Catering trades

Statistical Office of the Republic of Serbia (SORS)

Domestic Trade, Catering and Tourism Statistics Division 

Valentina Ilić

Advisor

Milana Rakica 5, Belgrade

  valentina.ilic@stat.gov.rs

+38111 6964 221, ext. 331

+381 11 2411 922

Quarterly surveys on catering trade provide data necessary for monitoring and analysis of economic trends, volume and structure of turnover in catering.

In order to achieve these goals, the following data are collected by surveys:

• on the turnover of business entities in the observed quarter by month

• turnover generated by catering activities by statistical territorial units (NSTJ 2);

• the structure of turnover generated from catering activity by types of catering services;

List of nomenclatures and classifications used in the survey:

• Classification of Activities - CA ("Official Gazette of the Republic of Serbia", No. 104/2009)

• Nomenclature of statistical territorial units ("Official Gazette of RS", No. 109/09 and 46/10) (Classification and nomenclature are available on the website of the Statistical Office of the Republic of Serbia: www.stat.gov.rs)

The coverage of the survey is a set of enterprises (legal persons) and entrepreneurs whose main activity classified into section Accommodation and food service activities, divisions Accommodation and Food and beverage service activities (divisions 55 and 56 of NACE Rev.2.).

Catering trade is an activity that consists of providing catering services, that is, accommodation, food and drink services, as well as other services that are usually provided in catering (transport of guests and luggage, tourist services, tobacco sales and memorabilia etc.)

Catering business unit is a catering facility that in a business, construction and functional aspect constitutes a complete entity or which within the wider construction has separate space and necessary business functionality for performing catering activities.

An enterprise (company) is a legal entity established by legal entities and / or physical persons for the purpose of performing a profitable activity.

Entrepreneur (unincorporated enterprise) is a registered physical person that, in order to earn profits in the form of a profession performs all legally permissible activities.                           

The turnover of a business entity is the accounting value (invoiced) of the income from catering and other (secondary) activities carried out by the business entity.

Turnover from catering activities represents the book value of total turnover based on performed catering services (accommodation, food, beverage), as well as other services that are usually provided in catering trade (transport of guests and luggage, tourist services, sale of tobacco and memorabilia, etc.).

Value Added Tax (VAT) is a general consumption tax that is calculated and paid for the delivery of goods and the provision of services, at all stages of the production and trade of goods and services, as well as on the import of goods, unless otherwise provided by law.

Units of statistical observation are enterprises with main activity classified under section I (Accommodation and food service activities).

The basic set of legal entities and entrepreneurs (target population) includes all economically active business entities whose principal activity is in the Catering trade (divisions 55 and 56 of CA), activities "Accommodation" and “Food and beverage service activities" (divisions 55 and 56 of CA).

Legal entities (enterprises)

Sampling frame is based on Statistical Business Register (SBR), which includes about 3920 enterprises involved in catering activities that have reported annual financial statements for 2020. The smallest enterprises according to reported annual financial statements were excluded from the sampling frame. Sampling frame included all the enterprises with an annual turnover greater than 2.5 million RSD. Excluded enterprises make up less than 0.5% of total turnover. The sampling frame included about 2170 enterprises.

Unincorporated enterprises

Sampling frame is based on Statistical Business Register (SBR), which includes about 13750 entrepreneurs involved in catering activities that have reported annual financial statements for 2020. Cut-off of smallest entrepreneurs were performed, excluded entrepreneurs make up less than 0.5% of total turnover. The sampling frame included about 12430 entrepreneurs.

The data are available for the level of the Republic of Serbia and statistical territorial units (NSTU 2).

Starting from 1999 the Statistical Office of the Republic of Serbia has not at disposal and may not provide available certain data relative to AP Kosovo and Metohija and therefore these data are not included in the coverage for the Republic of Serbia (total).

Index series of total turnover in catering trade are comparable and can be considered continuous.

In accordance with the Eurostat Regulation for short-term indicators, from 2020, the indices are calculated in relation to the base year, 2015.

Monthly turnover indices in the catering trade are published in relation to “the same month of the previous year”, “the previous month”, “the previous year's average” and “the same period of the previous year”.

Also, annual indices are calculated and published.

Turnover data is collected in RSD thousand.

Indicators and absolute values are published annually, and only indicators are published on a monthly basis.

Data is collected quarterly.

The reference period is the calendar quarter. 

The Surveys are conducted according to the Law on Official Statistics ("Official Gazette of RS", No. 104/09), Programme of the Official Statistics over the period 2016 - 2020 ("Official Gazette of RS", No. 55/2015, as of 25.06.2015), as well as regulations on the introduction of the Official Statistics Plan.

The results of the survey are used to monitor and analyse the volume, dynamics and structure of turnover in catering trade, to meet international statistical obligations, as well as to plan and analyse economic policy measures in the area of catering trade.

The obligation to protect the individual data of the reporting units is based on article 3 of the provision on the protection of data providers, as well as articles 44, 45, 46, 47, 48 and 49 of the confidentiality provision – Law on Official Statistics.By the Law on Official Statistics

When processing confidential data for user’s purposes, data protection must be such that individual data cannot be identified at any level of aggregated data. Individual data is treated as confidential and can only be given to the owner of such data. Individual data is an official secret, used exclusively for statistical purposes and cannot be published or made available to users.

Release Calendar is publicly accessible on SORS website, providing the information on the exact date of statistical releases and publications’ issuing. The schedule of statistical release dates is announced in advance (at the end of the year for the whole coming year).

Release calendar

The dissemination policy of SORS is based on the provisions of the Law on Official Statistics ("Official Gazette of the Republic of Serbia" No. 104/2009), the Strategy of the Development of Information and Dissemination in SORS and the Rulebook on the manner and procedure of data provision produced by SORS. Official statistics data is available to all users at the same time and in the same way. SORS keeps an up-to-date dissemination calendar publicly available. All deviations from the deadlines set in the calendar are announced and explained publicly. Competent producers of official statistical data develop and maintain publicly available databases that are the result of official statistics. SORS is obliged to provide expert interpretation and assessment of produced and disseminated data. All information about sources and methodology used are available to the general public. All data or all official statistics information can be used only if the source is specified. At the request of the users and on their behalf, statistics can provide data and information obtained by special processing.

Dissemination policy is available on SORS website.

The data are published in monthly and annual periodicity.

Not provided.

Survey results are, with methodological explanations, issued in “Monthly statistical bulletin” and on the Internet presentation of SORS (www.stat.gov.rs).

 „Statistical Yearbook of the Republic of Serbia“– is complex annual publication, involving all final data and series of the most significant indicators from various divisions of economic and social situation in the country.

„Statistical Pocketbook of the Republic of Serbia“– the publication that offers basic statistical data on national social and economic development.

Data on catering trade (monthly and annual indicators) are available in the statistical database within the division of Tourism and catering trade. 

The protection and security of individual data on physical and legal persons is carried out according to strictly defined procedure - Access to microdata.
The Statistical Office of the Republic of Serbia (SORS), as the responsible producer of official statistics, provides the use of anonymised microdata based on the submitted request. The request can be submitted by accredited scientific research organizations (institutes, faculties, universities and centres of exceptional values); researchers and PhD students, as well as institutions that implement a special project financed by national or international research programs.

More detailed information on microdata access is available on SORS website.

http://www.stat.gov.rs/korisnicka-podrska/micropodaci/

On user’s request, SORS can provide data and information obtained by special processing.

http://www.stat.gov.rs/korisnicka-podrska/

Methodological explanations and statistical forms are available on the website of SORS:

Methodological materials and documentation

In monthly and annual publications.

Quality management system

SORS has accepted the European Statistics Code of Practice. Accordingly, SORS applies the following principles: relevance, accuracy and reliability, timeliness and compliance of the announced deadlines for publication, availability and comprehensibility, coherence and comparability in accordance with the Law on Official Statistics and other relevant international and national laws.

The quality management system of the SORS is based on the Code of Practice of European Statistics and is fully adapted to the statistical needs because it systematically improves the quality of statistical processes, final results, i.e. the data, as well as providing services to users.

The Quality Policy document is available on SORS website:

SORS has accepted the European Statistics Code of Practice. Accordingly, SORS applies the following principles: relevance, accuracy and reliability, timeliness and compliance of the announced deadlines for publication, availability and comprehensibility, coherence and comparability in accordance with the Law on Official Statistics ("Official Gazette of the Republic of Serbia", No. 104/09), and other relevant international and national laws.

The quality management system of the SORS is based on the Code of Practice of European Statistics and is fully adapted to the statistical needs because it systematically improves the quality of statistical processes, final results, i.e. the data, as well as providing services to users.

The Quality Policy document is available on SORS website:

The results of the survey are used to monitor and analyse the volume, dynamics and structure of turnover in catering industry; to meet international statistical obligations, as well as to plan and analyse economic policy measures in the area of ​​catering.

The main users of the data are government bodies (Government, ministries), chamber of commerce, business entities, economic analysts, media representatives, scientific researchers, students, internal users (national accounts statistics, Department for rapid and complex reporting and support to public policies), international users.

User satisfaction survey is measured through the "Survey on Users’ Satisfaction of SORS", conducted in October 2021

There is no separate survey on user’s satisfaction related to the Survey on catering trade.

All variables envisaged by the statistical survey are collected on the basis of the Decision on the Official Statistics Program in the period from 2016 to 2020 and the Regulation on the establishment of the Plan of Official Statistics.

The main sources of errors in this survey are of sampling and non sampling nature.

The survey is based on random sample. Sampling frame is constructed using enterprise data from the Statistical Business Register (SBR).

The main sources of errors in this survey are of sampling and non sampling nature.

The survey is based on random sample. Sampling frame is constructed using enterprise data from the Statistical Business Register (SBR).

The sample design is such that the estimates for the main domains are of satisfactory precision.

The following non-sampling errors exist in this survey:

• coverage errors that are a due to not completely updated SBR and existing time lag in registering the changes of enterprise characteristics;
• errors that are a consequence of cut-off sampling, smallest enterprises are excluded from the sampling frame;
• measurement and non-response errors are inevitable, but the process of data collection and data entry are controlled to reduce these errors.

The general assessment is that the type and design of survey and data collection methods ensure sufficient overall accuracy 

Legal entities (enterprises)

Sampling error is estimated for the quarterly turnover in catering and presented by the corresponding coefficients of variation for the estimation domains. Sampling weights used in estimation are corrected for non-response. For the total turnover, estimates of the coefficients of variation are in the interval of 4.35 – 4.94%.

In the Annex referring to Accuracy is a table with quarterly estimates of coefficients of variation for the turnover in catering.

Unincorporated enterprises

Sampling error is estimated for the quarterly turnover in catering and presented by the corresponding coefficients of variation for the estimation domains. Sampling weights used in estimation are corrected for non-response. For the total turnover, estimates of the coefficients of variation are in the interval of 4.08 – 5.28%.

In the Annex referring to Accuracy is a table with quarterly estimates of coefficients of variation for the turnover in catering.

Non-sampling errors can arise in all stages of survey activities. Non-sampling errors can arise due to: coverage errors, non-response, processing, etc.

Under-coverage error is not estimated, but it is supposed that it does not significantly influence the results. It appears, first of all, due to inadequately updated SBR that is used for constructing the sample selection frame.

The over-coverage and non-response errors (or the rate of response) are computed using the information on units’ response that is classified in 8 categories:

1. submitted report, active;

2. active, but rejects to submit the report;

3. not found at the address (questionnaire not delivered);

4. changed address;

5. closed;

6. does not work temporarily;

7. out of the survey coverage (does not perform the referent activity);

8. other reasons (e.g. unknown reasons of non-response).

Legal entities (enterprises)

Over-coverage units, determined not to belong to the target universe for the survey, are those for which the coded information on response is 5, 6 or 7. The average rate of over-coverage is 8.41% in 2022. The main reasons for over-coverage are ‘temporary not working’ and ‘outside the scope of the survey’.

Non-response units are in-scope units for which data were not collected. Non-response units are those for which the response code is 2, 3, 4 or 8. The average unit non-response rate in 2022 is 14.97%. Size-weighted unit non-response rate in 2022 on the level of Republic of Serbia on average is 10.63%; the size-weight is the product of design sample weight and a size measure, reported annual turnover from financial statements.

Unincorporated enterprises

Over-coverage units, determined not to belong to the target universe for the survey, are those for which the coded information on response is 5, 6, or 7. The average rate of over-coverage is 13.89% in 2021. The main reasons for over-coverage are ‘closed, extinguished’ and ‘temporary not working’.

Non-response units are in-scope units for which data were not collected. Non-response units are those for which the response code is 2, 3, 4 or 8. The average unit non-response rate in 2021 is 12.22%. Size-weighted unit non-response rate in 2021 on the level of Republic of Serbia on average is 10.64%, the size-weight is the product of design sample weight and a size measure, reported annual turnover from financial statements.

Over-coverage units, determined not to belong to the target universe for the survey, are those for which the coded information on response is 5, 6, or 7. The average rate of over-coverage is 12.31% in 2022. The main reasons for over-coverage are ‘closed, extinguished’ and ‘temporary not working’.

Non-response units are in-scope units for which data were not collected. Non-response units are those for which the response code is 2, 3, 4 or 8. The average unit non-response rate in 2022 is 10.87%. Size-weighted unit non-response rate in 2022 on the level of Republic of Serbia on average is 7.40%, the size-weight is the product of design sample weight and a size measure, reported annual turnover from financial statements.

In order to reduce non-sampling errors caused by human errors, the following measures are undertaken: collected data are entered in the PC application that represents the so-called "controlled entry", written and e-mail reminders, telephone contacts with the reporting units. During data collection and data entry phase, the program does not allow the entry of incorrect data, it's checked whether the questionnaires are filled out completely. The next step is the release of the program for computation-logical control. Further steps in data editing are based on the analysis of statistical experts and resulting with correction of discovered errors. If necessary, reporting unit is contacted in order to get correct data. Finally, data validation is done during analysis of aggregates, horizontal logical dependences, vertical relations, etc.

In the Annex referring to Accuracy are tables with quarterly estimates of unweighted over-coverage and non-response rates.

The deadlines for the reporting units are determined on the basis of the annual Plan of statistical surveys.

Final data of the quarterly survey are published 60 days after the end of the observed period (t+60).

Deadlines are respected and data are published and delivered on time, according to the pre-announced Release calendar.

The same statistical concepts are applied for the entire territory.

Time series of the presented indicators are comparable over time.

There are no major discrepancies between available data from administrative sources and survey results.

The data are internally coherent. In order to check internal coherence, comparison is made between the data from the previous month and the data of the reference month, as well as the comparison of current data with data from the same period of the previous year.

Information on cost and burden is not systematically collected.

 General Revision Policy:

http://www.stat.gov.rs/media/2283/opsta-politika-revizije-rzs-1.pdf

Current revisions - all monthly published indices in the area of the catering industry are treated as the previous ones, which means that certain corrections can be made based on information retrieved subsequently.

Legal entities

For this statistical survey, the sampling frame is based on the data of the Statistical Business Register, state of 31st of December 2021. Stratification of the sampling frame is according to economic activity (divisions 55 and 56 of NACE Rev.2.), NUTS2 territorial classes (Region of Belgrade, Region of Sumadija and West Serbia, Region of South and East Serbia, Region of Vojvodina) and the amount of annual turnover.

Within each class defined by cross classifying economic activity and territorial classes, enterprises are further stratified into 2 classes according to the annual turnover: larger and smaller. Units with largest turnover were census units. A random sample is selected from strata marked as ‘smaller’.

Allocation of sample was done using the Bethel algorithm (Bethel, J. “Sample allocation in multivariate surveys”, Survey methodology, 15, 1989: 47–57). Turnover was used as an auxiliary information. This way a sample of 452 units was allocated.

Sample of enterprises was selected using SORS system of coordination that is based on the SAMU system (SAMU, 2003). In this system every unit has it’s unique permanent random number from uniform (0,1) distribution. This number is used in sequential simple random sampling inside each stratum. The starting point for selection was 0.

Unincorporated enterprises

For this statistical survey, the sampling frame is based on the data of the Statistical Business Register, state of 31st of December 2021. Stratification of the sampling frame is according to NUTS2 territorial classes (Region of Belgrade, Region of Sumadija and West Serbia, Region of South and East Serbia, Region of Vojvodina) and the amount of annual turnover.

Within each class defined by territorial classes, entrepreneurs are further stratified into 4 classes according to the annual turnover. Units with the largest turnover were census units.

Allocation of sample was done using the Bethel algorithm (Bethel, J. “Sample allocation in multivariate surveys”, Survey methodology, 15, 1989: 47–57). Turnover was used as an auxiliary information. This way a sample of 402 units was allocated.

Sample of entrepreneurs was selected using SORS system of coordination that is based on the SAMU system (SAMU, 2003). In this system every unit has its unique permanent random number from uniform (0,1) distribution. This number is used in sequential simple random sampling inside each stratum. The starting point for selection was 0.

Quarterly data collection for year t; for the first quarter to 30.04, for the second quarter to 31.07, for the third quarter to 31.10. and for the fourth quarter to 09.02. of the year t + 1.

Type of the survey – the survey is conducted on sample of unincorporated enterprises and legal entities providing catering trade services.

Methods of data collecting – reporting units can deliver completed questionnaires by post, mail, fax or web application.

Questionnaire ‒ https://www.stat.gov.rs/istrazivanja/methodology-and-documents/?a=22&s=0

Individual data (micro level) is controlled to ensure the quality of data. At the same time, by collecting, registering and encrypting, statisticians visually check the data to see any missing, incorrect or inconsistent questionnaires or answers, and, if necessary, contact the reporting unit.

Afterwards, check is performed during the data entry and during processing. Data validation rules apply when each questionnaire is loaded into the database; Logical connections between values, detection of errors in calculation, and missing values ​​are checked. Errors are corrected by contacting the reporting units and / or colleagues in the regional organizational units of SORS. Data check is performed in accordance with the defined criteria of logical and computer control within the IST application (statistical information system fully developed in SORS) and correction of errors is done.

Statistical results (aggregated data) for the reference quarter and are compared with the results of the previous quarter (month) and the corresponding quarter (month) of the previous year, at each level of aggregation.

Estimates of total values and their standard errors are calculated by using the Horvitz-Thompson estimates in accordance with the standard procedure for stratified simple random sample. This means that the estimates of total data are calculated by summing the weighted values from the sample. The sampling weight is corrected for unit non-response.

Turnover indices are calculated as free indices (relative value). Indices are calculated directly from the data (obtained estimates).

Turnover indices at constant prices are obtained by deflating the index at current prices with the corresponding indices of prices of catering services.

Not applied.