Statistical Service of Cyprus (Cystat)

Wholesale and Retail Trade Statistics Unit

Michael Karaoli str., 1444 Nicosia, Cyprus

Wholesale and Retail Trade; Repair of Motor Vehicles and Motorcycles

NACE Rev. 2.

The indicators in this sector cover economic activities listed in section G of NACE (G45, G46, G47).

The purpose of the Turnover Value Indices is to monitor short-term developments classified under Divisions 45, 46 and 47 of the Statistical Classification of Economic Activities of the European Union NACE Rev.2. Turnover comprises the total amounts invoiced by an enterprise during the reference period and this corresponds to the market sales of goods and services, excluding VAT but including other duties and taxes on the goods.

There are no discrepancies with the definition of variables laid down in the Commission Implementing Regulation 2020/1197.

Enterprise.

The frame is the Business Register (as for SBS) and numbers around 16.900 enterprises. Enterprises classified in NACE Rev. 2 Division 45 numbers 3200, in Division 46 4500 and in Division 47 9200.

Republic of Cyprus

Data are available as from 2000.

Base year 2015.

Index (2015=100).

Quarter (for Divisions 45 and 46).

Month (for Division 47).

Article 3 of the National Official Statistics Law, No. 25(I) of 2021 defines the functions of the Statistical Service of Cyprus regarding the production and dissemination of official statistics. Moreover, Article 13, explicitly stipulates the mandate for data collection and introduces a mandatory response to statistical enquiries by stipulating the obligation of respondents to reply to surveys and provide the data required. This relates not only to national but also to European statistics which, by virtue of Article 8 of the said Law, are incorporated in the annual and multiannual programmes of work without any further procedure. Link to the Statistics Law No. 25(I) of 2021: https://www.cystat.gov.cy/en/StaticPage?id=1074  

The legal basis for the short-term statistics is the European Business Statistics (EBS) Regulation (EU) 2019/2152 on 27 November 2019, followed by the Commission Implementing Regulation 2020/1197 laying down technical specifications and arrangements pursuant to the mentioned EBS Regulation (General Implementing Act). The former legal basis for the STS indicators is the Council Regulation No 1165/98 of 19 May 1998 concerning short-term statistics and subsequent amending regulations.

Apart from Eurostat, the index is not transmitted to any other international organisations.

Official statistics are released in accordance to all confidentiality provisions of the following:

• National Official Statistics Law No. 25(I) of 2021 (especially Article 16 on statistical confidentiality).
• Regulation (EC) No 223/2009 of the European Parliament and of the Council of 11 March 2009 on European statistics and its later amendments (especially Chapter 5 on statistical confidentiality).
• European Statistics Code of Practice (especially Principle 5 on statistical confidentiality).
• CYSTAT's Code of Practice for the Collection, Publication and Storage of Statistical Data.

Links to all of the above documents:

• Statistics Law No. 25(I) of 2021: 

https://www.cystat.gov.cy/en/StaticPage?id=1074  

• Regulation (EC) No 223/2009 on European statistics (consolidated text):

 http://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:02009R0223-20150608&qid=1504858409240&from=EN

• European Statistics Code of Practice:

 http://ec.europa.eu/eurostat/web/products-manuals-and-guidelines/-/KS-32-11-955

• Code of Practice for the Collection, Publication and Storage of Statistical Data: 

https://www.cystat.gov.cy/en/StaticPage?id=1066

No data is considered confidential at the level published. The treatment of confidential data is regulated by CYSTAT's Code of Practice for the Collection, Publication and Storage of Statistical Data.  

The link is as follows: https://www.cystat.gov.cy/en/StaticPage?id=1066

In the framework of its mission, CYSTAT provides high-quality statistical information, through the web portal and social media, with the use of statistical products such as announcements, interactive tables, predefined tables, metadata, infographics and publications. The principles and the legal framework governing the dissemination of official statistical data are defined and explained in the document “Dissemination Policy”. The means of dissemination, the main statistical products and the services provided to the users, are also presented. Additionally, the document describes the procedures for data revision and error treatment. The link is as follows:Dissemination Policy of the Statistical Service of Cyprus (cystat.gov.cy)

An annual release calendar is prepared and forwarded to Eurostat. At national level, a release calendar with preliminary dates for the next four months is published at the new web portal of the Statistical Service. Announcements are confirmed on the Friday preceding their release. Notifications about the dissemination of statistics are published in the release calendar, which is available on the web portal. The annual release calendar, announced during the 4th quarter of the year, includes provisional dates of publication for the following year, which are finalised the week before publication.

The release calendar published at national level can be found at: https://www.cystat.gov.cy/en/AnnouncementList

As provided in article 4(1) of the Official Statistics Law (Law No. 25(I)/2021) regarding the principle of impartiality, statistics are disseminated in such a way that all users have equal and simultaneous access to the data. Also, according to the Dissemination and Pricing Policy of the Statistical Service of Cyprus (section 2.3) CYSTAT΄s main channel for dissemination of statistics is the website, which offers the same conditions to everyone and is updated at the same time every working day (12:00 noon). Privileged pre-released access (of no more than 1 day in advance) has been granted to a few selected users for specific statistics. These are specified in the Dissemination Policy (section 2.3).

In addition to the annual release calendar, users are informed of the various statistical releases through the “Alert” service provided by CYSTAT.

Link to the Dissemination and Pricing Policy of the Statistical Service of Cyprus can be found at: https://www.cystat.gov.cy/en/StaticPage?id=1064.

Quarterly (for Divisions 45 and 46).

Monthly (for Division 47).

There is a regular monthly news release. The news release is accompanied by a set of Predefined Tables available in Excel format and is disseminated on a monthly basis on the new web portal of the Statistical Service of Cyprus. The Predefined Tables include data up to 2022. Data from 2023 onwards, are available only in the CYSTAT-DB Online Database.

No available.

CYSTAT-DB is the online database of the Statistical Service of Cyprus. It gives users the ability to produce the desired table, to format the presentation, to edit and make calculations and to save it in any form available. Additionally, requests can be saved and used at a later stage to get the updated table with the latest available statistics. It is an interactive tool, providing the possibility to create customized tables for wholesale retail trade statistics indices. CYSTAT-DB can be accessed from the home page or alternatively from the pages of statistical sub-themes.

Data from 2023 onwards, are available only in the CYSTAT-DB Online Database at: PxWeb - Select table (cystat.gov.cy).

There is no microdata access to outside users.

Under the provisions of the Statistics Law, CYSTAT may release microdata for the sole use of scientific research. Applicants have to submit the request form "APPLICATION FOR DATA FOR RESEARCH PURPOSES" giving thorough information on the project for which micro-data are needed.The application is evaluated by CYSTAT’s Confidentiality Committee and if the application is approved, a charge is fixed according to the volume and time consumed for preparation of the data. Micro-data may then be released after an anonymisation process which ensures no direct identification of the statistical units but, at the same time, ensures usability of the data.

The link for the application is: https://www.cystat.gov.cy/en/DataRequestContactForm?fid=7

Indices are transmitted to Eurostat and are used for the calculation of European aggregates.

A methodological note is available on Cystat web portal.

Not available.

The quality of statistics in CYSTAT is managed in the framework of the European Statistics Code of Practice which sets the standards for developing, producing and disseminating European Statistics as well as the ESS Quality Assurance Framework (QAF). CYSTAT endorses the Quality Declaration of the European Statistical System. In addition, CYSTAT is guided by the requirements provided for in Article 11 of the Statistics Law No. 25(I) of 2021 as well as Article 12 of Regulation (EC) No 223/2009 on European statistics, which sets out the quality criteria to be applied in the development, production and dissemination of European statistics.

Links to all of the above documents:

• European Statistics Code of Practice:

 http://ec.europa.eu/eurostat/web/products-manuals-and-guidelines/-/KS-32-11-955

• ESS Quality Assurance Framework (QAF): 

http://ec.europa.eu/eurostat/documents/64157/4392716/ESS-QAF-V1-2final.pdf/bbf5970c-1adf-46c8-afc3-58ce177a0646

• Quality Declaration of the European Statistical System: 

http://ec.europa.eu/eurostat/documents/4031688/8188985/KS0217428ENN_corr.pdf/116f7c85-cd3e-4bff-b695-4a8e71385fd4

• Statistics Law No. 25(I) of 2021: 

https://www.cystat.gov.cy/en/StaticPage?id=1074

• Regulation (EC) No 223/2009 on European statistics (consolidated text):

 http://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:02009R0223-20150608&qid=1504858409240&from=EN

The quality of statistics is assessed according to the following quality criteria: relevance, accuracy, timeliness, punctuality, accessibility and clarity, coherence and comparability. The quality indicators are assessed taking into account Eurostat defined methodology and recommendations. On the basis of the above criteria, the indicator is assessed as being of good quality.

Eurostat, Ministry of Finance, the Central Bank, economic analysts, enterprises from various economic domains, industrial federations, media, researchers, national accounts.

A user satisfaction survey is carried out on an annual basis since 2008 (with the exception of 2010, 2013 and 2020) but is not specific to short-term indicators. It does not allow for adequate conclusions to be made on this specific indicator. The results of the surveys are available on CYSTAT’s web portal at the link attached below. Overall, there is a high level of satisfaction of the users of statistical data published by CYSTAT.

The results of Cystat's user satisfaction survey can be found at:https://www.cystat.gov.cy/en/StaticPage?id=1144

The data are transmitted to Eurostat at the level of detail required by the Regulation.

The Index is based on a sample survey, so errors from sampling are likely to occur. Coverage errors, measurement errors, non-response errors, processing errors are considered to be small but nevertheless actions are undertaken to reduce these different types of errors as much as possible. 

The sampling error is estimated for the levels of the main components (turnover) and is expressed by the coefficient of variation, based on various assumptions and simplifications according to the “Monographs of official statistics: Variance estimation methods in the European Union, 2002 edition” issued by Eurostat.The CV's are presented in %. For the reference year 2022, the twelve monthly CV's for retail trade turnover (value) (G47) based on the availability of the new base year data (2015=100) are summarised as follows: Jan (1,42), Feb (1,44), Mar (1,25), Apr (1,42), May (1,33), June (1,33), July (1,27), Aug (1,31), Sep (1,29), Oct (1,34), Nov (1,29), Dec (1,46). 

The non-sampling error is not quantified, but is considered to be small. Cystat tries to reduce non-sampling error through continuous methodological improvements and survey process improvements. In particular,

• The Business Register is of fundamental importance to the compilation of the STS indices. The register is updated every year from administrative sources. Allowing coordination between the various units within Cystat, the Business Register is being updated with new, additional or amended information for the enterprises (e.g. change of contact details, employment size, economic activity codes) since the frame information is being checked to see whether it is up to date.
• The personnel working at the collection stage is well experienced and properly guided. At the end of the year the interviewer confirms the total value of turnover for the year ending. Moreover, each month the enterprises are requested to report the turnover of the previous month in order to confirm the quality of the data provided. Furthermore, comparison of the enterprises' data is being made with the annual data provided for the SBS survey.
• The respondents are well informed about the concepts and the items that are generally to be included/excluded.
• To minimise the respondent’s burden as much as possible, the questionnaire is designed to be clear and simple. The data collection is made using the means that each enterprise prefers (fax, telephone, e-mail or personal interview) in order to reduce non-response. The response rate of the first release to Eurostat (at t+30 days) is around 75% in terms of turnover value for NACE Rev. 2 Division 47 and for Divisions 45 and 46 (at t+60 days) is around 80% in terms of turnover value. The non response rate is due to non availability of data by some enterprises. Enterprises that do not have final data for the month in question, provide quarterly data after the end of the reference quarter. Usually, missing data refer to small enterprises with limited impact on final results, while for non-responding enterprises with significant effect, estimation is being made using the enterprises' records for previous months. There are many ways of trying to encourage response and minimise refusals, including reminders to the non responding units before resorting to the enforcement measures laid down in national legislation.
• Many checks are carried out at micro level. Responses are compared to the response of previous months’ turnover values, as well as last year’s corresponding month. Inconsistencies or large deviations are checked. Also during the data editing process, the  value entered is being checked twice.
• To ensure the quality of the time series, comparative analyses are made with the previous years’ results. If inconsistencies are detected, the data are verified at micro level again by using the raw data of the questionnaire or by contacting the enterprise for explanations and confirmation of the data.
• Index results are compared to annual SBS results and any significant deviations are examined further.

Provisional data flagged as free are disseminated to Eurostat 30 days after the end of the reference month for NACE Rev. 2 Division 47. For Divisions 45 and 46, provisional data flagged as confidential are disseminated to Eurostat 60 days after the end of the reference quarter. The final results for Divisions 45 and 46 are published two months and twenty two days after the end of the reference quarter.

Both Eurostat and national deadlines are respected. All releases are delivered on time, based on the scheduled release dates.

It is possible to compare the national index with that of other European countries, as full compliance with the definitions of the variables laid down in the EBSR is achieved.The EBS Regulation and the EBS methodological guidelines are applied.

Indices are comparable over time. When significant changes are introduced (e.g. change of classification, base year or methodology), historical time series are recalculated as far back as it is reasonably possible. There are no breaks in series.

When SBS data become available, these are compared at an enterprise level with the yearly averages of the values reported monthly for the index; when discrepancies are identified, these enterprises are being contacted and the reason is sought. If necessary, appropriate amendments are made. Most of the times discrepancies are the result of more up to date information being available for SBS purposes. The results are consistent.

 The data are internally consistent.

No cost and burden exercise has been recently performed.

The production and dissemination of revised figures is an integral part of the STS compilation process. Routine revisions are primarily the result of updated information received from the responding units. Major revisions occur in order to take account of the availability of a new structural source that is only collected at long intervals, an update of the base year and the weights of an index series, methodological changes such as changes in concepts, definitions and/or classifications used to produce the data and new legal acts entering into force. Unexpected revisions may also occur due to unforeseeable events, such as errors either from the data provider or during compilation.

There is a formal revision policy at Cystat. Cystat publishes its Revision Policy on its web portal Revision Policy (cystat.gov.cy) describing the general rules and principles governing the procedure of revising data published by Cystat. The policy is based on the guidelines of the European Statistical System (ESS) regarding revision policies for Principal European Economic Indicators, also taking into account the Quality Assurance Framework of the ESS and the European Statistics Code of Practice. 

CYSTAT also publishes a list of scheduled revisions (regular or major revisions), also published on its web portal at: https://www.cystat.gov.cy/en/AnnouncementList.

The same practice is applied both to data released nationally and to data transmitted to Eurostat. When revised data are transmitted to Eurostat, these are flagged accordingly and accompanied by the necessary explanations.

Furthermore, CYSTAT has set its strategic goal to provide high-quality statistical information in an objective, transparent, reliable and timely manner. CYSTAT consider quality to be its main advantage in a world experiencing a growing trend of instant information which often lacks the necessary proof of quality. In order to realise strategic goals it is imperative to establish policies which ensure that an organisation is moving towards the right direction. For this reason, CYSTAT establishes the "Quality Policy" which forms the basis of all statistical activities and leads towards continuous improvement of its statistical output.

Routine revisions are carried out by Cystat in order to improve disseminated provisional figures in a way that important information is published as promptly as possible and the number of such revisions is kept to the minimum over a given period of time. Major revisions are backwards implemented for the complete time-series or up to the point where it is feasible and are coordinated across statistical domains. Major revisions are well documented and made public, with an explanation of the reasons for the revision.

When published statistical data are provisional, this is indicated both in the text and the relevant tables. When revised data are disseminated by Cystat, they are appropriately flagged both in the text and the relevant tables and are accompanied by explanatory notes, if needed.

When the revisions are major, non-regular or non-scheduled, the explanatory notes contain information explaining the reasons for revising the data and, where relevant, new methodologies or new sources. Also, Cystat carries out regularly an analysis of the revised data at statistical domain level, in order to assess and improve the quality of provisional figures published and the overall revisions procedure.

The Mean Revision (MR) of year-on-year growth rates for the G45 (turnover value) for calendar adjusted data, taking into account 20 values/growth rates, is 0,75%, whereas the Mean Average Revision (MAR) is 2,51%. 

The Mean Revision (MR) of year-on-year growth rates for the G46 (turnover value) for calendar adjusted data, taking into account 20 values/growth rates, is 0,30%, whereas the Mean Average Revision (MAR) is 1,06%. 

The Mean Revision (MR) of year-on-year growth rates for G47 (value - TOVT) for calendar adjusted data, taking into account 36 values/growth rates, is 1,14%, whereas the Mean Average Revision (MAR) is 2,74%.

The Mean Revision (MR) of year-on-year growth rates for G47 (volume of sales - TOVV) for calendar adjusted data, taking into account 36 values/growth rates, is 0,42%, whereas the Mean Average Revision (MAR) is 2,86%.

The data are collected by survey. Around 600 enterprises are surveyed on a monthly basis.

Monthly or quarterly.

The majority of the enterprises are contacted by telephone, e-mail or fax. Close cooperation and telephone contacts with the data providers are performed in order to ensure high quality of the data. Re-contacts by e-mail and phone as many times as necessary increase the rate of response.

Quality checks are performed based on month to month variations. Data validation is done by comparing the value for the current month with that of the previous month and of the same month of the previous year. In case of outliers, enterprises are contacted for verification of data and explanations, if necessary.

A Laspeyres Index is compiled comparing the current period with the fixed period in the base year. In order to compile turnover indices at higher levels of NACE Rev. 2, the indices at the lowest level have to be aggregated. This aggregation is done by using weights based on the turnover share of each activity in the base year derived from the annual SBS survey (Wholesale and Retail Trade Survey 2015). The index is based on year 2015 (i.e. average 2015=100). Enterprises with 10 or more persons employed are surveyed exhaustively. Sample survey is used for smaller enterprises. 

• Indicate the software used and version

JDemetra+, version 2.2.3

• Indicate the model/filter selection (manual vs. automatic)

Generally, automatic selection is used but, quite often, manual selection is necessary in cases when the automatic selection does not produce well fitted models.

• How often are the models and the respective parameters re-estimated

Systematically, models are re-estimated when the final gross data of the previous year are available. Also, models are re-estimated in case of multiannual gross data revisions. Parameters can be re-estimated more frequently in cases the model does not provide a good fit.

• Indicate the horizon of revisions (how often are the seasonally adjusted time series revised and how far backwards)

Seasonally adjusted time series are revised with each new period back to the first reference date.

• Indicate seasonal adjustment decomposition (additive vs. multiplicative)

Automatic decomposition is used. For the components of the Index with positive values, the decomposition is always multiplicative. For series with zero values, it is a case-by-case treatment.

• Indicate the model used

Models may change at least once a year and vary among the different components of each Index. Some of the ARIMA models used for the various series of this Index are: [(0,1,1)(0,1,1)], [(1,1,1)(0,1,1)], [(1,0,0)(0,1,1)], [(0,1,1)(0,0,0)], etc.

• Indicate the critical value for outlier detection

3.5

• Indicate the filter length (automatically chosen vs. user-defined)

TRAMO-SEATS method (therefore there is no filter, question not applicable) is used.

• Indicate the date of seasonal breaks in the series

There are no seasonal breaks.

• Indicate if indirect adjustment via components is used

No, we use direct adjustment, adjusting the aggregate and the components independently.

• Indicate whether residual seasonality is checked and from which level of detail the aggregation is started

Residual seasonally is checked for all levels. The direct adjustment method is used.

• Indicate the consistency amongst the different levels of breakdown

In the direct adjustment method, the different levels of breakdown do not need to be consistent. In the choice between no residual seasonality and level consistency, our choice is to provide good quality seasonally adjusted series without residual seasonality

No additional comments.