| |

Harmonized Index of Consumer Prices (HICP)

      1. Kosovo Agency of Statistics - KAS
      1. Department of Economic Statistics and National Accounts
      1. Ibish Asllani
      1. Head of Price Division Statistics
      1. Street “Zenel Salihu” no 4. 10000 Pristina, Kosovo
      1. + 381 38 200 31 125
      1. No fax number available. The fax number is general for the office: +381 38 235 033
      1. 20/11/2015
      1. 20/11/2015
      1. 20/11/2017
      1. Harmonised indices of consumer prices (HICPs) give comparable measures of inflation for the countries and country groups for which they are produced. They are economic indicators that measure the change over time of the prices of consumer goods and services acquired by households. In other words, they are a set of consumer price indices (CPIs) calculated according to a harmonised approach and a single set of definitions.
      1. The HICPs are classified according to the five -digit level categories and sub-categories of the ECOICOP/HICP (European Classification of Individual Consumption by Purpose Adapted to the needs of HICPs). Main COICOP/HICP headings: 00. All-items (global index) 01. Food and non-alcoholic beverages 02. Alcoholic beverages and tobacco 03. Clothing and footwear 04. Housing, water, electricity, gas and other fuels 05. Furnishings, Household equipment and routine maintenance of the house 06. Health 07. Transport 08. Communication 09. Recreation and culture 10. Education 11. Restaurants and Hotels 12. Miscellaneous goods and services
      1. HICPs cover the whole household sector, more precisely the goods and services that are acquired by households including both resident and non-resident households.
      1. The Consumer Price Index in Kosovo was established in May 2002. It has been / is being continuously developed and improved in accordance with EU Regulations and standards. With the index of December 2014, new weights largely based on National Accounts data were introduced bringing the coverage of the CPI more into line with European Harmonised Index of Consumer Prices. As such the CPI from December 2014 is in effect an HICP. To reflect this, from the January 2015 index, the CPI was renamed the HICP. From January 2016 HICP indices were calculated with base year 2015=100. Data are published monthly, starting from year 2010. The HICP will be continually developed going forward to implement all current and future HICP Regulations and guidelines which at present have only partially been implemented. From January 2016 HICP The published data is as follows: Monthly data: - Indices: from January 2016 HICP Indices are calculated with the base year 2015=100. - Annual rates of change - Monthly rates of change - 12-month average rate of change Annual data: - Average index and rate of change - Country weights - Item weights
      1. Each published index or rate of change refers to the 'final monetary consumption expenditure' of the whole household sector of the corresponding geographical entity.
      1. The target statistical universe is 'household final monetary consumption expenditure' (HFMCE) within the economic territories of the countries compiling the HICP. The household sector to which the definition refers includes all individuals or groups of individuals irrespective of, in particular, the type of area in which they live, their position in the income distribution and their nationality or residence status. These definitions follow the national account concepts in the European System of Accounts (ESA 1995). HICPs comprise all products and services purchased in monetary transactions by households within the territory of a country; those by both resident and non-resident households (i.e. 'domestic concept'). Resident’s expenditure abroad is excluded. HICPs cover the prices of goods and services that are paid for in in monetary transactions only. The prices measured are those actually faced by consumers. The HICPs exclude interest and credit charges, regarding them as financing costs rather than consumption expenditure.
      1. Kosovo (National level)
      1. HICPs for Kosovo are available from January 2015. CPIs (which mainly used the HBS as the source of the weights and covered resident households only) are available from May 2002 until Octoberr 2017.
      1. The index reference period for the HICP is December 2015=100.
      1. Following units are used: • Index (unit less, 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 month (rates) Percentage share of the total (weights).
      1. Monthly
      1. Statistical units, natural and legal persons, regardless of whether they have a legal personality or not, are obliged to provide complete, updated and truthful information to the KAS and other producers of official statistics in appropriate form, timely and free of charge determined by the producer of official statistics, defined in article 2, Law No. 04/L-036 ON OFFICIAL STATISTICS OF REPUBLIC OF KOSOVO.
      1. Not available.
      1. “Agency shall ensure that individual data collected for statistical purposes, whether collected from natural or legal persons, or bodies and organizations of the public administration (hereinafter “Respondents”), are handled in a strictly confidential manner and used exclusively for statistical purposes. Law 04/L-036, Article 34. “All respondents shall be obliged, in accordance with the applicable law, to cooperate and provide timely and accurately statistical data to the Agency, and to cooperate with the Agency to verify the accuracy of the collected data. Law 04/L-036, Article 21: .
      1. Access to confidential data shall be permitted only to persons who are in charge of producing the official statistics up to that level that these data are necessary for producing statistics. Article 37, Law No. 04/L-036: .
      1. The KAS publishes yearly an advanced release calendar for all its publication for the current year. The calendar is publicly accessible on the KAS website.
      1. The general policy is that before publishing statistics on the Kosovo Agency of Statistics web site a press release is available, also on the web site, to inform users and media. All users get access to data at the same time.
      1. Harmonised consumer price indices are produced monthly.
      1. News releases on-line at the time of data dissemination.
      1. KAS publications, tables and material for press release are always available in three languages: Albanian, English and Serbian. The all-items HICP and detailed HICPs (for the 12 ECOICOP Divisions) are made available and first released in a special publication called 'First Release':
      1. KAS has online database:
      1. Users do not have direct access to micro-data, but by law researchers and institutions can request access through KAS.
      1. Data on statistics are also published in the KAS Statistical Yearbook:
      1. A brief explanation of the definitions, key concepts and methodological explanations for users is presented in the publication of data:
      1. KAS is committed to quality assurance in the production of official statistics. Based on the "Law On Official Statistics, Law 04 / L-036", KAS uses statistical methods and processes in accordance with internationally accepted scientific principles and standards and conducts ongoing analyzes in order to improve the quality and delivery of updated statistics. In carrying out its duties, KAS follows the overall quality management principles, in line with the European Statistics Code of Practice. KAS has developed a Quality Statement which is available on the KAS website: . The document lists eleven principles, much in line with the CoP principles like professional independence and statistical confidentiality, on which the work of KAS is based.
      1. Not available.
      1. During July 2017, in Kosovo Agency of Statistics was conducted the process of assessment of the Kosovo Statistical System through the “Peer Review” approach.
      1. Generally, HICPs are in particular suited for cross-country economic comparisons. The main users, apart from those above, include National Central Banks and other financial institutions; economic analysts, media and public at large.
      1. One of the key elements to ensure the quality of statistical data is the measurement of the satisfaction of users. The survey aims to gather comprehensive information on the needs and requirements of users of official statistical data. Through this survey the users of statistical data have expressed their thoughts and opinions regarding statistical views, they have provided advice and suggestions regarding their needs for statistics and how to improve these statistical data in the future. This survey was conducted during the conference held with the users of statistical data, in which 11 users responded. The questionnaire contained eight questions and included various topics: the use of statistical data, evaluation of KAS in general, the assessment of the site in KAS, evaluating the quality of statistical data, etc. More detailed information on this survey can be found on the web: .
      1. All statistics that are required by international standards are calculated. HICP covers more or less all the groups and subgroups of the ECOICOP/HICP classification, whose share in total consumption is greater than 0.1%.
      1. 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. As far as possible, methodology recommendations are taken into account, however, the HICP in Kosovo is still under development. Prices are collected in different types of outlets, supermarkets, markets, etc., in 13 municipalities in the country, some of them also via the internet and by phone-centrally. They reflect the price situation for the whole country. Higher level published weights are based on the data from structure of household final monetary consumption expenditure, unpublished weights at the most detailed level are derived from the HBS. HICP weights for the year 2016 are based on the NA data 2014, while for year 2017 are based on the NA data, reference year 2015. The outlets from which prices are collected are chosen to represent the existing trade and service network. Private households are included irrespective of their income. The domestic concept is in force..
      1. Not relevant as the sample is purposive and not statistical.
      1. For the HICPs non-sampling errors are not quantified. Eurostat and the NSIs try to reduce non-sampling errors through continuous methodological improvements and survey process improvements such as computer assisted price collection (not yet used for the collection of prices in Kosovo), which can help avoiding coding and typing errors. Unit Non-Response Rate Retail prices of selected representative products and services used to calculate the CPI and now the HICP are monitored at selected outlets (e.g. shops, markets, craftsmen and other organisations). At the points of sale, which were selected in the sample at the beginning of the year, each month information on prices should be obtained, since the number of sales locations during the year should not be changed. Therefore, each month we aim to have 100% response of units. Item Non-response Rate In the case of item non-response similar methodological limitations are valid as in the case of unit non-response. The number of prices which will be collected for the selected product at selected outlets shall be determined at the beginning of the year and generally does not change, except for retail prices of seasonal products. In the latter case, the price is only collected in those months when they are sold on the market (i.e. during the season.). If an item in a particular outlet disappears, these are replaced by the price collectors following written procedural guidelines.
      1. Timeliness of the First Release of the survey results is specified as the difference between the date of the first release and the end of the reference period, in our case therefore the last day of the month to which the results are related. First data for HICP are also final data, and are not corrected at a later stage.
      1. Delay time is 0.
      1. HICP regulations prepared by Eurostat in collaboration with EU Member States. HICPs are therefore developed on the basis of a harmonised methodology, and as such they should reflect only price movements and differences in consumption of population in an individual country The work carried out for the harmonisation of quality adjustment and sampling methods across EU countries is expected to further improve the comparability of the HICP – these developments have yet to be fully implemented in the Kosovar HICP.
      1. The CPI and now the HICP data are not fully comparable over time. As there have been several improvements in methodology since the CPI was first calculated. Most recently (December 2014) the coverage of the weights changed with the introduction of national accounts data, which aims but does not fully adhere to the Domestic concept. Methodological changes have been introduced with the aim of improving reliability and comparability of the HICP. These changes may have introduced breaks in time series. HICP is in the phase of implementation at KAS, so the efforts are to produce the HICP data that are as fully comparable over time as possible, following HICP regulations, manuals and methodologies.
      1. There are no considerable differences between what was published as the CPI and what is now published as the HICP, except that HICP aims to follow the domestic concept of consumption via the use of national accounts data for the higher-level aggregate weights. The CPI until November 2014 was based on the national concept of consumption and used largely HBS data for the weights. Thus the difference between the two is in weights. Given resource constraints it was decided to publish only the HICP from January 2015.
      1. HICPs are internally coherent. Higher level aggregations are derived from detailed indices according to well-defined procedures.
      1. Not available.
      1. There is no revision policy at KAS.
      1. HICP series, including back data, are revisable under the terms set in Commission Regulation (EC) No 1921/2001 of 28 September 2001. The published HICP data may be revised for mistakes, new or improved information, and changes in the system of harmonised rules.
      1. Product selection, sampling and data collection are carried out by NSIs. There is a variety of data sources both for weights (National Accounts, Household Budget Survey etc.) and prices (visits to local retailers and service providers and central collection via mail, telephone, email and the internet are used). The type of survey used is chosen by NSIs. However, all HICPs are based on the continuous measurement of a sample of prices of specified goods and services. The HICPs must be based on samples sufficient to yield reliable and comparable results, taking into account the national diversity of products and prices. Furthermore, as products or retail outlets disappear from the market, they need to be replaced with new ones. HICPs are required to be based on up-to-date samples, in particular by banning the practice whereby 'missing' prices are simply assumed to be equal to the last observed prices. The HICP will incorporate a new product when it achieves an estimated sales volume of over one part per thousand of total consumers' expenditure covered by the HICP. KAS data collectors, who are based in seven regional centres, collect approximately 6400 prices for 408 items (goods and services) in more than 1000 outlets during the period of 10th - 20th of each month. They obtain prices in stores, markets and other retail outlets in 13 municipalities of Kosovo: • Ferizaj • Gjakova • Gjilan • Istog • Mitrovica • Peja • Podujeva • Prizren • Prishtina • SuhaReka • Rahovec • Kamenica, and • Vushtrri The KAS central office staff in Pristina using the internet collects prices for items such as electricity, water, postal and telecom services, and rail transport. The regulation on tariffs has been applied in case of electricity, water, internet connection services, telephone services, and subscriptions to TV networks, car and health insurance, transport services by bus and railway, kindergarten services, university tuition fees.
      1. Data on prices for representative goods and services are collected monthly, between the 10th and the 20th day of each month by full-time price collectors employed in Regional Statistical Offices (KAS).
      1. The price collection methods are chosen by NSIs they aim to ensure sufficient quality, however, there is only limited data validation in the field due to a lack of resource. At present sales prices (discounts) are not included in the HICP. Outlet selection The outlets in each location are selected on the basis of the knowledge of price collection and regional statistical specialist. Replacement outlets if required, and sample updates are performed in the same way. The main criteria for selection of outlets in each locality are the coverage of the available shopping areas within each location and the representation of different types of outlets. The number of outlets sampled varies by size of locality and by the type of item being priced. Once a year, usually in November and December, the sample of outlets is reviewed and updated. The sample covers different types of outlets from market stalls, specialised shops, big shopping centres, restaurants and hotels as well as internet shops and catalogues. Prices for fresh fruit and vegetables are collected also from open market in addition to supermarkets and traditional shops, price for mobile phone and package holiday in internet shops. Most of all prices are collected in a traditional way, i.e. in the field from shops; some prices are collected centrally such as; Electricity, water, internet connection services, telephone services, and subscriptions to TV networks, car and health insurance, transport services by bus and railway, kindergarten services, university fees. Techniques of products selection and specification The representative products to be priced are selected judgmentally at the end of every year by central price statistics staff and price collectors (specialist) of regional statistics, who also determine their specifications. These products are selected on the basis of information obtained from detailed HBS data, price collectors’ suggestions, PPP product lists, producer’s information, market research data and other sources. Price collectors are instructed to select the most adequate product available in the outlet taking into consideration its specification as well as the instructions for selecting product. The specifications for individual good/service are more or less detailed; indicating size, unit, materials, brand, and characteristics. The specification will be depends also on the nature of the product. If a product has many characteristics which could have effect on its price, then the specification is more exact. For some products such as food and some garments, specifications are looser.
      1. Data validation is undertaken by KAS, however, resource constraints severely restrict the amount of data validation that can be actually undertaken. Only one person is available for entering and checking the data in the head office, thus prices collected in the field are taken as given and are not validated. All collected prices are reviewed by price collectors in the field before being entered into the computer centrally in the head office; the second phase of control is incorporated in the computer program for data entry and in the end all data entry is manually checked by the responsible person 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 in the field. However, resources for doing this are very limited. 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.
      1. Weights From December 2014, the elementary-aggregate (lower level) unpublished weights are derived from Kosovo’s Household Budget Survey (HBS) and from other internal KAS sources. KAS estimates higher level published weights for the 83 E-COICOP classes largely from National Accounts (NA) data. All weights are generally updated each year. The current weights, introduced in January 2017, are based on national accounts expenditure estimates for the year 2015 price updated to December 2016. Updating the weights each year assures that the HICP reflects current consumption patterns. Computation of the lowest-level indices The price indices for elementary aggregates are calculated as a ratio of geometric mean prices. Imputation of the prices For the seasonal items which disappear from the market place during one or more months of the years the price relative is imputed with the price relative of the group where this item is included. This same methodology could also be used for non-seasonal items that disappear from the market place on a temporary basis (though this is not currently undertaken). While similar to HICP standards, the current method is not fully compliant with the HICP seasonal regulation with regards to the estimation of the price in the first out of season month. Calculation of the index The HICP is calculated at the national level, no regional indices are calculated. Each month’s HICP is calculated in two steps: 1. Elementary indexes (indexes for the elementary aggregates) are compiled from collected prices using the unweighted-geometric-average (Jevons) formula. 2. Higher-level indexes, including the all items HICP itself, are formed by averaging elementary indexes using a weighted arithmetic-average (Laspeyres-type) formula. We use the geometric means of price ratios between current with December for calculation of price relatives. Aggregation over items then gives the national HICP of Kosovo:
      1. Not applicable.