day of the month (prices are not collected during the weekends and public holidays) according to predefined schedule and are even distributed through the month. 2. What is the period covered by transaction data? Not relevant. 3. What is the period covered by large administrative data? Not relevant. |
||||||||||||||||||||||||||||
18.3.2. Devices for price collection | ||||||||||||||||||||||||||||
Combined price collection is done: prices are collected using electronic devices (EDs) or paper collection forms. EDs are mainly used in big outlets (supermarkets, hypermarkets, etc.). Paper forms are mainly used in smaller outlets (for example, pharmacies, these that supply services, etc.). |
||||||||||||||||||||||||||||
18.4. Data validation | ||||||||||||||||||||||||||||
Process for validating the basic data The monthly checks against errors and mistakes in price information are done during the validation stage of CPI/HICP production. Data quality checks and validation work is distributed between central office and regional statistical offices, but most of work is carried out at the 'Consumer prices, Housing prices and PPP Department' in the central office of NSI. The data validation process at regional offices can be divided into two stages:
The validation of the data in the central office is done after the first index calculation. Data quality checks fall into the following types of validation: 'relevant' index change validation (extreme and unusual price levels/changes); missing prices validation; outlets/products replacement validation; product specification change validation; etc.
Procedures for testing the correctness and plausibility of outcomes The monthly checks against errors and mistakes in preliminary index results are done during the validation stage of CPI/HICP production. Data quality checks and validation is carried out at the Consumer prices, Housing prices and PPP Department in the central office of NSI. The validation of the data is done after the first index calculation. Data quality checks fall into the following types of validation: 'relevant' index change validation (extreme and unusual price levels/changes); missing prices validation; outlets/products replacement validation; product specification change validation; etc. Finally, the indices are reviewed before dissemination. The senior members of staff of the Consumer prices, Housing prices and PPP Department reviews the indices before publication. The validation of the indices goes down to quite detailed item groups. Usually the meeting with experts responsible for validation takes place and the various topics concerning the monthly production round are discussed (reported price changes, imputation rates, cases of quality adjustment, treatment of missing prices, etc.). |
||||||||||||||||||||||||||||
18.4.1. Data validation - Survey data | ||||||||||||||||||||||||||||
1. Please describe the procedure for detecting survey data entry errors. The detection of the data entry errors (including the missing price observations) are done during the validation stage of CPI/HICP production. Data quality checks and validation work is distributed between central office and regional statistical offices, but most of work is carried out at the central office of NSI. The data validation process at regional offices can be divided into two stages:
The validation of the data in the central office is done after the first index calculation using various reports/lists generated by the software. Data quality checks fall into the following types of validation: 'relevant' index change validation (extreme and unusual price levels/changes); missing prices validation; outlets/products replacement validation; product specification change validation; etc. 2. How is detection of outliers done? The first outlier detection is done during the data entry into the software/EDs. Prices are recalculated automatically to the target quantity if the observed quantity differs from the target quantity. The price change is calculated immediately after entering of the price for the current month. All extreme price changes (+/-50%) are coloured in red to alarm the price collectors. In such circumstances, the price collector is immediately forced either to correct the data or to accept it providing some explanation. 3. How are errors detected and outliers treated? The detected errors and outliers are treated as follows: each case (problematic price) is considered individually, trying to obtain additional information for removal of the error and all necessary modifications are done only on the basis of relevant information. When it is considered that the individual price observation have to be rejected and new observation cannot be established, the rejected prices are treated as missing observations following the minimum standards regarding the treatment of missing observations, imputations and replacement procedures in the HICP. The rejections or adjustments of the reported prices are done centrally during the validation process in NSI. The rejection/adjustment of one price observation is done on account of information related to the individual observation concerned. During the validation process in central office, the responsible experts contact with price collectors in order to derive additional information for the individual observation concerned. In addition, if it is considered, the prices are cross cheeked in outlets or in Internet. 4. How is the monitoring the consistency of the price information over time done (comparing like with like)? The monitoring of the consistency of the price information over time is done during data validation using the various reports/lists generated by the software. Data quality checks fall into the following types of validation: 'relevant' index change validation (extreme and unusual changes, comparison is done with previous month and monitoring of the number of the consecutive months with no price change); missing prices validation (number of the consecutive months with missing prices); outlets/products replacement over time validation. 5. How is the monitoring the consistency of the price information across similar products in the same period done? The monitoring of the consistency of the price information over time is done during data validation using the various reports/lists generated by the software. Data quality checks fall into the following types of validation: extreme and unusual price levels, comparison is done between prices of the one and same product in the same period. |
||||||||||||||||||||||||||||
18.4.2. Data validation – Transaction data, web scraping and large administrative data | ||||||||||||||||||||||||||||
1. Please describe the validation procedures for transaction data. Not relevant. 2. Please describe the validation procedures for web scraped data. Only targeted web scraping is used. Standard data validation procedures (e.g. extreme outliers, number of records and items). 3. Please describe the validation procedures for large administrative data. Not relevant. |
||||||||||||||||||||||||||||
18.4.3. Data validation - Weights | ||||||||||||||||||||||||||||
The review and update of weights at lower levels is done during the annual updating of the HICP weights. The constructed weights are analysed and validated at all hierarchical levels of aggregation (from lowest EA level to general index). Plausibility checking activities include:
|
||||||||||||||||||||||||||||
18.4.4. Indices | ||||||||||||||||||||||||||||
The senior members of staff of the Consumer prices, Housing prices and PPP Department reviews the indices before publication. The validation of the indices goes down to quite detailed item groups. Usually the meeting with experts responsible for validation takes place and the various topics concerning the monthly production round are discussed (reported price changes, imputation rates, cases of quality adjustment, treatment of missing prices, etc.). Before publication, the calculated indices are analysed and validated at all hierarchical levels of aggregation (from product level to general index). Validation activities include:
|
||||||||||||||||||||||||||||
18.5. Data compilation | ||||||||||||||||||||||||||||
1. Please confirm that the HICP is a Laspeyres-type index. The HICP is a Laspeyres-type index. 2. What elementary price index formulae are used? For elementary aggregation, the Jevons price index (ratio of geometric means) is used. 3. Please specify the number of decimals that are applied for: The following rules are used for the number of decimals:
4. Please specify the cases for which rounding or truncation of the number of decimals are used. In all instances ‘round half away from zero’ is used for rounding. |
||||||||||||||||||||||||||||
18.5.1. Elementary price index formulae | ||||||||||||||||||||||||||||
For compilation of price indices for elementary aggregates, the ratio of geometric mean prices is used. |
||||||||||||||||||||||||||||
18.5.2. Aggregation of different data sources | ||||||||||||||||||||||||||||
Bulgarian HICP is a Laspeyres-type index. Aggregation steps from bottom up:
For web scraped data, only targeted web scraping is used. See 18.1.2.2. |
||||||||||||||||||||||||||||
18.5.3. Chaining, linking and splicing methods | ||||||||||||||||||||||||||||
1. Please describe your chaining and linking methods. Вulgarian HICP is chained Laspeyres-type index. The indices are first calculated with year t-1 as reference period for indices, weights and prices. Each year, the link is done in December, using the index for December of year t-1 calculated with year t-1 as reference period for indices, weights and prices and the index for December of year t-1 rebased to 2015=100. 2. Do you use splicing in your time series? If yes, please explain the method applied. Splicing is not used for the time series of the Bulgarian HICP. 3. When was the last time you ‘restarted’ your multilateral indices? Not relevant. |
||||||||||||||||||||||||||||
18.5.4. Quality Adjustments and replacements | ||||||||||||||||||||||||||||
1. Please list the main quality adjustment methods used by product. The quality adjustment methods that are usually applied by groups of products area:
2. Please describe the rules for product replacements. When replacing an item by a new one, price collectors are instructed to:
When replacing an outlet, price collectors are told to choose a new one, which has to be:
3. Under which conditions are replacements made (e.g., after certain number of months without a price observation)? When an item (variety) is not available in the market for two months or it is no longer important in terms of consumption because of a new variety, it is replaced by the item that has taken its place in the market. |
||||||||||||||||||||||||||||
18.5.5. Seasonal items | ||||||||||||||||||||||||||||
1. What product groups are treated as seasonal? Seasonal products are treated according to the requirements of the Implementing Regulation (EU) 2020/1148. Minimum standards are applied to seasonal products within the following ECOICOP classes and groups:
2. What are the methods used in the terms of Implementing Regulation (EU) 1148/2020? Strict annual weights are used or determining the weights for seasonal items, i.e., the indices of seasonal items are calculated with fixed weights during the whole year. Therefore, estimated prices are applied for seasonal items that are out-of-season. Estimated prices for seasonal products that is out-of-season are calculated by ASE (all-seasonal estimation) or by CSE (counter-seasonal estimation):
|
||||||||||||||||||||||||||||
18.6. Adjustment | ||||||||||||||||||||||||||||
See next point. |
||||||||||||||||||||||||||||
18.6.1. Seasonal adjustment | ||||||||||||||||||||||||||||
No seasonal adjustment is made. |
|
|||
|
|||
|
|||