Croatian Bureau of Statistics

Service Statistics Department

Ilica 3

10000 Zagreb

Croatia

Retail trade

The index of turnover of trade describes development in the turnover of enterprises engaged in trade.

It is important short-term indicator used to analyse business cycle trends in  trade and as input for National accounts statistics. 

For G 47 the data sources are statistical survey the Monthly Retail Trade Report (TRG-1) and administrative data (data from fiscalization) and for G 45 and G 46 the data source are statistical survey the Monthly Service Activities Report (USL-M) and administrative data (VAT data). 

For G 47 the following variabels are collected:

• monthly turnover with VAT for retail trade
• monthly turnover with VAT for other activities

Variables are reported in thousand kuna.

Indices on the retail trade turnover are presented in two ways:

 a) for the total turnover generated by all business entities with the retail trade as main activity (classified in Division 47).

 b) for the retail trade turnover generated by all business entities engaged in this activity, irrespective of their main activity.

Results are shown in the form of nominal (value indices) and real indices (volume indices). Value indices show turnover movements in current prices. Volume indices are calculated by deflating value indices by retail trade price indices of goods (without electricity and water distribution) according to consumer price indices.

According to Structural Business Statistics (SBS), within the entire non-financial business sector, division 47 participates with 11% in the total number of business entities, with 25% in the overall turnover, with 17% in the total value added and with 20% in the total number of employees.

In Section G, retail trade (division 47) covers 42% of the total number of business entities, 40% in overall turnover and 47% in value added of the distributive trades.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

For G 45 and G 46 is collected information on turnover (excluding VAT) for the reference month and for the same month of previous year. Results are shown in the form of nominal (value indices). 

NACE Rev. 2 

Retail trade (G47)

Division 47 of NACE Rev.2 covered business entities (legal entities, tradesmen and free lances) registered in the retailing trade as a main activity (Division 47 of NACE Rev.2) as well as selected business entities whose main activity is not in the scope of the survey (NACE Rev. 2 Division 47), but they carry out significant secondary activities within the scope of this survey.

Sample for G 47 covers all business entities with 10 and more employees registered in the Statistical Business Register and business entities with less than 10 employess which are selected by using random sample method. Turnover is not taken in account in sample selection.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Division 45 of Nace Rev.2 and division 46 of Nace Rev.2 covered business entities (legal units, tradesmen and free lances) if their prevailing activity is one of the following:

G 45 Wholesale and retail trade and repair of motor vehicles and motorcycles

G 46 Wholesale trade, except of motor vehicles and motorcycles

Sample for G 45 and G 46 covers all medium-sized and large enterprises (sizes 5, 6 and 7) from the Statistical Business Register. Units marked in the Register as small ones are also included if they exceed the determined threshold according to the turnover.

Retail Trade (G 47)

Statistical variable which is provided is turnover. Information is collected on turnover (including VAT) for the reference month, split between i) from retail activities and ii) from other activities of a business entity. Information on retail stocks in the reference month are also collected.

Definition of retail trade turnover is the one as defined in CR 1503/2006, with an exception of VAT which is included.

Data on turnover are collected in two ways:

- businesses with main activity in Division 47 (retailers) report their total turnover, i.e. turnover from their main activity as well as from their secondary activities

- businesses engaged in retailing, but with main activity outside Division 47, report only turnover from retailing.

Turnover covers flows during the calendar month.

Deflated turnover or volume of sales represents the value of turnover in constant prices. It is calculated as turnover at current prices deflated by the deflator of sales.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Statistical variable which is provided is turnover. Information is collected on turnover (excluding VAT) for the reference month and for the same month of previous year.

STS definition on turnover is used. Turnover is defined as a value of all goods sold and services provided on the market during a month, irrespective of whether paid for or not.

Business entities report their total turnover, i.e. turnover from their main activity as well as from their secondary activities.

Turnover covers flows during the calendar month.

Enterprise is reporting and observation unit.

Units whose principal activity is outside of Division 47 of NACE Rev 2 report only turnover on retail trade disregarding turnover from other activities.

The target population are business entities (legal units, tradesmen and free lances) which are classified in the Division 47 by main activity, as well as selected business entities whose main activity is not in the scope of the survey (NACE Rev. 2 Division 47), but they carry out significant secondary activities within the scope of this survey, Division 45 by main activity and Division 46 by main activity. 

The frame for identifying units for the population is Statistical Business Register.

Frame for 2022 for G 47 consists of 19 384 units. Sample covers 3502 units.

Frame for 2022 for G 45 and G 46 consists of 21802 units (14955 in G 46 and 6847 in G 45). Sample consists of 4 197units (3 507 in G 46 and 690 in G45), of which 195 are included in the regular Monthly Report on Service Activities (USL-M form) (167 units in G 46 and 28 units in G 45).

Geographical area covered is Republic of Croatia.

The Monthly Retail trade survey for G 47 has been carried out since 1 January 1998.Comparable data series are available from 2000.

For monthly series  the first period for which turnover index for  G 45 and G 46 was compiled is the first month of 2010. Since January 2017, the Croatian Bureau of Statistics has supplemented the quarterly dynamics of conducting survey with monthly dynamics of turnover changes in G 45 and G 46. 

Base (reference) year is 2015 .

Base year is renewed every five years.

For G 47 the variable for which data are collected is turnover (including VAT) expressed in thousand kuna. Only index numbers are disseminated as a result of the survey.

For G 45 and G 46 the variable for which data are collected is turnover (excluding VAT) expressed in thousand kuna. 

Only index numbers are disseminated as a result.

Reference period is month.

The legal basis is the Official Statistics Act (NN, Nos 25/20) and the Annual Implementation Plan of Statistical Activities. Metodological bases include Eurostat and national regulations.

The methodology for this survey is based on the following Eurostat regulations:

• Council Regulations (EC) Nos 1165/98 (Annex C for G 47 and Annex D for G45 and G 46), 1158/05 and 1503/06 concerning short-term statistics
• Regulation (EU) 2019/2152 of the European Parliament and of the Council on European business statistics, repealing 10 legal acts in the field of business statistics (EBS-Regulation)
• Commission Implementing Regulation 2020/1197 laying down technical specifications and arrangements pursuant to Regulation (EU) 2019/2152 of the European Parliament and of the Council on European business statistics repealing 10 legal acts in the field of business statistic (General Implementing Act)
• Commission Implementing Decision 2021/1003 granting derogations to certain Member States with respect to the transmission of statistics pursuant to Regulation (EU) 2019/2152 (Derogations)

Data series are regularly monthly transmitted to Eurostat as defined in the Council Regulations (EC) Nos 1165/98 (Annex C for G 47 and Annex D for G 45 and G 46), 1158/05 and 1503/06 concerning short-term statistics and Regulation (EU) 2019/2152 of the European Parliament and of the Council on European business statistics, repealing 10 legal acts in the field of business statistics (EBS-Regulation) concerning short-term statistics.

Volume Retail Sales Index, seasonally and calendar adjusted, on the base year 2015 is monthly transmitted (from 2010 onwards) to the Statistical Department of IMF.

National legislation:

Under the Official Statistics Act (NN No. 25/20), the CBS can not publish, or otherwise make available to any individual or organization, statistics that would enable the identification of data for any individual person or legal entity. Individual data are strictly confidential and must not be published or reported.  

European legislation:

Regulation (EC) No 223/2009 of the European Parliament and of the Council, of 11 March 2009, on the transmission of data subject to statistical confidentiality to the Statistical Office of the European Communities.

Confidential data are treated according to policy rules (see point 7.1). 

Data are nationally published only on the levels at which they are not confidential. Data which allow statistical units to be identified, either directly or indirectly must not be published.

All data on the levels proposed as obligatory by the STS Regulation Annex C (for small countries) and Annex D (for small countries for G 45 and G 46) are transmitted to Eurostat. Confidential data are marked with the confidentiality flag.

Data are disseminated nationally with a predefined Release Calendar publicly accessible.

A release schedule for the coming year, specifying dates of release is published each December in the CBS Publishing Program. This document is available in both Croatian and English.

The exact dates of release are pre-announced in the Calendar of Statistical Data Issues.

A release calendar for the year ahead is available on the statistical office's website (www.dzs.gov.hr).

The data publishing revision policy in the Croatian Bureau of Statistics includes the following:

                1) Updating of the Calendar of Statistical Data Issues

                2) Publishing of corrigenda of the published data

1) Updating of the Calendar of Statistical Data Issues

The data publishing revision policy of the Croatian Bureau of Statistics, which is carried out according to the defined deadlines, is carried out by updating the Calendar of Statistical Data Issues. According to the Official Statistics Act, changes in the publishing deadlines for publications/data are announced in advance. The Croatian Bureau of Statistics is obliged to announce each change in the publishing deadlines (the Calendar update) at least three days prior to the date originally announced in the Calendar at the web site of the Croatian Bureau of Statistics.

The update of the publishing deadlines for data or publications (the update of the Calendar) is announced without delay on the Croatian Bureau of Statistics’ website by updating the date in the Calendar and putting the notice beside the Calendar, which says: updated: (the accurate new date).

Therefore, the Calendar that contains the original publishing deadline for a particular publication/statistical information is replaced with the new Calendar which includes the updated publishing deadline. The original Calendar is kept in the Publishing Department which registers every change in publishing deadlines for publications in the Calendar Update Base.

2) Publishing of the corrigenda of the published data

In cases of error in the published data, the Croatian Bureau of Statistics announces the correction as soon as possible and as simple as possible in order to help the users to clearly see what was changed in comparison to the originally published data. The correction is carried out by marking the incorrect data with an asterisk and creating the corrigendum.

Release calendar is available on CBS website in Croatian and English language: 

CRO  Kalendar objavljivanja

ENG  Calendar of Statistical Data Issues

Data are simultaneous released at the same time (11.00 ) to all interested parties by publishing on the CBS’s website on date defined in Calendar of Statistical Data Issues.

There is no prior access to data before its release.

Data (as indices in unadjusted form, trend, SA and WDA form) are transmitted to Eurostat 30 days after the reference month.

Monthly

Retail Trade (G47)

Data for monthly retail survey are published, in the First Release: "Retail trade", on the CBS website: https://podaci.dzs.hr/en/statistics/trade-and-other-services/retail-trade/

News releases provide data on:

• graph for volume retail trade turnover indices (gross, seasonally and working-day adjusted and working-day adjusted indices). Data are presented on base year 2015=100.
• retail trade for a sequence of last six months:
  • month-on-mont growth rates calculated on basis of seasonaly and working-day adjusted indices
  • year-on-year growth rates calculated on basis of working-day adjusted indices
  • value and volume (seasonally and working-day adjusted, working-day adjusted) indices by main activity according to NACE Rev 2 (division 47 and special agregates)
• value and volume of retail trade turnover (gross, non-adjusted)
• value indices of retail trade by branches (gross, non-adjusted)
• standard error and coefficient of variance for turnover chain index

Wholesale and retail trade; repair of  motor vehicles and motorcycles (G), Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Data for G, G 45 and G 46 are published in the First release Service activities, monthly on the CBS website: http://www.dzs.hr.

The time series of the turnover indices of G 45 and G 46 are published on the web site of the Croatian Bureau of Statistics www.dzs.hr in the STS Database (Short-Term Business Statistics Database) in the area Services under the headings Turnover indices of services activities − monthly data, and Turnover indices of services activities − quarterly data, on the link https://stsbaza.dzs.hr/en/Report?dt=9 and within Statistics in Line under the title Economy – Basic Indicators.

News releases provide data on:

-nominal month on month growth rates calculated on basis of seasonally and working-day adjusted indices

-nominal year on year growth rates calculated on basis of working-day adjusted indices

-nominal seasonally and working-day adjusted, working-day adjusted indieces and gross unadjusted indices, on base year 2015=100

Printed form of First Release is available for a fee, in Croatian and English and can be ordered at:

Croatian Bureau of Statistics

Ilica 3

P. O. B. 80

10 000 Zagreb

CROATIA

E-mail: stat.info@dzs.hr

Phone: + 385  (0) 1 4806 138; 4806 154; 4811 212 Fax: + 385  (0) 1 4806 148; 4806 199  

Retail trade (G47)

Name of national paper publication                First releases: Retail trade

Name of national electronic dissemination      First releases: Retail trade

Wholesale and retail trade; repair of  motor vehicles and motorcycles (G), Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Name of national paper publication                First releases: Service Activities

Name of national electronic dissemination      First releases: Service Activities

Reatil turnover (G 47)

Data for G 47 are available in PC Axis database on CBS web site

https://web.dzs.hr/PXWeb/Menu.aspx?px_language=en&px_type=PX&px_db=Trgovina+na+malo

In database following data series are available: value and volume turnover indices -  gross, non-adjusted indices; working-day adjusted indices; seasonally adjusted and trend monthly indices (2015=100) for:

1. Retail trade turnover, according to the special NKD aggregates - available series from 2005:

Special NKD aggregates are:

• Retail trade, except of motor vehicles and motorcycles
• Retail trade of food, beverages and tobacco
• Retail trade of non-food products (except of automotive fuels)
• Retail trade, except of automobile fuels in specialised stores
• Other activities (outside Division G47)

2. Total turnover-division 47, according to the special NKD aggregates - available series from 2000:

Special NKD aggregates are:

• Retail trade, except of motor vehicles and motorcycles
• Retail trade, except of automobile fuels in specialised stores
• Retail trade of food, beverages and tobacco
• Retail trade of non-food products (except of automotive fuels)
• Retail sale of automotive fuel in specialised stores

Dat are also available in STS database on CBS web site

https://stsbaza.dzs.hr/en

1. Total turnover-division 47, according to the special NKD aggregates - available series from 2000:

Special NKD aggregates are:

• Retail trade, except of motor vehicles and motorcycles
• Retail trade, except of automobile fuels in specialised stores
• Retail trade of food, beverages and tobacco
• Retail trade of non-food products (except of automotive fuels)
• Retail sale of automotive fuel in specialised stores
• Retail sale of textiles, clothing, footware and leather goods in specialised stores
• Dispensing chemist, retail sale of medical and orthopaedic goods, cosmetic and toilet articles in specialised stores
• Retail sale of computers, peripheral units and software, telecommunications equipment, etc. in specialised stores
• Retail sale of audio and video equipment, hardware, paints and glass, electrical household appliances, etc. in specialised stores
• Retail sale in non-specialised stores with food, beverages or tobacco predominating
• Other retail sale in non-specialised stores
• Retail sale of food, beverages and tobacco in specialised stores
• Retail sale via mail order houses or via Internet

Wholesale and retail trade; repair of  motor vehicles and motorcycles (G), Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Data for G, G 45 and G 46 are available in Excel format on the web site of the Croatian Bureau of Statistics in the STS Database (Short-Term Business Statistics Database) in the area Services under the headings Turnover indices of services activities − monthly data, and Turnover indices of services activities − quarterly data, on the link https://stsbaza.dzs.hr/en/Report?dt=9 and within Statistics in Line under the title Economy – Basic Indicators.

Micro data are not disseminated.

Data are transmitted to Eurostat to be used in the European aggregates as well as for the dissemination of national data in Eurostat's dissemination.

Retail trade (G 47)

Short methodological explanations are available in the First release, avaliable on the CBS website  https://podaci.dzs.hr/en/statistics/trade-and-other-services/retail-trade/

Main data included in the First release:

- turnover indices for retailers (main activity in Division 47) at the level of agregates as defined in Annex C of STS Regulation (for small countries)

- turnover indices for retailing activities (businesses engaged in retailing regardless on thier main activity) at the same levels as for retailers.

Data are presented as indices for a month-on-previous-month, month-on-same-month-of-previous-year and as month-on-average-on-base-year (2015).

Indices are published in the gross unadjusted form, seasonally and working-day adjusted form and seasonally adjusted form.

On the CBS website a special publication is also available, Methodological Guidelines 69: Methodology for Monthly Survey on Retail Trade (TRG-1 form), that gives very detailed methodological explanations for this survey https://podaci.dzs.hr/media/s0tj1qac/metod_69.pdf

Wholesale and retail trade; repair of  motor vehicles and motorcycles (G), Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Main data included in the First release for G, G 45 and G 46: turnover (value) indices for 2-digit NACE level and for Sections, (as defined in Annex D of STS regulation).

Indices are published in the gross, working day adjusted and seasonally adjusted forms and trend. Short methodological explanations are available in the First release, avaliable on the CBS website https://podaci.dzs.hr/en/statistics/trade-and-other-services/service-activities/. 

Publicly available quality management documentation is this report following bullets from 11 to 18.

There is a written statement under the Official Statistics Act (NN Nos. 25/20) that official statistics in Croatia should be of enough quality.

CBS has started systematic approach to quality management with the adoption of the European Code of Practice and with the decision to implement TQM. This process is still in course. Data base for storing information for the purpose of assessing data quality has been developing.

Usual quality checks have been undertaken during the data editing. The outputs are improved data.

Several quality indicators for monthly survey on retail trade are calculated and published in the First Release each month such as sampling errors (standard error, coefficient of variance, lower and upper 95% reliability interval limits).

CBS has started systematic approach to quality management with the adoption of the European Code of Practice and with the decision to implement TQM. This process is still in course. Data base for storing information for the purpose of assessing data quality has been developing.

Overall quality assessment for this monthly survey, based on available quality indicators is following:

• Data are complete in a sence that turnover variable for all NACE Rev.2 activities and for all levels of aggregation as required by Annex C of STS Regulation (for small countires) for G47 and Annex D of STS Regulation (for small countires) for G 45 and G 46  are provided
• Sample error in general is small
• Results of the Retail trade survey for G47 are disseminated to Eurostat on time (t+30) and published nationally according to the pre-announced release calendar.
• Results for the G 45 and G 46 are disseminated to Eurostat on time (t+60) and published nationally according to the pre-announced release calendar.

The main problems which can influence results are:

• increasing resistance of reporting units to report data
• dealing with constant market changes, especially organizational changes in reporting units which have impact on data comparability during the time

The main users are government, financial institutions, economic analysts, media, researchers and students, enterprises, Eurostat and internal users (National accounts statistics).

User satisfaction is measured via CBS's web questionnaire on user satisfaction available on its website.

There is a good cooperation with main users like Croatian National Bank, Chamber of Economy and Ministry for Economy.

CBS responds to all user's requests up-to-date.

Indicators are complete and fully in line with the concepts and definitions in methodology based on the Regulation (EU) 2019/2152 of the European Parliament and of the Council on European business statistics.

Index series, publiced nationally and transmitted to Eurostat are complete, with no gaps or missing data parts.

Retail trade (G 47)

Since the survey does not include all units of a target population but rather a randomly selected sample of units, there are sample errors that may occur in estimations. The coefficient of variation is a relative measure (percentage) of the accuracy of an estimate. Along with these measures, a lower and upper limit of a confidence interval are calculated.

Sample error in general is small. On the level of total turnover index for Division 47 Standard error amounts about 0,01 same as Coefficient of variance.

The accuracy is improved by eliminating as much as possible non-sampling errors. 

The first estimates in general are not biased. The exception may occur for data for January when new sample is drawn and the first estimates are provided before all units from new sample respond. 

Wholesale and retail trade; repair of  motor vehicles and motorcycles (G), Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

The main sources of errors are sampling errors and non-sampling errors.

The main source for non-sampling errors is the accuracy of the sample frame. In order to update sample frame and to give feedback to Statistical Business Register, based on the information from the survey, units from the sample are classified as:

0 - runs business, refuse to report the data

1 - runs business, report submitted

2 - stopped running business

3 - not engage in in the scope of the survey

4 - dormant unit

5 - bankruptcy

6 - undeliverable

7- does not perform specified service activity but some other service activity

8- budget users

9 - organizational changes (merge, splits etc.)

Retail trade (G47)

Sampling error as coefficient of variance is regularly calculated for each month.

For G45 and G 46 sampling error is not available.

Retail Trade (G 47)

In  September 2022 following indicators were calculated (unweighted) for Monthly retail trade survey:

Response rate 99.09 %

Non-response rate 0.91 %

Over-covearge rate 9.62 %.

Over-coverage rate include units which

• stopped running business 5,25 %
• do not perform retail trade 2,31 %
• CBS don't have any information about units (undeliverable questionnaires) 0,83 %

Indicators are the same in time when data are provided to Eurostat and when data are first published nationally.

Item non-response is not relevant because respondents fill electronic (on-line) questionnaire with built in error checker which prevents sending questionnaire without data. At data entry essential errors are identified which force responding unit or administrator to eliminate them. If not the data could not be successfully send to database.

Entered data in survey processor go through logical and calculation controls according to which data are then checked and if there is a need corrected by statistician.

Measures to reduce non-response: e-mail remainders, telephone contacts with reporting units.

There are units selected into the sample that do not meet the survey requirements due to the method of sample selection, reorganisations or other changes in their operation.

Sampling frame is one of the main source of non-sampling errors. In order to update sample frame and to give a feedback to Statistical Business Register, during the survey each reporting unit is classified into the one of the following status:

Status 0 – runs business, refuses to submit a report

Status 1 – runs business, submitts report

Status 2 – stopped running business

Status 3 – not engaged in distributive trades activities

Status 4 – dormant

Status 5 – bankruptcy, liquidation

Status 6 – undeliverable questionnaire

Status 7 – outside the survey range (does not perform Retail trade, but it performs other distributive trade activities)

Status 8 - government budget user

Status 9 – other reasons (merger or other organisational changes) .

Retail trade (G 47)

The first and final results are published  30 days after the end of the reference month.

In the case of data collection via Internet application, web application for reporting units is opened 20 days after the end of the reference month. 

The survey is in general closed 24 days after the reference month.

Wholesale and retail trade; repair of  motor vehicles and motorcycles (G), Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Results are nationally published within approximately 60 days after the end of the reference period monthly and quarterly in Excel Sheets in STS databse and monthly in First Release.

From January 2019 results are diseminated to Eurostat 60 days after the end of the reference month and quarter. 

The data are collected via a web-based application (the so-called CAWI). The reporting units enter data directly into the USL-M form, which is available on the web site of the Croatian Bureau of Statistics at www.dzs.hr . The period for data collection ranges each month, as a rule, between the 1^st and the 20^th day in a month for the previous reference month data.

The period for VAT data from Tax Administration is 45 days after reference month.

The survey is in general closed 60 days after the reference month.

Data are published in accordance with pre-announced release calendar and there is no time lag between the actual delivery of the data and the target date when it should have been delivered.

Same statistical concepts are applied in the entire national territory. There is no problem of geographical comparability.

Comparable data series are available from 2000 for G 47 and from 2010 for G 45 and G 46. 

The most important sources for cross checks for turnover variable are: Structural Business Statistics, data on registration of vehicles.

Data are internal coherent. Higher level aggregations are derived from detailed indices according to well-defined procedures. For all NACE areas covered by the survey, the same definition of turnover is used.

Monthly Retail Trade Survey

Cost of the CBS: approximatelly 4 800 hours annually.

Burden of respondents: approximatelly 14 min per respondent per month.

Monthly Survey on Service Activities 

Cost of CBS: approximately 3 200 hours annually. 

Burden of respondents: there is no information. In order to reduce burden of reporting units, administrative sources are used as data source for this survey.

Burden for reporting units is available only from 2018 which are conducted via Internet survey. Reporting units give information on time they spent to fill out the questionnaire only in first month of the year. Average time spent as respondents to fill the USL-M surveys is approximately 0,10 hours per month.

The General Revision Policy of the Croatian Bureau of Statistics is based on the following documents:

• European Statistics Code of Practise
• Quality Assurance Framework of the European Statistical System
• ESS Guidelines on Revision Policy for PEEIs.

The corrections of published data caused by technical errors, calculation errors, linguistic and other similar errors are not the subject of the Revision Policy of the Croatian Bureau of Statistics. When disseminating changes to already published statistical data, it is necessary to clearly indicate whether they are corrected data (due to technical or calculation errors) or revised data.

In order to ensure the transparency and availability of data, following the publication of the revised data, the Croatian Bureau of Statistics provides users with the previously published (original) data in the publishing media in which it is possible.

Document General Revision Policy of the Croatian Bureau of Statistic is available on CBS web site https://dzs.gov.hr/other-documents/759 

 The "de facto revision policy" used for this survey includes:

- for mayor revisions (such as change of base year) - all series are recalculated but changes are not announced in advance. Explanations are given when new data are published.

- routine revisions (such as changes of SA and WDA data series) - revised data are published when new data are normally published without classified changed data as revised. There is only methodological explanation regarding usage SA and WDA tool and its implication on changes of previously published data.

- if errors occur, corrected data are published as soon as possible or in the next issue of the publication.

The same revision policy is applied nationally and in transmission to Eurostat.

There is no availability of a vintage database.

Revision calendar exists - information covered under item 8.1.

The benchmarking is not carried out.

Types of revisions for this survey includes:

- mayor revisions (major changes in the methodology, base year change) - all series are recalculated but changes are not announced in advance. Revisions are announced in the First Release at the time the change is introduced and explanations are given when new data are published.

- regular revisions (such as changes of SA and WDA data series ) - revised data are published each month in the First Release for the whole data series, when new data are normally published, without classified changed data as revised. There is only methodological explanation regarding usage SA and WDA tool and its implication on changes of previously published data.

Since January 2016, the software package JDemetra+, version 2.0.0. has been used in the process of seasonal adjustment (identification and evaluation of seasonal and calendar effects). Considering that there are two available options in the JDemetra+, TRAMO-SEATS (using Seats method for estimating seasonal effects) and X13 (using the X11 method for estimating seasonal effects), seasonal and working-day adjustment has been done by using the X13 ARIMA method in this First Release. The effect of a random component in the seasonal adjustment process of time series of indices has been excluded.

Due to the character of the implemented seasonal adjustment method, the extension of the index series by adding new monthly observations for each new month could cause subsequent corrections of the already published seasonally and working-day adjusted indices and trend for several previous months.

- elimination of errors: if errors occur, corrected data are published as soon as possible or in the next issue of the publication.

The same revision policy is applied nationally and in transmission to Eurostat.

There is no avalibibility of a vintage database.

The benchmarking is not carried out.

The Mean Absolute Revision (MAR) and Mean Revision (MR) of year on year growth rates for unadjusted and calendar data for the period from January 2019 to December 2021 for G 47.

 For unadjusted data MAR and MR are 0,0000.

Retail Trade (G 47)

The production of retail trade indices is based on the compilation of data from monthly statistical survey.

The frame on which the survey coverage is based is Statistical Business Register.

Data are collected based on a sample. Random stratified sample is used. Criteria for stratification is the main activity and the size of businesses. The size thresholds are based on the number of persons employed. 

By size, business entities are classified as folows:

Size class 1 : 0-4 persons in employment 

Size class 2 : 5-9 persons in employment 

Size class 3 : 10-19 persons in employment 

Size class 4 : 20-49 persons in employment 

Size class 5 : 50-99 persons in employment 

Size class 6 : 100-249 persons in employment 

Size class 7 : 250 and more persons in employment. 

The sample includes all businesses with 10 or more persons employed. Other small and micro sized units are chosen by random sample method.

A new sample has been drawn every 2 years, with annual update of large and medium-sized units.

In 2022 sample covers 3 502 units (18,1% of total population 19 381)

Covearge rate in terms of turnover is 78%.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Data set is based on a regular monthly statistical survey. Frame on which the source is based is Address list maintained by the statistics office, derived from the Statistical Business Register.

The survey is carried out by using the sampling method. The sample is selected once a year. It is based on size and on annual turnover of business entities for the previous year. All medium-sized and large enterprises (sizes 5, 6 and 7) are taken from the Statistical Business Register. Units marked in the Register as small ones are also included if they exced the determined threshold according to their annual turnover. Information on size of business entities  is obtained from the Statistical Business Register and data on annual turnover from the regular monthly survey (USL-M form) and from administrative data sources (data bases of value added tax reports). A subset of units that will be included into the regular survey (USL-M form) is selected from all units selected in the sample. A selection criterion has been determined according to a particular turnover threshold, which has to be covered by those units. The sample consists of 4 197 units (3 463 in G 46 and 700 in G45), of which 195 are included in the regular Monthly Report on Service Activities (USL-M form) (167 units in G 46 and 28 units in G 45).

Criteria for stratification is the main activity and the size of business entity. The main activity is defined for each business entity according to NACE Rev 2. The size thresholds are based on the number of persons employed. According to their size, business entities are classified into the size-classes.

Monthly

Retail Trade (G 47)

Data are collected by on-line questionnaires and from administraive source - Fiscalization databse from TAX Office. From the beginning of 2021 fiscalization data are used in the production process as a supplement to existing business survey data for micro and medium size units (business entities employing less than 10 persons selected by using the random sample method).

Actions taken to speed up or increase the rate of response: re-contacts by mail (e-mail remainders), telephone contacts.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

The data are collected via a web-based application (the so-called CAWI) and via administrative data sources (data bases of value added tax reports). The reporting units enter data directly into the USL-M form, which is available on the web site of the Croatian Bureau of Statistics at www.dzs.hr. The period for data collection ranges each month, as a rule, between the 1^st and the 20^th day in a month for the previous reference month data. Data can also be collected by e-mail instead of paper questionnaire. Responding units send paper questionaires to CBS by post or by fax. The period for VAT data is 45 days after reference month period.

Actions taken to speed up or increase the rate of response: automatic reminders sent through the web application, re-contact by mail or by e-mail (written reminders), telephone contacts.

Retail Trade (G 47)

There is an automatic control during the entering data into the on-line questionnaire. At data entry essential errors are identified which force responding unit or administrator to eliminate them. If not, the data could not be successfully send to database. Entered data go through logical and calculation controls in survey processor according to which data are then checked and if needed they are corrected by statisticians. There are specific rules that indicate if data are not valid. If neccessary, reporting unit is contacted.

On micro level the most important validation rules are:

-       error if data on turnover in the reference month is 50% higher or lower compared with previous month

-       error if data on value of retail stocks in the reference month is 50% higher or lower compared with previous month.

In the case of web questionnaires first checkings are done at the moment of data entry. Reporting units receive massages if errors occur and/or massages with warnings if data are not logical and have to be re-checked.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

There is an automatic control during the entering data in to on-line questionnaire. At data entry essential errors are identified which force responding unit or administrator to eliminate them. If not, the data could not be successfully send to database.

In the case of web questionnaires first checkings are done at the moment of data entry. Reporting units receive messages if errors occur and/or messages with warnings if data are not logical and have to be re-checked.

Entered data also go through logical and calculation controls in survey processor according to which data are then checked and if there is a need, corrected by statistitian.There are specific rules that indicate if data are not valid. If neccessary, reporting unit is contacted.

On micro level some of the validation rules are for reporting data:

- total turnover by enterprise depends on the size class of the enterprise, e.g.: for large and medium sized enterprise system indicates error if their turnover is below pre-defined limit.

- total turnover of enterprise in the reference month is 50% lower or higher compared with the previous month and with the same month of the previous year.

- total turnover of enterprise for the same period is 20% lower or higher compared the VAT data of reference month and with the same month of the previous year.

On micro level some of the validation rules are for VAT data:

- Correction of negative values

- Comperison with fild survey data

- Detection of outliers

- Imputations

Retail Trade (G 47)

Data are collected on sample basis. Unit non-response is treated by weighting. The weights are calculated as a sum of sample weights and non-response weights. The sample weight is calculated as a reciprocal value of selection probability, while the non-response weight is calculated as a relation between the number of units in the sample and the number of unit responses and non- responses. Weighting is carried out by strata that are defined by NACE activity and size class of enterprises. The relation between the number of units in the sample is expressed by the level of their accertability. Since the number of acceptable units changes over months, their level of acceptability is also a subject to change.

Units that do not respond the questionnaire are treated in a way that data are automatically imputed to them, taking into account data on the turnover that they submitted in a previous month and given the calculated average proportion between turnovers presented in a current and in a previous month of enterprises that responded and that are located in the same stratum. If a new enterprise does not respond the questionnaire, its data are estimated by taking into account other responses in the same stratum and register data on this enterprise.

Data are weighted due to a difference of probabilities of the selection of a unit into a sample and weights are additionally corrected in regard to the proportion of newly-created enterprises and enerprises that stopped running business.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

This survey is conducted by using the sample method. The Statistical Business Register is used as a frame for sample selection. Item non-response is dealt with data editing.

Grossed up results (value of turnover) are used to compile indices. Grossed up results as absolute numbers are used internally, mainly by National accounts.

Retail Trade (G 47)

Results are issued: 

- in the form of nominal (value) turnover indices, that is, the turnover expressed in current prices from which an effect of price changes are not excluded, and

- as deflated indices (volume indices) from which the effects of price changes are excluded.

Volume indices are calculated by deflating the value indices by retail trade price indices for goods (without electricity and water distribution) according to consumer price indices.

Indices are presented in original (non-adjusted) form, as well as seasonally adjusted (SA), working-day adjusted (WDA) and as trend.

Wholesale and retail trade and repair of motor vehicles and motorcycles (G 45), Wholesale trade, except of motor vehicles and motorcycles (G 46)

Nominal turnover indices (value indices) in original, unadjusted form for a current month/quarter are calculated in relation to the average of a base year, then in relation to the same month/quarter of a previous year.

Indices are presented in original, non-adjusted form, as well as seasonaly adjusted, working day adjusted form and as a trend.

Since 2016, in the process of seasonal adjustment (identification and evaluation of seasonal and calendar effects), the software package JDemetra+ was used. Considering that there are two available options in the JDemetra+, TRAMO-SEATS (using Seats method for estimating seasonal effects) and X13 (using the X11 method for estimating seasonal effects), seasonal and working-day adjustment has been done by using the X13 ARIMA method.  The effect of a random component in the seasonal adjustment process of the time series of indices has been excluded.

Due to the character of the implemented adjustment method, the adding of new quarterly/monthly observations for each quarter/month may cause changes in the seasonally and working-day adjusted indices for previous periods. The official list of holidays and non-working days in the Republic of Croatia is used to assess the working-day component, that is, to assess the effect of working days and holidays.

The level of detail: nominal and real series – Base indices of the various aggregates/subgroups of the National classification of economic activities (NKD) based on NACE Rev.2. on the following levels: "47", "47.11+47.2", "47.19+47.4+47.5+47.6+47.7+47.8+47.9", "47.3", "47-47.3", "G45", "G_451_453_454", "G_452","G_46", "G_461", "G_462", "G_463", "G_464", "G_465", "G_466", "G_467" and "G_469"

The use of default vs. national calendar – National calendar of holidays for Croatia is used in X13ARIMA method. 

Adjustment for moving holiday effects (e.g. Easter) – Each series is tested for presence of Easter and Corpus Christi effect (automatic procedure in ARIMA X 13) – effect is significant in part of time series.

Treatment of leap year – The effect of leap year is tested as one of the calendar regressors, it is significant in part of time series.

Lack of calendar adjustment – There is calendar adjustment, i.e. calendar effect for Croatian holidays is tested for all the series

Type of calendar adjustment (e.g. regARIMA) – Calendar adjustment is performed by using automatic identification procedure in ARIMA x13, starting with 7 regressors and reducing their number as some may not be significant for given series.

Type of outliers detected – Level shifts (LS), additive outliers (AO) and transitory changes (TC) are tested, most common are LS's and AO's, automatic procedure is used in ARIMA X13.

Known economic outliers – At present there is not known economic explanation for persistent outliers.

Software / its version and the seasonal adjustment method: JDemetra+ 2.2.2, method is X13ARIMA.

Manual vs. automatic model or filter selection  - For the majority of series, automatic model selection procedure is used; for problematic series, several models are tried in the frame of detailed analysis module until optimal model is found.

How often are models and respective parameters re-estimated? - Parameters re-estimation for ref. periods April, August and December, in other months application of forecasted factors for calculating ‘sa’ and ‘ycal’ series. Annual revision of models, filters, calendar regressors for ref. period m12

The horizon of revisions – It depends primarily on revisions of original series. Seasonally adjusted time series are revised in April, August and December (all values backwards)

Additive vs. multiplicative decomposition of seasonal adjustment – For the majority of series, multiplicative decomposition is performed. (more details in the attached document "Seasonal adjustment_retail trade" and "Seasonal adjustment_G45_G46")

The verification of the adequacy of the models – Adequacy of models is checked by built-in diagnostic indicators in ARIMA x13 after each new observation is added.

Critical value and automation of outlier detection – Default critical value in the automatic detection procedure of outliers is used (ARIMA x13).

The method of selecting filter length – For the length of seasonal filters, automatic procedure is used in  ARIMA x13

Seasonal adjustment over the known breaks in series – Currently there are no breaks in series.

Indirect SA and checks for residual seasonality – No, direct SA approach is used.

The consistency of different aggregation levels – Not applicable

The critical value for outlier detection - 4

The filter length (automatically chosen vs. user-defined)- Seasonal filters are fixed during the year (revised at the end of a year if necessary) - (more details in the attached document "Seasonal adjustment_retail trade" and "Seasonal adjustment_G45_G46")

Whether residual seasonality is checked and from which level of detail the aggregation is started - qs test and f-test on residual seasonality are checked for every series

Not available.