National Institute of Statistics, Romania

In Romanian: Institutul Național de Statistică, România (INS)

Directorate of Prices Statistics (R.2.1.2)

B-dul Libertății 16, Sector 5, Cod Poștal 050706, România

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.

European classification of individual consumption according to purpose (ECOICOP)

The HICP covers the final monetary consumption expenditure of the household sector.

The main statistical variables are price indices.

The basic unit of statistical observation are prices for consumer products.

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

Not the case.

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

All 42 counties (NUTS 3) are covered in the Romanian HICP. The 68 survey centers are  set up by the territorial offices in 42 urban localities which have been chosen in accordance with the number of inhabitants.

The domestic concept is implemented. The compliance with the domestic concept is assured by using the national accounts data, which are compiled based on the supply use table concepts and standards.

3.8.1. Start of time series

The HICP series started in January 1997.

3.8.2. Start of time series - national specifics

HICPs with harmonised coverage and methodology have been published since January 2001. Interim indices based largely on existing national Consumer Price Indices (CPIs) are available back to January 1996; these are adjusted to reduce differences in coverage of goods and services observed between national CPIs.

See the HICP database

2015=100

The following units are used:

• Index point
• Percentage change on the same period of the previous year (rates);
• Percentage change on the previous period (rates);
• Percentage share of the total (weights).

HICP is a monthly statistics.

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 documentation, can be found in Eurostat’s website - HICP dedicated section, namely recommendations on specific topics, under the methodology page, and guidelines, under the quality page.

None.

The standards defining the confidentiality of statistical data are compliant with the Regulation (EC) No 223/2009 of the European Parliament and of the Council (11 March 2009), on the transmission of data subject to statistical confidentiality to the Statistical Office of the European Communities, also with Article 36 of the Law no. 226/2009 on the organisation and functioning of Official Statistics in Romania.

The article 36 in the Romanian Law on Statistics states that:

• the statistical data are deemed confidential if they relate to a single person or legal entity or allow the identification, directly or indirectly, of the person or legal entity concerned;
• the statistical data obtained from processing individual data should only be disseminated if after aggregation the results refer to at least 3 sources and if none of them has a weight bigger than 80%;
• confidentiality does not extend to individual data on institutions and organisations financed from the state budget, unless such data are protected by laws and other special acts;
• confidential statistical data collected by the producers of official statistics cannot be used as evidence in court or to establish rights and obligations for data providers to which it relates.

Almost all INS statistical programs rely on voluntary respondent cooperation. Consequently, it is important to ensure that respondents are comfortable that sensitive information they give to a statistical program will not be revealed in a way that jeopardises their interests. If not, respondents are less likely to cooperate with that program and perhaps other statistical programs.

In the case of CPI/HICP, the price collectors request permission from the managers of the outlets to price a set of unique consumer and services surveyed items, which are specific goods and services that can be purchased by a general consumer.

Official HICP products released include:

• HICP by 4 digits of ECOICOP (class) at national level
• HICP by 5 digits of ECOICOP (subclass) at European level

Any decision to publish additional data below 5 digits level of COICOP is conditional on having assurance that the additional publication will not compromise INS confidentiality pledges. When a customer requests non-published information the INS evaluates the feasibility of producing a special tabulation or the feasibility of the researcher accessing micro data.

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 Protocol on impartial access to Eurostat data for users.

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.

The publication dates can be found by following the links below:

Press releases calendar - INS Romania

Statistical publications calendar - INS Romania

Eurostat

In line with the Community legal framework and the European Statistics Code of Practice Eurostat disseminates European statistics on Eurostat's website (see item 10 - 'Dissemination format') 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.

Monthly

The HICP is published monthly or annual in hard or electronic copy, in both Romanian and English languages.

The press release is referring to the monthly, annual and the 12 month average rate of HICP and is available simultaneous to all users when the CPI press release is published. The CPI press release is available on the INS website at 9:00 a.m. on the day of release.

The monthly HICP sub-indices are published in the Monthly Price Statistical Bulletin and the annual HICP sub-indices are published in the Statistical Yearbook.

The HICP index levels are disseminated with 2 decimals and the rate of change with one decimal.  

See above (accessibility and clarity)

See above (accessibility and clarity)

Detailed HICP time series for Romania are available only on the Eurostat HICP database.                                                                                                                                

Access to confidential data (microdata) for scientific purposes is the only exception to the rule that confidential data can only be used to produce official statistics.

More about the microdata access in case of Romanian’s INS can be found at the following link: INS-microdata. In the framework of the PRISMA project set up in 2018 by the European System of Central Banks (ESCB), INS Romania provided to the National Bank of Romania CPI/HICP anonymized microdata for the period 2015-2020.

None.

The HICP Methodological Manual provides the reference methodology for the production of HICP. (https://ec.europa.eu/eurostat/web/products-manuals-and-guidelines/-/KS-GQ-17-015)

10.6.1. Documentation on methodology - national specifics

There is no specific methodology for the HICP at the national level. A short description regarding the HICP is published together with the national CPI methodology. 

Methodological explanations attached to the monthly press release on the official site of INS Romania.

INS did not compile yet any dedicated HICP quality report so far.

The first quality assessment report was done by Eurostat in 2007, at the moment of Eurostat’s compliance monitoring visit. A second visit was done in 2018 and a third in 2023.

All reports are accessible on Eurostat's website, page Quality - Harmonised Indices of Consumer Prices (HICP), under 'Compliance Monitoring'.

In the context of compliance monitoring and quality assurance, Eurostat reviewed the Romanian HICP system in spring 2007 and in winter 2018. The statistical practices used to compile the HICP for Romania have been reviewed against HICP methodology and other guidelines and good practices in the field of consumer price indices.

Besides of compliance monitoring visits, the article 9 of the Council Regulation (EC) No 2016/792 provides other forms of quality assurance documentations: quality reports and inventories containing details of data sources, definitions and methods used.

11.1.1. Quality management - Compliance Monitoring

Compliance Monitoring

11.1.2. Quality assurance - national specifics

INS Romania has been developing its quality policy and the methods and tools of quality assessment in accordance with the standard documents of the ESS quality system. More about the quality statistical system in Romania can be found by following this link:

Quality of the Romanian Statistical System

11.2.1. Compliance monitoring - last report and main results

The last available compliance and follow-up reports can be found in the dedicated HICP, webpage Quality - Harmonised Indices of Consumer Prices (HICP) - Eurostat (europa.eu).

A follow-up compliance monitoring report was agreed and published on Eurostat’s website in February 2023.

11.2.2. Quality assessment - national specifics

There isn`t any quality assessment document for HICP/CPI prepared at national level in present. However the assessment of the HICP/CPI data in terms of accuracy is occasionally made by the National Statistical Council (NSC) and the National Statistical System Committee (COMSTAT).

In addition to being a general measure of inflation, the HICP is also used in the areas of:

• wages, social benefit and contract indexation;
• economic forecasting and analysis;
• measuring specific price trends;
• accounting purposes and deflating other series;
• inflation targeting by central banks;
• cross-country economic comparisons.

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

Internal beneficiaries for the statistical data from INS Romania are the following institutions: the National Bank of Romania, the Government of Romania, the Ministry of Economy, the Ministry of Finance, the Ministry of Labour and Social Solidarity, the Parliament of Romania and the Presidential Administration.

External beneficiaries: World Bank, the European Union Statistical Office and the International Monetary Fund.

INS Romania conducts a web opinion survey which covers all statistical domains. The  purpose of this web survey is to gather statistical information in order to help INS improve the national statistics system - so it would better fulfil the user needs. All feedback is anonymous and confidential.

The contacts between INS Romania and the main users of official statistics are established via two advisory boards. National Statistical Council (NSC) and National Statistical System Committee (COMSTAT)

INS Romania produces and delivers the full set of data for indices and weights in accordance with the existing European standards and regulations for the consumer price statistics.

CPI/HICP price data are routinely assessed using clear rules. First, when interviewers enter price data into their computers, the figures are checked for validity of the results. If there is a large divergence from the previous price, the interviewer is asked to confirm the new price. After the prices have been sent to the central office they are automatically checked. The exceptional price changes are verified against price collection sheets or by calling the price collector or the outlet. Centrally collected prices are checked in a similar manner.

National accounts and household budget survey data are investigated and assessed before using them to compile CPI/HICP weights.

No information is available on the sampling errors of component or aggregate CPI/HICP series, and there are no recent INS studies on this issue. Neither are there standard error estimates associated with the HICP expenditure weights, because these are taken from the national accounts.

The CPI/HICP system does not provide a specific report on the non-sampling errors. However, as noted above, the CPI/HICP system includes for each stage of processing validation checks, such as for coding, entry, transfer and editing (control or correction). Annually, a general assessment is made of price data collection in term of non-responses, outlets which cannot be contacted or refuse to participate in the price survey or of temporary missing prices.

The full set of HICPs is published each month according to Eurostat’s Release calendar, usually between 15 and 18 days after the end of the reference month.

Each year, the January release is published at the end of February to allow for the annual update of the weights, both 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.

Since the March 1997, launch of the HICP release, the HICP for the country groups aggregates has always been published on the dates announced in Eurostat’s Release calendar.

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).

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 HICPs. These changes may have introduced breaks in the time series.

The use of different consumption concepts, data sources for the weighting system and item classification in the CPI, made that CPI indices cannot be reconciled at higher levels with corresponding national accounts series as well as with the HICP.

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

Not available

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

HICP data can always be subject to revision, even if they are published as final when first released. Revised data are always identifiable as such and are accompanied by the reasons which led to the respective revision.

As mentioned above, HICP data can be revised but this never happened in the past.

18.1.1. Weights

Weights are derived in accordance with Commission Implementing Regulation (EU) 2020/1148.

As a rule, for year t, the implementation of the Regulation means the use of the data on the household final monetary consumption expenditure from the national accounts relating to year t-2 and the expenditure from the t-2 Family Budget Survey to calculate the weights of the harmonised indices. The weights calculated in this manner are then updated to the prices of December t-1.

For the 2023 weights derivation round, the weights were estimated based on the data on the household final monetary consumption expenditure from the national accounts relating to the year 2022, updated to the prices of December 2022.

18.1.1.1. Compilation at elementary aggregate level

The weights below sub-index level are based mainly on HBS data for the year t-2. These data are supplemented and verified using other statistical and non-statistical sources.

Additional sources are used in case of energy products, pharmaceutical products, telecommunications and postal services, education, new or used cars and transport services. The additional sources are represented by the queries sent each year to the units, like for energy products, postal services and transport services (metro, rail or fluvial transport).

For education and other transport services internal statistical sources developed by the departmental statistical units are used.

For telecommunication and new or used cars sources of information are national regulators, the ministry of internal affairs or studies and reports provided by the automotive manufacturers and importers` association.

For the cases of no reliable information for deriving the weights the judgmental adjustment is applied.

Neither regional nor outlets weights are compiled.

Weights are updated annually and are kept constant throughout the year.

The regular update of the weights reference period will be carried out on the basis of national accounts data. Further to Eurostat guidance for derivation of HICP weights for 2023, the national accounts experts will investigate the available national accounts data sources in order to provide the best estimate for HFMCE.

18.1.1.2. Compilation of sub-index weights

Q1.The expenditure shares at sub-index level should be derived from data sources referring to year t-2 and these shares should be updated to make them representative for year t-1. How are these principles implemented in the most recent weight update?

The expenditure shares are based on national accounts data referring to t-2 that were adjusted using additional sources in order to make them representative for t-1. In particular, short-term statistics (turnover index) and tourism statistics referring to the three first quarters of 2022 were used to make these adjustments.

Q2. What are the main data sources on which the sub-index weights are based on? Specify the reference period of the data sources, explain how they are used and whether any adjustments were made.

Step 1. Data on national accounts for household consumption in the first 3 quarters of 2022 were used

Step 2. We assumed that the 4th quarter is the average of the three quarters of 2022

Step 3. Household final monetary consumption expenditure (HFMCE) was estimated (see point C. Q1)

Step 4. For all sub classes it has multiplied the 2021 value by combining an indicator of the change in volume with an indicator of the change in price.

Step 5. After step 4, the amount of expenditures in 2022 for all subclasses was compared with the sum of expenditures in 2021 for all subclasses.

Step 6. If we obtained class changes or high levels we applied proportionally to the lower levels.

Step 7. Finally, when the difference in step 6 was small, the subclass expenditures was scaled and then we estimated the total HFMCE to eliminate any discrepancy between the total and subcomponents

Step 8. It has calculated the 2022 expenditure shares for each sub-class by dividing the corresponding expenditure by the total HFMCE.

Information from the short-term statistics was used, as follows:

* turnover and volume of sales in wholesale and retail trade (the table below shows the detailed breakdown on NACE, reference period and adjustments)

• Turnover in services - quarterly data
• Detailed breakdown by NACE:

• Tourism statistics, quarterly data, for Q4 were assumed to be the average of the three quarters
• HIPC (2015 = 100) - monthly data (index)

Q3. Provide details for specific product categories with the biggest changes in weights compared to the previous weight derivation exercise. 

Increase in weight compared to previous year

Compared to the previous year, a weight increase can be observed for almost all subclasses.

Decrease in weight compared to the previous year 

Based on the available data, a decrease in weight can be observed for some subclasses, such as:

Q4. Describe how the 4th quarter of t-1 is integrated in the calculations of the sub-index weights. 

The 4th quarter of t-1 was assumed to be the average of the three quarters of year t-1.

Weights are updated annually and are kept constant throughout the year.

18.1.1.3. Compilation of sub-index weights

2022.

18.1.1.4. Weights – plausibility checking

We check the plausibility of the weights by comparing with previous years`s data and where we notice significant variations we look for an additional data source in order to explain better such changes.

18.1.1.5. Price updating

Q1. Describe whether price-updating is applied between year t-2 and year t-1 in order to make the expenditure shares 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.

Q2.Describe how the price-updating to December t-1 is conducted.

All sub-index weights (5-digits ECOICOP) are price updated to the previous year’s December price level.

For the elementary aggregate level no price update of the weights is applied.

Q3. At which level of detail is the price-updating applied?

The price-updating was applied at the 5-digits ECOICOP level.

18.1.1.6. Compilation of total household final monetary consumption expenditure

Q1. Which data sources are used and which adjustments are made to estimate the total Household Final Monetary Consumption Expenditure (HFMCE) needed to compute the country weight?

In order to obtain the HFMCE, the value of 2021 was multiplied by combining a volume change indicator with a price change indicator for:

-          Narcotics

-          Imputed rentals for housing

For this issue, estimates were compared with the data form the NA, respectively the average of the three quarters for the imputed rent

-          Games of chance

-          Prostitution

-          Public insurance connected with health

-          FISIM (Financial Intermediation Services Indirectly Measured)

-          Net purchases abroad (deducted from the total in order to have the data reflecting correctly the domestic principle of the HICP).

For this issue estimates  were compared with the average of the three quarters compile based on Bop data

-          Income in kind, such as free food for employees in agriculture, and other own final consumption that does not involve monetary transactions

For this issue, estimates were compared with the data form the NA, respectively the average of the three quarters for the own final consumption

-          Administrative charges of private pension funds and the like (part of ECOICOP 12.6.2). They should be deducted in case they have been included in 12.6.2

After that, the total HFMCE obtained from estimates was compared with the total on subclasses, and the subclass expenditures was scaled to eliminate any discrepancy between the total and subcomponents.

Q2. Describe how the 4th quarter of t-1 is included in the calculation of the total HFMCE.

Firstly, the total HFMCE was obtained.

Secondly, the elements which were deducted from the HFMCE were estimated. (Please see above how they were estimated).

18.1.2. Prices

Currently there are two basic price collection methods used: local price collection and central price collection.

The prices collected at local level are obtained by visiting the outlets selected in the sample and located across the country.

Central price collection covers mostly the prices that are identical for the whole economic territory.

18.1.2.1. Data Source - overview  

18.1.2.2. Scanner data - general information

Not applicable.

18.1.2.3. Web scraping - general information

Starting with 2020 we have been collaborating with colleagues from another department who are carrying out experimental statistics research regarding the use of webscraping  for consumer price collection, for  a small basket of food and non-food items. In 2023, we continue to cooperate with our colleagues  in testing the webscraping as a data source for specific groups of products.

18.1.3. Sampling

18.1.3.1. Sampling design: locations for survey

The Romanian HICP covers the entire area of the country, without using any regional weights. The sample of localities is representative for the entire territory, the stratification of the index being national. 42 urban localities (NUTS 3) compose the sample of localities. 

18.1.3.2. Sampling design: outlets

The observation and recording of prices and tariffs are carried out in all of the 42-county seats, where 68 survey centers were established based on the number of inhabitants. The units where prices/tariffs are recorded were selected at local level by the survey centers, taking into account the volume of sales of goods and services provided. The outlet sample (nomenclature) contains approximately 7000 units, 84% of which being privately owned. These must be maintained in the sample for as much as possible in order to ensure the continuity of the observation of prices.

Data from the survey on 100 agro-food markets for main agricultural products (vegetables and fruit) are also used.

The main types of outlets included in the sample are: specialised stores, supermarkets, hypermarkets, mini-markets and agro-food markets (farmers` markets). The cash-and-carry type stores are not taken into consideration (they sell goods only to member access card holders, namely legal persons, authorised physical persons and family associations).

18.1.3.3. Sampling design: newly significant goods and services

New products on the market are deemed significant for the consumer basket based on the expenditure levels (from HBS), also on the market share (if available). A certain product offer is chosen by the price collector at the outlet based on information they are able to get regarding both the sales volume and the regularity of supply.

New products are usually brought in at the end of the year (December), but forced replacements may happen when a product disappears from the market. Replacement is done by choosing a well sold similar product in the same price range, from the same outlet. If necessary, quality adjustments are done, by the experts at central level.

Here are some of the new items (goods and services) that were introduced into the item list in 2023: Non-alcoholic flavoured beer, Champagne for children, organic eggs, double bed mattress (springs/memory foam), baby high chair, robot vacuum cleaner, size 5 football, barbecue charcoal, lubricant eye drops, dog shampoo, dog leash, Dacia Spring Expression electric new car, Hyundai Tucson Style+ mild hybrid new car, Papanicolaou cervical test, tooth sealing for 6-12 years old children, football ground rental, parcel collection point delivery fee, self-service car wash.

Price data is collected every month.

18.3.1. Price collection surveys

The observation and recording of prices is carried out in the 42 county seats from which 68 survey centres were selected based on the number of inhabitants. The units where prices/tariffs are recorded were selected at local level, by the survey centres, taking into account the volume of sales of goods and services provided. The nomenclature includes approximately 7000 units, which must be maintained as much as possible in order to ensure the continuity of the observation of prices. The prices collected on a monthly basis are retail prices, including the VAT.

The activity of collecting prices and tariffs is carried out by statistically trained staff (approx. 120 people at national level), doing field work - using printed questionnaires, also tablets – starting being used this year.

They are locally coordinated by survey supervisors, who also collect prices and services` tariffs from administrative sources and from the local distribution companies.

At central level, the CPI staff organise and coordinate the national CPI survey and also do the central collection of prices of certain non-food goods and services` tariffs.

Prices/tariffs are centrally collected for the following non-food goods and services: newspapers and magazines, electric energy, natural gas, rent, postal services, telephone (landline and mobile), TV subscriptions, urban transport (by underground), interurban transport (by train), air transport, river passengers transport, administrative fees (passport), administrative fees (driving license), financial services, desktop computers, Compulsory Auto Insurance (RCA), Compulsory Dwelling Insurance (PAD).

The experience of the price collectors and their knowledge of the local market is used in the outlet selection, but the decision of including an outlet in the sample is taken at central level, by the experts here, who also get information from retail statistics and market researches (via Internet, press etc.).

For most goods, the selection of products and varieties within outlets is purposive. In each outlet, collectors choose one variety ‘representative of what people buy in your area’ from all products matching the specification of each item to be priced in that outlet. To facilitate this, they ask the retailer which are the most popular brands and those stocked regularly. As it is vital that the same product is priced each month, collectors must record enough detail of the product, such as brand and model, to ensure that it is uniquely identifiable.      

18.3.2. Timing of price collection

Frequency of data collection – every ten days for food goods, tobacco, fuels and water supply, sewage collection, refuse collection. The price collectors have to collect prices/tariffs for these goods and services three times a month, 1-7, 10-17 and 20-27 being the periods of collection. For the rest of the non-food goods and tariffs of services, where products are showing no sharp and no irregular price changes within the same month, price are collected at the middle of the calendar month (second decade).

The validation of data including outlier detection, missing prices and data entry errors takes place in a number of stages from the point of price collection onwards.

There is no automatic rejection of observed prices in our validation process. Each case (problematic price) is considered individually and all modifications are done on the basis of relevant information. All collected prices are reviewed by price collectors before being entered into the computer.

The second phase of control is incorporated in the computer program for data entry and in the end all data are checked by a person (supervisor) in the unit. If there are doubts about the reliability of one or several prices, these prices are checked once again by contacting price collectors or, if necessary, checked directly on the field.

The price collector and supervisor have to verify if the price variety is unchanged: description, unit of measure, producer etc. Keeping in touch with the manager of the outlet, they identify the causes of the change: changes in mark-up or exchange rate of Euro, transport costs, wholesale price or other reasons.

The reasons for price variations are filled-in in the ‘observation’ field. Data files are transmitted to the central office after this checking.

At central level the price information collected locally is loaded into the database after integrity control. The specialized program prints out indicators related to prices and indices at the country level as follows: minimum, maximum, geometric mean, standard deviation and variation coefficients for prices and indices.

These indicators are analysed and the outliers and replacements are identified. Questions are raised with the regions many times each month. Preliminary index results are obtained and different procedures for quality adjustment and treatment of missing prices are applied.

18.4.1. Data validation - price data

See 18.4

18.5.1. Elementary price index formulae

The index is calculated using a Laspeyres chain index with weights that are updated on a yearly basis.

The prices indices for the elementary aggregates are computed as an unweighted geometrical mean of the indices for the product offers. This elementary aggregate is calculated for the current month, as against the base year t-2. A single formula is used for the compilation of the elementary aggregates. Since January 2001 we`ve been using a geometric mean formula for all elementary aggregates.

Index figures are published using 2 decimal places, while the rates of change are published using 1 decimal place. 

18.5.2. Aggregation of different data sources

In the national system, the nomenclature of goods and services used in order to build the CPI is divided into 3 aggregation levels: groups, positions and items as follows:

• the group of food goods contains 54 positions with 429 items;
• the group of non-food goods contains 112 positions with 983 items;
• the group of services contains 50 positions with 459 items.

In the European system, in order to build the HICP, a classification of expenditure according to purpose (ECOICOP – Classification of Individual Consumption according to Purpose), which regroups the items of the national system, is used. The ECOICOP ensures the comparability of indices at European level and is structured, in accordance with Regulation (EU) 2016/792, on 12 detailed divisions, 47 groups, classes, sub-classes.

Indices for higher levels of our HICP are weighted averages of the elementary aggregate indices. A statistical program performs the aggregation of elementary indices to the upper level indices (item, sub-index and total).

18.5.3. Chaining, linking and splicing methods

The Romanian HICP is a chained Laspeyres-type one, the weights being updated annually.

The index is calculated and published against the average of the year 2015 (2015=100). This reference period of the index is used for the complete time series of all HICP indices and sub-indices, according to Commission Implementing Regulation (EU) 2020/1148. All EU Member States comply with this rule for comparability reasons, regardless of the reference base of national indices and the weighting system used. This means that complementary calculations are performed on the same data in order to obtain an index with the 2015 average as the reference base; also, for comparability reasons, the weights used by each country to calculate the HICP are expressed in the prices of the month of December of the previous year.

Each year, the link is done in December, when indices are computed by using the updated basket and the new weights are linked to the previous series.

18.5.4. Quality adjustment – Detailed information

If a non-comparable replacement is made, then all products could be subject to quality adjustment.

The following quality adjustment methods dealing with quality change of products are applied:

• annual overlap: For many of the products new samples are drawn each year during the annual revision of consumer basket. December is used as a linking month and then the dual price collection is done - the prices are collected both for the old and for the new sample. Quality differences between these two samples are then eliminated by the overlap method called 'annual overlap'.
• direct comparison. Price collectors are instructed to measure the price for the same variety throughout the year and if the variety disappears permanently from the market, they should choose another one with the most similar quality. In these cases, direct comparison method is applied, because of the minor difference in quality between the old and the new variety.
• implicit quality adjustment methods. In some particular cases, the second approach is not applicable, due to the fact that quality difference between old and new product is 'significant', and implicit quality adjustment methods are applied. Overlap is used when the prices of both products are available in the same time period; bridged overlap (class-mean imputation) - when prices are not available; option cost.

Quality adjustment procedures are done centrally by the staff in central office. At local level, price collectors do not make any quality adjustments; they are only instructed to report to central office for the all cases of considerable quality changes of the replacement products.

18.5.5. Seasonal items

The standards for the treatment of seasonal items in the Romanian HICP were implemented starting with the index for January 2011 and follow the rules and definitions of Commission Implementing Regulation (EU) 2020/1148.

The classes which we treat now as seasonal are 01.1.6 Fruit and 01.1.7. Vegetables.

Not applicable.