Monthly consumer price indices, by COICOP

Statistical Office of the Republic of Serbia (SORS)

Price statistics division, CPI/HICP unit

5 Milana Rakica str., Belgrade 11000, Republic of Serbia

Consumer price indices are measures of inflation in Republic of Serbia. They are economic indicators that measure the change over time of the prices of consumer goods and services acquired by households for the purposes of directly satisfying consumer needs.

The CPIs are classified according to the ECOICOP (European Classification of individual consumption by purpose).

Main ECOICOP headings:
00. All-items (total or all-items);
01. Food and non-alcoholic beverages;
02. Alcoholic beverages, tobacco and nacotics;
03. Clothing and footwear;
04. Housing, water, electricity, gas and other fuels;
05. Furnishings, household equipment and routine household maintenance;
06. Health;
07. Transport;
08. Communication;
09. Recreation and culture;
10. Education;
11. Restaurants and hotels;
12. Miscellaneous goods and services.

CPI covers the consumption expenditure for the goods and services that are acquired by households.

Price refence period – previous year

Index reference priod – previous year 

Weight reference period – t-1

Elementary aggregate – the lowest level at which observed prices enter the CPI (level of products or services)

Elementary  index – price index for the elementary aggregate

Weights –expenditure  on any goods and services covered by the CPI expressed as share (1/10000) in total expenditure of households

Unit of observation are prices of good and services purchasted by household (final household monetary consumption expenditure).

The target statistical universe is the 'household final monetary consumption expenditure' (HFMCE) within the economic territories of the countries compiling the CPI. 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 account concepts in the European System of Accounts (ESA 2010).

CPIs comprise all products and services purchased in monetary transactions by households within the economic territory of a country and abroad (i.e. ''National concept'').

The CPI covers the entire territory of the Republic of Serbia. For the purpose of price collection, the country is divided into fifteen regions which are economic and administrative centers and represent the whole country. The largest urban centers and the areas around these have been deliberately selected (Beograd, Kragujevac, Kraljevo, Leskovac, Niš, Smederevo, Šabac, Užice, Valjevo, Zaječar, Novi Sad, Sremska Mitrovica, Subotica, Zrenjanin and Pančevo).

CPIs are calculated from January 2007. 

Base period for calculation of CPI are previous year (previous year=100).

Following units of measure are used:

• Index (the ratio of the price of the basket in a given year to the price in the base year multiplied by 100. However, the HICP can be thought of  as the amount the average consumer would have to spend in a given year to buy the same basic goods and services that one would have to pay 100 monetary units for in the base period);
• Percentage change on the same period of the previous year (rates);
• Percentage change on the previous period (rates);
• Proportion of the total expenditure (weights) expressed in 1/10000.

Month (indices and rates).

Year (weights, indices and rates).

All activities on collecting and processing data on prices are carryed out according Law on Official statistics and Programm of official statististics.

Not applicable.

National legislation:

Official statistics law

(http://www.stat.gov.rs/media/2322/zakon_o_statisticie.pdf)

The confidential data transmitted are used exclusively for statistical purposes and only accessible to staff working in statistical activities. In order to protect individual's information privacy and business interests of business units, only aggregated data are published (observation units are not recognizable either directly or indirectly). Therefore, adjusted contents of the tables are in use and certain rules are applied to protect data (Official statistics law, Official gazette of RS, No 104/2009). In order to protect individual's information privacy and business interests of business units, only aggregated data are published (observation units are not recognizable either directly or indirectly). Therefore, adjusted contents of the tables are in use and certain rules are applied to protect data (Official Statistics Law (Official gazette of RS, No 104/2009)).

The release calendar is publicly available and published at the end of the year for the next year on the SORS website, in Serbian and English.

SORS website:

https://www.stat.gov.rs/en-us/calendar/

In line with National legal framework and the European Statistics Code of Practice, the release policy determines the dissemination of statistical data respecting professional independence to all users at the same time in an objective, professional and transparent manner in which all users are treated equally. Users are informed about data release by the release calendar. 

Monthly, about the 12th of the month following the reference.

Press release  - Consumer price indices by COICOP is published on monthly periodicity on the website at 12:00  (local time), on the day of release,  in Serbian as well as in English language.

https://www.stat.gov.rs/en-US/oblasti/cene/potrosacke-cene

Consumer price indices by COICOP are published as Statistical release (with mark CN11) in monthly periodicity, as well as in other (complex) publications in monthly and yearly periodicity (available on the SORS website).

Consumer price indices by COICOP are available on web-site www.stat.gov.rs

According to the procedure for access to microdata, which was published on the website of the Repiblic Statistical Office.

None.

Short methodology оn CPI by COIOCP is given in Statistical Release (CN11) as well as in other publications with CPI data.

None.

Statistical Office of the Republic of Serbia regularly checks and follows new recommendations and regulations in the area of Consumer price indices in order to achieve the highest  level in relevance, accuracy, timeliness and punctuality, accessibility and clarity, comparability and  coherence.

Statistics of Republic of Serbia follows the principles in the Code of Practice for European Statistics (CoP). Quality Assurance Framework of the European Statistical System (QAF) is used for the preparation quality system and implementation of the principles.

None.

CPIs are the main instrument for measuring of inflation in the Republic of Serbia. They are also is used for:

• wages, social benefit and contract indexation;
• economic forecasting and analysis;
• measuring specific price trends;
• accounting purposes and deflating other series;
• inflation targeting by National Bank.

The key users of the CPIs are national state institutions (National Bank, the Ministry of Economy and the Government), other national users (financial institutions, economic analysts, the media, students, enterprises and the general public), European and international institutions (Eurostat, European Central Bank, International Monetary Fund, UN ECE, etc.) and internal users (other statistical departments in the SORS).

User satisfaction and needs are monitored through the User satisfaction survey. This survey is conducted electronically via web questionnaire, in order to  obtain the information on reasons and modes of usage of Office’s data and services, as well as how the users assess the data quality.

The questionnaire encompasses the following issues: data use, users’ satisfaction with the website, database and statistical data, users’ awareness, rating of the Office’s staff, ranking of the data quality, also including the issues related to demographic characteristics of the respondents. The main purpose of that survey is to study the users' needs, to get feedback on quality of data important for further work.

This survey is conducted every two years.

CPI's are available since 2007.

The overal accuracy is monitored by assessing and implementing all the methodological recommendations.

The goods and services selected for the basket are those of most importance to the customers; have a significant share in total consumption; best reflect the changes of prices of related products.

There are a variety of data sources both for prices and weights.

Prices are collected in outlets, craftsmen, supermarkets, green markets, etc., also via the internet and by phone. They reflect the price situation for the whole country. 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 are based usually on the following criteria: popularity with consumers, significant turnover from consumer sales, availability and representativeness of goods and services included in HICP basket.

Weights are based on the data from NA on the structure of Household Final Monetary Consumption Expenditure, HBS, etc. The type of survey and the price collection methods ensure sufficient coverage and timeliness.

The CPIs are statistical estimates that are subject to sampling errors because they are based on a sample of consumer prices and household expenditures, not on the complete universe of all prices/expenditures. The SORS does not produce numerical estimates of HICP sampling errors, which are difficult to quantify due to the complexity of price index structures and due to the common use of non-probability sampling. Consequently, no estimate for a global CPI sampling error could be produced.

The SORS tries to reduce the sampling errors by using a deliberate sample of consumer prices that is as large as possible in each geographic area and each item category, in order to minimize the variance of the all-items index.

Every sub-index level contains enough number of elementary aggregates which could show a realistic price movement. Principle of representativity is applied.

Non-sampling errors are not quantified. SORS tries to reduce non-sampling errors through continuous methodological and survey process improvements which can help to avoid coding and typing errors.

Consumer price indices by COICOP are published each month about 12th, in the edition Statistical Release with the mark CN 11, and they are also presented on the website of the Statistical Office of the Republic of Serbia according to a pre-announced schedule http://www.stat.gov.rs/WebSite/Public/CalendarView.aspx?pKey=37&cType=1.

The January News Release each year is published about 22nd February (due to the annual updating of the weights system).

CPI by COICOP  is published according to pre-announced release dates availabe on SORS website.

CPI by COICOP is in line with the definitions and classifications which ensure the minimum disparities in CPI calculation among different countries.

CPI by COICOP is produced only on the country level.

CPI by COICOP data are comparable over time.

Improvements in coverage and methodology with the aim of improving reliability and comparability may have introduced breaks in time series, and back calculation under the newer standards was performed when appropriate basic data was available.

Differences between national CPI by COICOP and HICP are based on:

• The weights concept: HICP are based on domestic concept, while national CPI by COICOP is based on the national concept of consumption
• Base period: for HICP it is December of previous year, while CPI by COICOP price reference period is average of the previous year.
• Coverage: HICP covers the consumption expenditure of both residents and non-residents and institutional households within the economic territory of the country (domestic concept), while CPI covers the residents consumption expenditure within the economic territory of the country and abroad (national concept)
• Methodology: The same  methodology is used for both CPI by COICOP and HICP

CPI by COICOP are internally coherent. Higher level aggregations are derived from detailed indices according to defined procedures.

No information.

CPI by COICOP are revisable under the terms set in General Revision Policy (available on SORS website) in case of mistake, new or better information and changes in Methodology. 

In practice, CPI by COICOP are published as final and are not subject to any revision.

Major changes in methodology are announced in advance.

However, if revisions are required in the future, SORS will make a revision in accordance with General Revision Policy.

Product selection, sampling and data collection are carried out by the CPI staff together with price collectors. There is a variety of data sources both for weights (National Accounts, Household Budget Survey, data from other statistics departments, Ministries, etc.) and prices (visits to local retailers and service providers, central collection via mail, telephone, email and the internet). CPIs are based on the continuous measurement of a sample of prices of specified goods and services. The CPIs are based on samples sufficient to yield reliable and comparable results, taking into account the diversity of products and prices. As products or retail outlets disappear from the market, they need to be replaced with new ones. CPIs calculations are based on up-to-date samples and introduce a new product when it achieves a sales volume of over one part per thousands of total consumers' expenditure covered by the CPI.

CPI measures 'pure' price changes. Prices should be unaffected by changes in the quality of products and they are adjusted for changes in quality of the goods and services.

Sample size

Number of price observations per month: approximately 37435

01. Food and non-alcoholic beverages  14021
02. Alcoholic beverages and tobacco  1379
03. Clothing and footwear  4294
04. Housing, water, electricity, gas and other fuels  886
05. Furnishings, Household equipment and routine maintenance of the house  4702
06. Health  1552
07. Transport  1269
08. Communication  539
09. Recreation and culture  2117
10. Education  110
11. Restaurants and Hotels  4576
12. Miscellaneous goods and services  1990

Number of elementary aggregates (representative products) at the lowest classification level:

All-items: 654

01. Food and non-alcoholic beverages  168
02. Alcoholic beverages and tobacco  20
03. Clothing and footwear  87
04. Housing, water, electricity, gas and other fuels  41
05. Furnishings, Household equipment and routine maintenance of the house  87
06. Health  30
07. Transport  60
08. Communication  29
09. Recreation and culture  59
10. Education  7
11. Restaurants and Hotels  27
12. Miscellaneous goods and services  39

Price collection takes places between the 1^st and the 23^rd in the month to which the index pertains, by price collectors, full-time price employed by SORS.

For the purpose of organizing the observation time in individual months and to cover the whole month, items are classified into following related groups for which prices are observed in a certain period of the month:

Agricultural products (observed in the 1^st and 3^rd week);

Non-food products (between 1^st and 10^th of the month);

Food products (between 11^th and 14^th of the month);

Services (between 14^th and 23^rd of the month);

Fuels (every Wednesday in the month).

For the products which show irregular price changes within the month, prices are collected more than ones (agricultural products and fuels).

The price collection methods are chosen by the SORS, in order to ensure sufficient quality, according to the methodology framework underlying the production of CPI.

Outlet selection:

Purposive sampling method is applied. The number of outlets was determined according to size of particular town. The number and structure of outlets ensure that the optimum number of prices is observed, enough to represent price movement for any group of goods and services observed.

Techniques of product selection and specification:

Price collectors, together with central staff, select a particular outlet and items offer for pricing according to Methodology and Guidelines for price collecting. The selection is done according to the criterion the most turnover and item sold in the outlet. In order to make sure that the same product is then re-priced each month, and in order to be able to observe which products are selected or priced, the price collectors should also record a pre-defined set of additional product characteristics for each priced product.

Techniques of price collection:

Most prices are collected in field locally, by price collectors visiting the outlets or service providers.

For about 15% of goods and services, centrally price collection is applied and done by specialists of the Price statistics unit of SORS. This is the case for state monopolies and nationally homogeneous prices, i.e. cars, insurance, tobacco, post and telecommunication services, package holidays, electricity and fuel prices, financial services, PC equipment, airplane tickets.

Data validation is carried out at different levels of the HICP compilation.

The first control of prices is done by price collectors on the field, before sending data in the Central office.

Second validation is carried out in SORS by central staff. The Price Statistics Division carries out the verification of the data received using the data control program designed for the monthly checks against data entering errors and mistakes. Computerized and manual checks are undertaken at various stages of price and index compilation. The verification sheets contain information on the price data entered and information related to the current and previous months; reasons of price changes indicated by price collectors, ratios of prices for all price quotations, covering all goods and services; the period of the last change of the price observed; the smallest and the highest prices; the coefficient of variation. Particular attention is paid to quality changes, to prices that do not change for some period of time, to the lowest and the highest prices. In some cases, price changes are checked by reference back to the outlet. The staff of the Price Statistics Division clarifies all uncertainties with the price collectors via telephone and e-mail.

Weights

Sources of weights: The main data source for the calculation of the HICP weight structure is data obtained from the National Accounts. National Accounts data are the main source for determining the weights at higher levels, while for lower levels, breakdowns are done using HBS data. The weight reference period is y-2.

The weights on 4-digit levels are based on Final Monetary Consumption Expenditure data obtained from the NA (t-2). The weights are classified according to the COICOP/HICP. Weights data from NA are adjusted with data from other sources (statistical as well as non-statistical). Detailing of weights' system is made using the information from HBS. The number of weights at the lowest level of aggregation.

The weights reference period for 2017 HICP is the year 2015, price reference period - average of the previous year.

The weights are changed every year. The critical weights are adjusted using the most recent statistical data (domestic trade, transport and services, energy statistics) as well as the information from other enterprises. Data for the weights reference period are price updated to the price reference period (December of the previous year).

Computation of the lowest-level indices

Elementary aggregates indices are on the lowest-level. The ratio of geometric means is used for computing the price indices for the elementary aggregates.

The next step is index calculation for higher levels (sub-indices) up to Overall level (All-Items HICP) using weights system and Laspeyres-type formulae. Lowest-level indices are aggregated into the price indices of classes, groups, divisions (and Total) of the ECOICOP.

Treatment of missing products and replacements
When a non-seasonal item is temporarily missing in a given outlet, the last recorded price is retained for one month, exceptionally up to two months, but usually at the same time the price for its substitute is observed. When it is clear that a non-seasonal item is missing permanently (in the third month or earlier), the item is substituted with the most comparable one in the same or in the most similar outlet.

Introduction of newly significant goods and services
Price collectors are instructed to observe developments in the market, to identify new goods and services and to report these to the Price Statistics Division. The central staff investigates the market, evaluates the relevance of new products to households and, using all available information, makes a decision whether they are significant and should be introduced into the HICP. This is done according to a planned timetable to coincide with the annual update list of goods and services at the end of each year. Goods and services that became insignificant for consumers or disappeared entirely from the market (they are not produced or imported no more) are excluded from product list and new, actual items are introduced.

Treatment of price reductions
Seasonal sales, other sales prices and reduced prices (e.g. special offers, discounts, etc.) are included in the index when they are available to all potential consumers with no special condition attached and with duration at least two weeks. Reduced prices for special sales stock (which will normally be of lower quality or quantity) are not observed.

Treatment of seasonal products

Particular products (some of fresh fruit, vegetables, clothes, footwear) are considered as seasonal. Their sale periods are from 2 to 6 months and sometimes duration and terms of every season differ from year to year.
In the out-of-season period, prices of seasonal products are estimated by applying the minimum standards for the treatment of seasonal products in the calculation of consumer prices.

All-seasonal estimation is used. Estimation is carried out in the following way:

• In the first month of the out-of-season period, the monthly typical price is calculated as average price for months of the in-season period.
• From the second month of the out-of-season period, the estimated monthly price is applied for each product which is out-of-season. To obtain the price ratio for estimation, only prices for products available in the current and previous months are used. The higher level price index is calculated using the weights of all (seasonal and non-seasonal) products belonging to the same class or sub-class and the long-term prices ratios at the territorial unit level.

In the first month of the new in-season period, available prices are observed by price collectors and the reporting month price for a product-offer in each outlet is compared with the estimated prices of the previous month.

No seasonal adjustments are made.

Adjustments for quality change

The quality descriptions of the products are carefully observed to ensure their comparability from month to month. Each change in the description is taken into account. QA are done in the central office case by case. There is no automatism. As HICP aims to measure 'pure' price changes, prices are adjusted for changes in quality of the goods and services using:

Explicit methods

• Direct price comparison: e.g. clothing - as required,
• Option pricing: new cars - as required,
• Judgmental QA: e.g. clothing, cars - as required,
• Package size adjustment: e.g. food and medicine,
• Mixed approaches: - as required.

Implicit methods

• Overlap: e.g. clothing, audio visual goods - as required,
• Bridged overlap: e.g. PCs, technical products, household appliances - as required.

At present, hedonic method is not used.

Minor quality changes are disregarded.

None.