Croatian Bureau of Statistics (CBS)

Macroeconomic Statistics Directorate

Croatian Bureau of Statistics - Internal organisation (gov.hr)

Ilica 3, 10000 Zagreb, Croatia

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 available.

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

The economic territory of Croatia is the same as the geographic territory. The HICP refers to the whole economic territory of Croatia consistent with NA (ESA 2010). No parts of the economic territory of Croatia are excluded from the index.

3.8.1. Start of time series

The HICP series started in January 1997.

3.8.2. Start of time series - national specifics

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.

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.  

In accordance with the Official Statistics Act statistical data on natural or legal persons, if these data can directly or indirectly be related to a natural or legal person, shall be deemed statistically confidential and shall represent an official secret.
Confidential statistical data collected for the purpose of official statistics, may be used only for statistical purposes and are presented in an aggregated form.


Confidential statistical data may not become the basis for determining any kind of rights and obligations for the reporting units, such as administrative, legal or tax purposes, nor for verification of the reporting units.


Access to confidential statistical data that enable only indirect identification of a statistical unit may be granted exceptionally, based on a written request, for conducting statistical analyses solely for scientific purposes. The purpose of using statistical data is stated in the request. For the use of statistical data for scientific purposes, a special contract is concluded, according to which the user is materially and criminally liable, whereby the statistical data are used only for the purpose stated in the request, only authorised persons have access to the data, and data must be destroyed after use.


The level of data dissemination is regulated by the Annual Implementing Plan. Statistical data may be disseminated at lower levels of aggregation than those specified in the Annual Implementing Plan, provided that direct or indirect identification of the statistical unit is not possible. Each organisational unit of the CBS must, within its scope of work, determine the rules and methods for the protection of confidential statistical data in line with provisions laid out in the Instruction on the protection rules and methods for dissemination of official statistical data of the CBS.

According to policy rules (see point 7.1).

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.

Calendar of Statistical Data Issues

The data are released simultaneously to all users by the issuance of the press release: First Release: Consumer Price Indices, available at the CBS website.

The CPI/HICP data are available in an equal manner and at the same time to all users. No special users are granted special or pre-access to data.

Monthly

The main channel for dissemination is the CBS website (new website was launched in April 2022).

The Croatian HICP is disseminated monthly together with national CPI news release (CPI/HICP First release) available in electronic and/or printed format.

Apart from the website, CBS uses other communication channels for dissemination: printed publications, electronic media, social networks, library and phone contact being among them.

Index levels are disseminated with two decimal places and rates of change with one decimal place.

All regular issues of publications are released on the CBS website, and are available both in Croatian and English language. 

The HICP is published together with the CPI news release.

Except from the CPI news release, HICP is included in Statistics in line (on the CBS website).

HICP database.

Detailed HICP data is available on users’ request through User Communication Department. The CBS, upon a written request, allow scientists and scientific organisations that conduct statistical analyses for scientific purposes access to confidential statistical data that enable only indirect identification of a statistical unit may be granted exceptionally, based on a written request, for conducting statistical analyses solely for scientific purposes. The purpose of using statistical data is stated in the request. For the use of statistical data for scientific purposes, a special contract is concluded, according to which the user is materially and criminally liable, whereby the statistical data are used only for the purpose stated in the request, only authorized persons have access to the data, and data must be destroyed after use.

Public microdata

See also Eurostat's HICP website.

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

Short description of methodology is published in every issue of the 'First release: Consumer Price Indices'. Written instructions like manuals and process documentation are available in Croatian.

The HICP Quality Reports are available on the CBS website: Quality reporting

The policy of the CBS is to continuously monitor and improve all statistical processes and products. CBS takes care not only about providers of statistical data but of users also. The European Statistics Code of Practice, together with other documentation, made available on CBS website, are used for quality developments and monitoring. Beside that CBS has developed POMI – Database of quality information which contains both quality concepts prescribed by Eurostat i.e. ESMS, ESQRS and SIMS (standard ESS metadata structures for quality reporting). The POMI is a central place for storing direct information on quality assessment and reference metadata. From this central place can be generated following information:

Quality reports for Internet purposes - bilingual

• Quality reports for Eurostat – ESMS, ESQRS and SIMS structure for different statistical domains in xml formats which enable direct insertion of metadata reports in ESS Metadata structures
• Quality reports using several surveys of the same domain
• Analysis within the same statistical survey through different period of time
• Analysis between different statistical surveys

Beside the possibility of generating quality reports according different ESS standards there is also a GSBPM module integrated in the DB. Having GSBPM the CBS can work on further improvements by using quality indicators and description of particular survey and in accordance with the Annual Implementation Plan published in the Official Gazette.

11.1.1. Quality management - Compliance Monitoring

Compliance Monitoring

11.1.2. Quality assurance - national specifics

In order to ensure the quality of price collection activities, a system of regular quality control of field collection has been established.

Quality control is carried out in two stages:

• In the first stage, technical inspection of collected prices is carried out. It includes inspection of the continuity of visiting the outlets by price collectors and the continuity of price collection of the product. The technical control includes a selected sample of outlets and selected product groups. The implementation of technical control is organised by Data Collection and Processing Sector, and the dynamics of the implementation is based on expert assessment. 
• In the second stage, central staff (Price Statistics Department) carry out methodological controls of received data on prices for each geographical location separately and for each item and outlet. There is no automatic rejection and when further explanations are necessary or when errors have been detected, the central staff then requires from price collectors to provide additional information or visits the outlet again.

Price collectors are contacted on a daily basis in order to confirm the monitored prices and when necessary to revise incorrect price observations. Furthermore, price movements are checked for EAs and up to total index.

11.2.1. Compliance monitoring - last report and main results

The last available compliance or follow-up report can be found in the dedicated HICP section ‘Compliance Monitoring’ of Eurostat’s website, under ‘Methodology’.

Compliance Monitoring Report for Croatia

11.2.2. Quality assessment - national specifics

HICP methodological requirements and standards have been followed. Also, accuracy, timeliness and punctuality, accessibility and clarity, comparability, coherence, and costs and burdens are controlled on a regularly basis.

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

The main HICP/CPI users are national state institutions, other national users (financial institutions, economic analysts, the media, students, enterprises and the public), international institutions (Eurostat, ECB, IMF, UN ECE, etc.) and internal users (other statistical departments within the CBS).

While the national CPI is preferred at national level, the HICP is mostly used for cross-country comparison of inflation between EU countries.

CBS conducted a user satisfaction survey in November 2013, April 2015 and 2022 (from November 25 to December 23).
Few user satisfaction surveys about CBS's activities on social networks were carried out in 2016 and 2017.
User consultation in CBS takes place in a variety of ways, both formal and informal. The main communication channel with users is the Statistical Council which is the advisory body for strategic issues concerning official statistics and it is established to ensure that user needs are considered (Official Statistics Act, Article 20).
Users and general public also have an opportunity to comment and give their opinion on CBS's draft strategies, laws, programmes and plans through application e-Consulting on the Central Government portal. Also, there are many bilateral contacts with the main users, and many informal contacts with occasional users.
CBS set up standing user groups for key statistical areas in the first half of 2017. User groups meetings are held occasionally (according to any open issue). Such groups provide an effective means for collecting feedback on statistical services and products, for informing users about quality and methodology reports and other metadata.

HICP and HICP-CT are in line with relevant regulations/guidelines.

All ECOICOP categories accounting at least one part in a thousand of the total expenditure are calculated (HICP and HICP-CT) and transmitted to Eurostat.

The accuracy of source data is monitored by assessing the methodological soundness of price and weight sources and adherence of the methodological recommendations.

The main data source for weights is National accounts data at higher levels and HBS on lower levels of aggregation.

Local price collection (visit to local retailers and service providers) and central price collection (telephone, e-mail, Internet) are the data sources for prices.

Price collection methods ensure sufficient coverage and timeliness.

The outlets, from which prices are collected, are chosen to represent the existing trade and service network and they are based usually on three main criteria:

• popularity with customers,
• significant turnover from consumer sale and
• availability of goods and services included in the HICP basket.

All private households in the economic territory of the country are covered, whether resident or not and irrespective of their income. There isn't any systematic errors and any revision of the data.

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

The CBS tries to reduce the sampling errors by using a sample of consumer prices that is as large as possible given resource constrains. In order to minimise the variance of all-items index the number of prices that should be observed in each geographical location for each item category is selected.

For HICPs non-sampling errors are not quantified. Statistics Croatia tries to reduce non-sampling errors through continuous methodological improvements and survey process improvements which can help avoiding coding and typing errors.

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 was introduced in 2007 and the main rescaling has been from 2005=100 to 2015=100 (since January 2016).

The HICP data is 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 backward calculations under the newer standards were performed when appropriate basic data was available.

Differences between the HICP and national CPI

Different population coverage:
The HICP covers the consumption expenditure of non-residents and institutional households within the economic territory of the country, while they are not included in the national CPI.

Different data sources for the calculation of weights:
The main data source for the HICP weights is the National Accounts data, while the main data source for the CPI weights is the Household Budget Survey.

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

 According to revision policy of the CBS, the CPI/HICP data is published as final and is not subject to revision (unless an error or mistake is found), a fact which is noted in the publications.

No cases of mistakes in the compilation of the total HICP that would require HICP revisions have arisen so far. Still, the change of reference year caused revisions to a number of previously published inflation rates because of rounding effects. Thus, inflation rates calculated from the 2015=100 series can differ from the rates calculated from the 2005=100 series.

18.1.1. Weights

The main data source for the calculation of the HICP weight structure are data derived from the National Accounts. 

Weights are updated annually. The update of weights is done with the revision of the HICP basket of goods and services.

According to Eurostat recommendation, weights for 2023 are calculated according to the t-1 estimated household final consumption expenditure data (domestic concept) data obtained from national accounts. The most recent version expenditure available from national accounts, including the ECOICOP breakdown, was the starting point for estimation purposes. The estimation of household final consumption expenditure is based on last available data from CBS surveys as main data sources: turnover data for retail trade and for services and other regular CBS monthly and quarterly survey data. In addition, the Croatian National Bank data (Balance of payments) and other administrative data sources are used.

18.1.1.1. Compilation at elementary aggregate level

The elementary aggregate is the lowest level of aggregation for which the weights are available (6th or 7th digit level). For product-offers within elementary aggregate, there are no weights available. The weighting structure follow the aggregation structure of the HICP (based on ECOICOP) and additional sub-divisions are introduced by stratification of the sample in order to obtain more detailed product level classification.

Below the ECOICOP category, level for construction of the weights on the 6 and 7 digit level last available HBS data are used. Additional data sources for construction of the weights for electricity (the Croatian Energy Regulatory Agency), telecommunication services (the Croatian Regulatory Authority for Network Industries), insurance (the Financial Agency, the Croatian Insurance Bureau), cars (the Ministry of Interior), accommodation services (tourism statistics), transportation (transport statistics), education (the Ministry of science, education and sports as well as the education statistics), tobacco, fuels, medicines etc.

Except for weights for elementary aggregates on the level of Croatia, there are regional weights as well (nine geographical locations included in the sample). Regional weights are defined at the elementary aggregate level – each geographical location in the sample as a pre-assigned weight (total sum of regional weights for each elementary aggregate is 1000). Elementary aggregates are weighted together by regional weights in order to obtain national elementary aggregates. These index numbers are then aggregated to the CPI/HICP.

At elementary aggregate level, weights are reviewed and price-updated on annually basis.

The HBS data on the level of regions is the base for calculation the weights on the region level.  As the prices for the CPI/HICP are collected in nine cities (geographical locations) this weights are allocated to the cities. In case where in a particular region only one city is included in the sample the weight of the region remains. On the other hand, where in a particular region, more cities are in the sample then regional weight is divided into cities according to the number of the population of these cities in the region (main source is the Census).

Weights on the level of nine cities are calculated for elementary aggregates for which prices are collected locally while for centrally collected prices there are no such weights (elementary aggregate indices are directly aggregated on the level of the Republic of Croatia).

No outlet weights are used. There are no weights associated with single price observations for product-offers.

18.1.1.2. Compilation of sub-index weights

Since 2021 at sub-index level weights are derived from provisional National Accounts data for t-1. The expenditure shares at sub-index level are derived from data for the year t-2 and these shares are updated to make them representative for t-1. From NA data weights for the indices at the 5-digit level are derived. Since the National Accounts data does not provide sufficient details on expenditure shares at lower levels (national levels), at the level below ECOICOP the HBS data is used.  

Estimation for Q4 is based on short-term statistics and other available sources. For some parts it was assumed that Q4 is equal to the average of the first three quarters.

For parts for which we could not apply such assumption we combined an indicator of the change in volume with the indicator of the change in price and for some we multiplied the value by an indicator of the change in volume.

18.1.1.3. Compilation of sub-index weights

According to the recommendation in Eurostat's Methodological note on the derivation of HICP weights, the weight reference period of the data used for the calculation of the weights of sub-indices is t-1.

18.1.1.4. Weights – plausibility checking

As regards weights, the plausibility is checked in a way that significant differences from the previous year are detected and cross-checked. Also, various additional data sources for weights are used and compared (where possible). Finally, the additivity of the weights is checked as well that total weight is 1,000.

18.1.1.5. Price updating

Price-updating to December t-1 is conducted by calculating price changes between the average of the t-1 and December t-1 (price reference period).

It is applied to the most detailed national levels (6th and 7th).

18.1.1.6. Compilation of total household final monetary consumption expenditure

Country weights

The main data source for the calculation is National Accounts data.

The most recent version of t-2 expenditure as available from the national accounts, including the ECOICOP breakdown, was the starting point for t-1 estimation purposes.

The total Household Final Monetary Consumption Expenditure (HFMCE) was calculated as the sum of quarters for 2022 HFMC =HFCE – (narcotics+ imputed rent for housing + games of chance + prostitution + life insurance + public insurance connected with health + FISIM + net purchases abroad +income in kind + administrative charges of private pension funds and the like).

Estimation for Q4 is based on short-term statistics and other available sources. For some parts it was assumed that Q4 is equal to the average of the first three quarters.

18.1.2. Prices

The price data is based on a survey, on administrative data sources, web scraped data and on data from other statistical activities.

18.1.2.1. Data Source - overview  

The prices data are mainly based on surveys.

18.1.2.2. Scanner data - general information

CBS participated in the Eurostat Grant Agreement on scanner data with the general goal to undertake research on the exploitation of scanner data as new source of price information which would improve current methods. Analysis has been performed in the field of food and non-alcoholic beverages and alcoholic beverages and tobacco. So far, data from three retail chains have been obtained.

As the methodology is finalised and the IT production system is established, all necessary preparations are performed in order to start the implementation of scanned data in the regular CPI/HICP production system.

During the year 2023, a monthly test calculation in the new production system, using in parallel current methodology and new methodology, will be carried out. 

18.1.2.3. Web scraping - general information

The   implementation of web scraping in regular production started with the January 2021 index.

ECOICOPs for which web scraping is applied:

• 04.1.1.0 (Actual rentals paid by tenants)
• 05.3.1.1 (Refrigerators, freezers and fridge-freezers)
• 05.3.1.2 (Clothes washing machines, clothes drying machines and dish washing machines)
• 05.3.1.3 (Cookers)
• 05.3.1.4 – partly (Heaters, air conditioners)
• 05.3.1.5 (Cleaning equipment)
• 05.3.2.2 (Coffee machines, tea makers and similar appliances)
• 05.3.2.3 (Irons)
• 05.3.2.4 (Toasters and grills)
• 05.3.2.9 (Other small electric household appliances)
• 08.2.0.1 (Fixed telephone equipment)
• 08.2.0.2 (Mobile telephone equipment)
• 09.1.1.2 (Equipment for the reception, recording and reproduction of sound and vision)
• 09.1.2.1 (Cameras)
• 09.1.3.1 (Personal computers),
• 09.1.3.2 (Accessories for information processing equipment)
• 09.1.4.2 (Unrecorded recording media)
• 09.1.4.9 (Other recording media)
• 09.3.1.1 – partly (Games and hobbies).

Data for 32 products are web scraped twice a month (1st and 2nd Tuesday) from 14 websites of which 13 are physical stores and 2 are online stores. In addition, prices for market rentals are web scraped from one (the most relevant) websites.

18.1.3. Sampling

18.1.3.1. Sampling design: locations for survey

As the reference population included in the Croatian HICP refers to the whole population of the country the HICP refers to the whole territory of the Republic of Croatia.  The geographical sample design is based on the results from the Household Budget Survey and the population Census. The choice of geographical locations is based on the Household Budget Survey disaggregated by statistical regions, according to the Nomenclature of Territorial Units for Statistics (NUTS), which was in the introductory phase at the time our CPI/HICP methodology was being developed.

18.1.3.2. Sampling design: outlets

As there is no relevant data that would allow the application of outlet sample design based on one particular sampling method, judgmental sampling is applied (non-probability sampling method). The number of outlets that should enter the sample are determined by central office. The number of outlets for each representative product in each geographical location is pre-determined by the criteria of the population number for each geographical location (city) in the sample and regional weights - HBS data on the level of regions allocated to the cities. If only one city is included in the sample of a particular region, the weight of the region remains, and where more cities are in the sample of a particular region, the regional weight is divided into cities according to the number of the population of these cities in the region (main source is the Census). 

In total, 15 outlets are selected for one geographical location, Zagreb (leading to 15 price quotes for each representative product), 8 outlets for three geographical locations (leading to 8 price quotes for each representative product), 6 outlets for two geographical locations (leading to 6 price quotes for each representative product) and 4 outlets for two geographical locations (leading to 4 price quotes for each representative product).

Different types of outlets are included in the sample:

• specialised stores with food
• non-specialised stores selling food, beverages and tobacco (minimarket, supermarket, hypermarket)
• petrol stations
• specialised non-food stores
• kiosks
• market stalls

18.1.3.3. Sampling design: newly significant goods and services

Introducing newly significant products is connected with re-sampling and in order to maintain the representativity of the reference sample and to represent current market and consumption pattern. Introducing newly significant products relates to the replacement of the goods and services from the basket which disappeared from the market with the ones which entered the market or to introducing completely new goods and services as such.

New products on the market are identified mainly through the Household Budget Survey but also through other sources such as press (newspapers, magazine), producer information, PPP product list, market research, price collectors’ suggestions and other sources. Price collectors are instructed to monitor development in the market to identify new good and services and report these changes and tendencies for future changes to the central offices.

For the newly introduced products, price collectors have to record prices for January of the current year and for December of the previous year (base period for prices in the current year).

The procedure of reviewing the product sample includes involvement of central staff and price collectors. While central staff is in charge for defining initial sample framework from the HBS results and additional alternative data source, price collectors provide the CBS with relevant information based on their experience and give the proposals regarding inclusion of new representative items or exclusion of existing ones as well as proposals on the changes of the existing product descriptions. Those proposals are sent each year, usually in October to central office where they are analysed.

Reference product-offers are selected by price collectors and they are updated monthly. Price collectors are instructed to select product-offers that are most sold in the outlet in accordance with pre-defined product description for the representative item. Selected product-offers are then checked and verified during the validation procedure in central office.

Price data is collected every month.

18.3.1. Price collection surveys

Price collectors collect prices by tablet computers (responsible for entering data on prices and additional explanations related to the products, verification the data and transmission the data to the central office).  Quality adjustment procedures are performed in the CBS by the central staff. At regional level, price collectors make no quality adjustments. They are instructed to report to central office all cases of considerable quality changes due to product replacement. 

Central price collection is carried out by Price Statistics Department and it is applied in the following cases: when the retailer selected in the sample has only one retail outlet, when the headquarters of the retailer are able to provide data relating to their retail outlets and they charge uniform prices over the whole country. Besides, central price collection is selected when there are no significant regional differences in consumption, when specialised product knowledge is required, when market research data are available to the Price Statistics Department and if elementary aggregate is homogeneous enough that further disaggregation is not required (e.g. fuel prices).

Prices collected by central staff from a single source (retailer’s head office) represent product prices in all outlets of the same retailer. However, prices collected from a single source are not treated as one observation in the sample but as the number of observations which is equal to the number of outlets whose range of products includes the sampled product. Centrally collected data are recorded in writing, by telephone, Internet or electronically.

18.3.2. Timing of price collection

Price collection has been carried out between 1st and 25th of the reference month.

Prices for the majority of goods and services are collected once a month, on working days (prices are not collected during weekends and public holidays) on approximately same days of the month.

Data validation is carried at different levels of organisation. First validation is done by price collectors on the local level in the special software system used for this purpose. Price collectors verify all price changes and provide additional explanations for unusual price changes (both prices and codes are validated). Second validation is carried out by central staff after data is received using the special data control program which performs several logical and arithmetical validation options in order to identify unusual price movements (except for percentage change for each product-offer comparing to the previous month, the tool indicates whether there is any change comparing to the previous period in quantity, code or product description) as well as the missing prices and replacement products. The prices are validated for each geographical location separately and for each item and outlet. There is no automatic rejection and when further explanations are necessary or when errors have been detected, central staff then requires from price collectors to provide additional information or to visit outlet again. After the validation of prices is completed, software produces price indices by comparing prices to the previous month showing the price movements on the level of individual representative items in the analysed geographical location or on the level of the whole country as well as the average prices for the individual representative items.

18.4.1. Data validation - price data

First validation is done by price collectors. One of the main functionalities of the tablet software is option that any price, quantity or product description cannot be stored without appropriate code of change (price increase, price decrease, replacement product-offer, price after reduction, product-offer not found in the outlet, change in quantity, additional explanations). Besides, the software validates data entered with arithmetic operations by giving warnings about allowed price oscillation and code type input (additional confirmation is required). In the main price recording form the price collector can easily fill in the form with important information about the selected product. Also, there is a review of historical data (one year period) of selected product from previous months/periods.

Second validation is carried out by central staff after importing prices into the central computer system. Prices are checked and validated comparing to the previous month for each geographical location separately and for each item and outlet by four employees. The person in charge for each geographical location has to check the whole list thoroughly. For the purpose of this price validation a special data control program has been developed which performs several logical and arithmetical validation options in order to identify unusual price movements (except for percentage change for each product-offer comparing the previous month, the tool indicate whether there is any change comparing to the previous period in quantity, code or product description) as well as the missing prices and replacement products.  The tool enables each product-offer to show its price movements in the previous 12-month as well as the prices for the same product in other outlets or in other geographical locations.  Prices that remain stable for a long period are checked as well. After the validation of prices is completed, software produces price indices comparing to the previous month showing the price movements on the level of individual representative items in the analysed geographical location or on the level of the whole country as well as the average prices for the individual representative items.

For analytical purposes, verification tool also enables the export of different kind of summarised tables in Excel, depending on the purpose of analysis (i.e. separate tables with missing prices, tables showing only product with difference in prices or quantities, codes, product-offer descriptions, seasonal products, replacement products, comments or table containing all joined table containing all this information together).

18.5.1. Elementary price index formulae

The Croatian HICP is Laspeyres chain index, covering the categories of the ECOICOP/HICP (European Classification of Individual Consumption by Purpose).

The price indices for elementary aggregates are calculated as a ratio of geometric mean prices.

Regarding the number of decimals, the following rules are applied:

• For price observations two decimals
• For weights two decimals (compilation and transmission)
• For compilation and transmission of HICP unrounded indices are used (13 decimal places)
• For publication of HICP index figures are published to two decimals and rates of change to one decimal place

From above listed cases rounding has been used for the purpose of publication of HICP index figures

18.5.2. Aggregation of different data sources

Elementary aggregate indices have been computed as a ratio of the current and the price reference period geometric mean (Jevons) of all prices of the products within an elementary aggregate.

Elementary aggregates indices are indices on the lowest level where only product-offers prices are used for calculation.

Elementary aggregates are compiled as ratio of the geometric mean of prices for each region (for example Rice in Zagreb, Rice in Dubrovnik, Rice in Split etc.). It means that prices for product offers within elementary aggregate in the current month are compared to the prices of the base period (December of the previous year).

Calculated elementary indices on regional level are then weighted together using regional weights in order to obtain elementary aggregate at national level. Regional weights are actually weights for each of 9 cities in which prices are collected and total sum for Croatia is 1,000.

Elementary aggregate indices at national level are aggregated to higher index level using the Laspeyres’ type formula.

18.5.3. Chaining, linking and splicing methods

The HICP is compiled by using December of the previous year as the linking month.

The aggregated indices (overall HICP and ECOICOPs) are first calculated with December of the previous year =100 as a base and then linked to the 2015=100 (average of the year 2015) by using the indices for December of the previous year based on 2015 average.

18.5.4. Quality adjustment – Detailed information

Product-offers are usually quality adjusted in cases when a quality change occurs and it is judged that there is a significant difference between the replaced and the replacement product-offer.

In order to deal with quality changes, a case by case approach is adopted. There are no automatic procedures for any product group. The choice of method depends on the specific replacement situation and selected replacement product-offer. At present, hedonic method is not used.

There are three main types of quality adjustment procedure used in the CPI/HICP: direct comparison (no quality change occurred and no adjustment is made), explicit or direct methods ('component wise-methods') and implicit or indirect methods ('holistic methods').

The following implicit methods that are used in both CPI/HICP: overlap method (when prices of replaced and replacement product-offers are available – so far applied only in few cases), bridged overlap (average price development of other available product-offers it the same elementary aggregate are used as a bridge for estimation for the price change) and retrapolation (only in cases when replacements are infrequent and in effect random).

Since the January 2022 index, the bridged overlap method is applied in accordance with the new HICP recommendation on bridged overlap method (June 2021). As recommended, the bridged overlap method is avoided in cases when the last price of the old product-offer is a reduced price, when the first price of the new product-offer is a reduced price or when the first price of the new product-offer is unusually high. Alternatively, other available QA methods are applied (direct comparison or explicit methods).

Explicit methods for quality adjustment that have been applied in the Croatian CPI/HICP are: package size adjustment (value of a change in package size is assessed as the relative change in package size), option pricing (when the price of the product-offer options are available), judgmental and supported judgmental quality adjustment (when additional information is available and assessed by judgement or by specialist).

For the most product-offers implicit quality adjustments are applied due to the fact that in the practice is often not possible to obtain enough information about characteristics of the product-offers in order to evaluate a proper quality change.


The incidence of quality changes and adjustments are monitored on regular basis. All quality changes and replacements are coded in the IT application and quality adjustment methods performed are coded as well.

General quality control rules are set and all available methods are rated as A, B or C methods (A and B methods are treated as appropriate quality adjustment methods while C methods are all other methods which in principle are not to be used).

Direct price comparison:

• Food and beverages, clothing and footwear, (minor changes)
• Used cars (minor changes), household appliances (minor changes, method A)
• PC games (method B), books – rapidly changing market (method B)
• Books – long selling market (method A)
• CD/DVD educational – long selling market (method A)
• CD/DVD educational - rapidly changing market (method B)
• Software (method A for applications, method B for games).

Implicit methods:

1. Bridged Overlap method is used for:

• clothing and footwear (non-automatically bridged overlap for major changes)
• household appliances (major changes, method B)
• new cars (major changes, method B)
• used cars (major changes, method B)
• TV-sets (minor changes, method A, major changes method B)
• notebooks (method B), audio, video and photo equipment.

2. Retrapolation is limited used only for all other non-food product-offers (in cases where replacements are infrequent in effect random).

Explicit methods:

1. Option pricing is used for:

• household appliances (major changes, method A)
• new cars (minor changes, method B)
• desktop computers (method B)
• telephone and telefax equipment
• audio, video and photo equipment.

2. Judgemental and supported expert judgement is used for:

• new cars (minor changes, method B)
• used cars (minor changes)
• telephone and telefax equipment.

3. Package size adjustment is mostly used for:

• food and beverages (major changes)
• non-durable household goods.

18.5.5. Seasonal items

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:

• 01.1.6    Fruit (4 EAs out of 11 EAs)
• 01.1.7    Vegetables (1 EAs out of 13 EAs)
• 03.1       Clothing (4 EAs out of 28 EAs)
• 03.2       Footwear (2 out of 7 EAs)
• 05.2       Household textiles (1 out of 4 EAs - sunshade)
• 09.4       Recreational and cultural services (1 EA out of 12 EAs)
• 09.6       Package holidays
• 11.2.0    Accommodation services (1 EA out of 7 EAs – accommodation in camps)

Fish is not considered seasonal.

For determining the weights for seasonal items, strict annual weights are used (during the whole year the indices of seasonal items are calculated with fixed weights). Therefore, for seasonal items that are out-of-season, estimated prices are applied.

Not applicable.

None.