Agency for Statistics of Bosnia and Herzegovina (BHAS)

Business Statistics Sector – Department for Services Statistics

Zelenih beretki 26, 71 000 - Sarajevo

The data are published in the form of monthly and annual change rates calculated from the volume indices of retail trade turnover in BiH, monthly series of base volume indices (2015 = 100), and volume and nominal gross indicators (growth rates and indices) in line with the Classification of Economic Activities of BiH 2010 (hereinafter: KD BiH 2010), collected by using a monthly survey on retail trade (M KPS TRG-1) in BiH. 

Classification of Economic Activities of BiH 2010 (KD BiH 2010) for enterprises (fully harmonized with all levels of NACE Rev.2).

Classification of Products by activities BiH 2010 (KPPD BiH), fully harmonized with all 6-digit levels of CPA 2008.

Coverage of activities: The RTI survey covers business entities /legal units which are, by the main activity, registered within the retail trade, except retail trade of motor vehicles and motorcycles (division 47 - KD BiH 2010), and businesses entities that are, according to their main activity, classified in other activities, but also performing retail trade.

Coverage by size:  For the monthly survey on retail trade in BiH the combined method of full coverage and stratified random sampling is used. The sample is divided into strata according to the entity to which the business entity belongs, the class of financial data (financial report for the previous year), and the activities of the business entity (Division 47-KD BiH 2010). The number of employees is used as an auxiliary stratification variable.

Nominal turnover index is expressed in current prices (unadjusted for price effect). For users of statistical data it is very important to follow the evolution of phenomena in time and for these purposes we use real index of retail trade. Real index of Retail trade is expressed in constant prices, and it is calculated by deflating retail trade turnover by adjusted Consumer Price Index. 

Observation units in the statistical survey are business entities/legal persons that are, according to the main activity registered to perform activities of retail trade, with the exception of trade in motor vehicles and motorcycles (division G47-KDBiH 2010), and in a minor extent business entities which are classified according to the main activity in other activities but also perform retail trade activities.

Business entities /legal units that are according to the main activity registered in other activities (outside the division 47), but realize a significant turnover in retail trade. Entrepreneurs are not covered by the survey. 

Data refer to the whole territory of BiH

Data on the retail trade turnover index covers time series starting from January 2006 and data are regularly published on a monthly basis. Data are available as gross indices as well as seasonal and calendar adjusted turnover indices. 

Retail trade turnover index is calculated on the base (2015) year and used in the calculation of the indices from January 2018. RTI are presented as nominal and real index values. EU Regulation (EC) No. 472/2008 prescribes the application of the base 2015 from January 2018 in EU member states.

Data are published as turnover indices and growth rates (in %).

Reference period is a calendar month.

- Law on Statistics of BiH (Official Gazette of BiH No. 26/04 and 42/04), as well as laws on statistics of the entity statistical institutions. Agency for statistics of Bosnia and Herzegovina is responsible for data collection, data processing and data publishing for the state level (BiH level) as well as for implementation of methodology in all three statistical institutions in BiH in a unique way;

- Multi-annual statistical work programmes for BiH (2021 – 2024) and Annual work plans of BiH;

- Strategy for development of statistics of Bosnia and Herzegovina 2030;

-  Methodological guidelines retail trade turnover index for BiH

- Data delivery/exchange between the Entity Statistical Offices (Republic Statistical Office of Republika Srpska and Federal Institute for Statistics of the Federation of BiH) and the Agency for Statistics of BiH is regulated by the Laws on Statistics, as well as an Agreement on the exchange of data between all three statistical institutions;

- Data delivery to external users - state institutions in the country which is regulated by the Law on Statistics and other laws that regulate the work of state institutions (eg. Directorate for Economic Planning BiH; Ministry of Finance of BiH; Central Bank of BiH etc.);

- Statistical Office of the European Union (Eurostat);

- External users – international organizations like UN Statistics Division (UNSD), International Monetary Fund (IMF), World Bank (WB), etc. based on their requests and/or agreements signed;

- Other users (students, academic community, individual users, etc.) in accordance with special procedures defined by the Agency and with the individual agreements signed.

Law has regulated confidentiality of statistical data, and staff conducting statistical survey are obliged, under the same legislation, to protect confidentiality. The Law on Statistics of BiH (Official Gazette of BIH 26/04 and 42/04 - Chapter XI - Articles 23-29) sets forth the principle of confidentiality as one of the main principles. The Agency for Statistics of BiH disseminates statistics in accordance with the statistical principles of the European Statistics Code of Practice, and especially with the principle of statistical confidentiality.

The document titled “Book of Rules on Protection of Statistical Data in the Agency for Statistics” contains the procedure to secure confidentiality during data gathering, processing and dissemination - which includes protocols securing individual data to which access is allowed, rules defining confidential cells in the output tables and procedures for detection and prevention of subsequent disclosures, as well access to micro-data for the survey purposes.

Release calendar for Statistical Press Releases in BiH is published in advance for the entire year and it contains detailed information about all publications planned to be published. In December every year, Agency for statistics of BIH publishes on a website a calendar with accurate dates and time of publication of statistics for the next year (the calendar is published on the website and in .pdf format). Deadline for publishing retail trade turnover index is 28th day of the month for the previous (reference) month (for example, 28.04. for the March as reference month). 

The release calendar of Statistical publications for publicity in BiH for year 2022 is available on following link: https://bhas.gov.ba/data/Dokumenti/Kalendar%20publikovanja/KALENDAR_2022.pdf

All press releases are published in accordance with the defined Release calendar on an exactly specified date at 11 o’clock, on the Agency’s website. If the release is delayed, the relevant information are posted on the website and a new date/time schedule is announced. All publications for users are available in 4 languages, including 3 local languages and English version. Users do not have access to new data prior to their official publication on the AgencyS’s website, nor is possible for them to be granted access to the data earlier. The principle that all users should have equal access to statistical data on an unbiased bases is set out in Article 8, paragraph (2), subparagraph h) and Article 19, paragraph (2) of the Law on Statistics of BiH, and BHAS consistently implements it in practice. 

Retail trade turnover index (RTI) for BiH is disseminated monthly.

https://bhas.gov.ba/data/Publikacije/Saopstenja/2023/STS_01_2022_12_1_EN.pdf

Turnover indices are available as gross indices, calendar and seasonal adjusted for BiH level of choosen classes, groups and total retail trade in BiH, division G47 - KD BiH 2010.

https://bhas.gov.ba/data/Publikacije/Bilteni/2023/NUM_00_2022_TB_1_EN.pdf

https://bhas.gov.ba/Calendar/Category/20

Micro-data are not disseminated and users have no access to them.

Data are transmitted to Eurostat, which also publishes data for Bosnia and Herzegovina on its website.

Development of the Quality Report is in progress and the one will be available on Agency’s website.

BHAS follows the recommendations for quality management and organisation provided in the European Statistics Code of Practice (CoP) and implements the guidelines provided in the European Statistics System Quality Assurance Framework (QAF). More details about quality assurance and all procedures describing the BHAS quality policy are contained in the document: BHAS Quality management policy and mechanisms: https://bhas.gov.ba/Content/Read/92?title=Kvalitet&lang=en

Note: In 2015, the Sector Peer Review for Business Statistics was conducted, which provided an assessment of the RTI survey and proposals for improving its quality.

- International main users: Eurostat, IMF, UN/UNECE, OECD, WB

- National main users: Directorate for Economic Planning of BiH with the Council of Ministers of BiH, Foreign Trade Chamber of BiH, Central Bank of BiH, Ministry of Finance of BiH, other bodies and institutions of the Government

- Other users: business entities – enterprises, banking sector, association of employers, researchers and students, media and general public.

- Internally, these data are used for the National Account statistics for production of the GDP and for comparisons and controls in the Structural Business Statistics and Short-term Business Statistics.

- helps enterprises to conduct the market survey and develop their business strategy

Having in mind the requirements EU Regulation 2019/2152 on European business statistics and Commission Implementing Regulation 2020/1197, as well as the length of time series, all requirements are met. Time series are available from January 2006 for the division G47 by KD BiH 2010.

Monthly data are obtained by using the reporting method, using the paper questionnaire (M KPS TRG 01) and represent the basis for estimating data for the total population. Data are subject to sampling errors, non-sampling errors, data entry and processing errors, and non-response errors. Considering a very high response rate, about 98.2%, overall accuracy is very good. For all reporting units included into the sample, data must be completed before data compilation (reporting units are re-called or visited and, if even after re-calling it is not possible to obtain data from them, imputation shall be applied).

There is no estimation available, nor the sampling error has been assessed because it is very difficult to calculate it. RTI indices were calculated using a combined method of full coverage (large and medium-size enterprises) and stratified random sample (small enterprises, annual turnover less than 1 million euros).

Unit non-response rate: The total non-response rate is approx. 1.8%. In case of unit non-response, the following imputation methods are used: based on data from the previous month, the same month of the previous year or based on data on the turnover of the most similar units (same stratum). In case of non-respons for individual items, the reporting units are contacted by phone, until the requested information is obtained. Further verification of the submitted data is performed by applying logical and mathematical controls during and after entering data into the STS IT application.  

Data collection is done on monthly basis. Reporting units have deadline for data delivery 10^th in the month for the previous (reference) month. Eventually, few more days are available for re-calling of reporting units, which did not delivered the report in order to get the data for all reporting units. Deadline for data publishing is T+28 days (for the level of BiH) for the Preliminary results.  Preliminary results shall become final on the date of publication of the press release for the next month.

There is no discrepancy between announced and real date of publishing (according to the Release calendar).  All 12 press releases of the monthly survey of R are published on the date of publication as foreseen in the Release Calendar

Considering that the RTI results are published in accordance with the EU Regulation 2019/2152 on European business statistics and Commission Implementing Regulation 2020/1197, the results are comparable with those of other countries (EU primarily) which apply this Regulation, methodology and relevant classifications. 

Available historical data series of retail trade data have been recalculated for the period 2006-2012 using the "matched sampling" and "overlapping" (overlapping period) methods in order to avoid break in series and maintain the consistency and continuity of the available RTI data series from the January of 2006. The monthly RTI survey conducted by the entity statistical offices until the end of 2012, was partially in line with the requirements of EU STS regulations. Since January 2013, a unique methodology has been applied in all three statistical institutions in BiH, which is fully compliant with the requirements of EU Regulation 2019/2152 on European business statistics and Commission Implementing Regulation 2020/1197. In 2013, all RTI series calculated using NACE Rev.1.1. were recalculated to NACE Rev.2 using the macro approach (at the macro level). Since 2018, all RTI series calculated on the base year 2010 (2010=100) have been recalculated to the new base year (2015=100) to ensure comparability over time, and are expressed in real and nominal values. EU Regulation (EC) No. 472/2008 prescribes the application of the base 2015 from January 2018 in EU member states.

A reference survey on monthly retail trade is fully harmonized with the requirements of EU Regulation 2019/2152 on European business statistics and Commission Implementing Regulation 2020/1197. Monthly retail trade surveys and quarterly statistics of distributive trade are mutually consistent and there is no significant deviation in the trend of the turnover indices. Approximately it is possible to compare the data of this survey with the annual data of the Structural Business Statistics and the National Accounts, and in most cases the data are consistent.

RTI are fully coherent on different aggregation level by NACE activity (class, group, special aggregates and total division G47) for the observed data set. RTI for BiH is also adjusted (seasonally adjusted) using TRAMO/SEATS method, which is based on the ARIMA model. Adjustments are made for total retail trade, group level, as well as special aggregates. Seasonally and calendar adjusted data are compared with the original data and they show mutual coherence. 

Data on monthly retail trade survey are collected by using paper questionnaires, which requires significant funding and human resources. Data are collected by three statistical institutions: Federal Institute of Statistics of FBIH for the territory of Federation of BIH, Republika Srpska Institute of Statistics for the territory of Republika Srpska and the Agency for Statistics of BiH for the Brčko District of BiH. Approximately, 3 people are involved in the data collection process and data compilation process on a monthly basis. In addition, one IT expert per institution is responsible for the development and maintenance of IT application (20% of his working time). All three statistical institutions have very high costs of printing the questionnaires, postal and telephone costs. The response burden is not very high, with approximately 5 minutes for fulfilling the questionnaires per respondent. 

There is no clearly defined data revision policy, except in the case of an error when the published revised data are marked as "corrected data ". Then the explanation is given to all users about the reason for the data correction/revision. The corrected press release is published on the Agency's website. After the publication of the corrected data on the Agency's website, data are also sent to Eurostat which means that the same revision policy has been used nationally and for sending the data to Eurostat. 

If new statistical standards and concepts are introduced, changes occur in the existing methodology and it is necessary to revise the data to ensure consistency and comparability of data from earlier historical series and new series of data. About these changes of data and reasons for changes, users are informed in regular quarterly releases and other publications as well as on the BHAS website.

The Monthly Retail Trade Survey (questioonaire M KPS TRG-1) is the main source of data for the calculation of RTI, which is conducted in the traditional way by sending paper questionnaires on the field by post. The source of data for filling in the questionnaire is the bookkeeping or other relevant documentation of the enterprise. The main observed variable is the monthly turnover of a business entity registered within retail trade activities, without VAT. In accordance with EU- STS regulations VAT is calculated and shown separately. Data are collected at the level of the business entity. If the enterprise has business units in other entity and/or Brčko District, it is necessary to breakdown turnover related to these units.

Frequency of data collection is monthly, with the deadline for data delivery 10^th in the month for the previous reference month. 

The RTI survey is conducted by  e-mail and paper questionnaires , which means that the business entities submit the filled questionnaire (within a certain deadline) to cantonal statistical office of FIS, regional statistical office of the RSIS, or to the branch office of the Agency for Statistics in BD BiH. At the beginning of the year sets of questionnaires – M KPS TRG 01 (12 sets) are sent to all reporting units. 

Data entry and validation are done by the authorized entity statistical offices for the territories of the entities, and for the Brčko District of BiH it is performed by the Branch office of the Agency for Statistics of BiH. Logical controls (large increase or decrease of turnover) and detecting of outliers are performed in the process of submitting and entering data into the STS IT application Entity institutes submit to the BHAS, in the prescribed format, all data necessary for the compilation of RTI for the level of BiH. Data cross-checking controls are applied, and in case of observed “suspicious” data, the data are checked and, if necessary, the authorized institutions perform additional control of data by contacting reporting units by phone or visiting reporting units. This is a standard procedure for a long period of time, enabling to obtain data of good quality and verified data.  Data validation is done automatically by applying predefined data controls through STS IT applications. The validation process includes: cross-checking (cross-cuting), comparison with previous data, etc.  Afterwards, indices are produced and results are cross-checked with historical data.   All verifications are performed through the STS IT application and manually (in Excel). For the data transmission to Eurostat, a special SDMX-ML format has been created that satisfies the structure of the data transmission format. No validation controls and checking are applied to this file, because the national validation rules have already been applied.

The RTI in constant prices are obtained by deflating turnover at current prices with appropriate consumer price indices (CPI). After that, aggregation at higher levels of activity is performed and volume RTI are calculated.

Seasonal adjustment of gross turnover has been done by using an automated model through software Demetra v2.2 and TRAMO/SEATS methods (regression method), which is based on the ARIMA models. Indices are published as gross/unadjusted, seasonal adjusted (SA) and calendar adjusted (WDA).  Calendar adjusted data compared to the same month of the previous year (t-12) are presented and interpreted in a calendar adjusted form, while seasonally adjusted data which are compared with data from the previous month are presented and interpreted in seasonally adjusted form.

No comment