Reference metadata describe statistical concepts and methodologies used for the collection and generation of data. They provide information on data quality and, since they are strongly content-oriented, assist users in interpreting the data. Reference metadata, unlike structural metadata, can be decoupled from the data.
Central Statistical Bureau Republic of Latvia (CSB).
1.2. Contact organisation unit
Business Statistics Department, Business Statistics Methodology Section.
1.3. Contact name
Confidential because of GDPR
1.4. Contact person function
Confidential because of GDPR
1.5. Contact mail address
Lāčplēša street 1, Riga, Latvia, LV – 1010.
1.6. Contact email address
Confidential because of GDPR
1.7. Contact phone number
Confidential because of GDPR
1.8. Contact fax number
Confidential because of GDPR
2.1. Metadata last certified
25 August 2025
2.2. Metadata last posted
25 August 2025
2.3. Metadata last update
25 August 2025
3.1. Data description
European Union (EU) survey providing statistics on the production of manufactured goods. It is based on a list of products called the PRODCOM list; for each product in the list, the statistics show the amount produced in each year in Latvia and whole Europe.
The list aims to include all manufactured products. But to keep it manageable, similar products are grouped into single items. The list is updated every 2 to 3 years – it currently contains 4043 items.
PRODCOM data are collected according to the EU Regulations:
Regulation (EU) 2019/2152 of the European Parliament and of the Council of 27 November 2019 on European business statistics;
The indicators requested are: value and volume of industrial production and/or actual production in Latvia during the reference period.
The sample comprises all industry legal units that are representative for the national economy and of each produces good included in the PRODCOM List.
Companies are addressed by the letter and asked to fill in a web form with information of their probable produced goods during the referense period.
Response is checked and analysed. Estimations are done for missing values, results are validated. Results are disseminated and published on the site - Official Statists Portal Official Statistics of Latvia. Please click the Statistics database.
3.2. Classification system
Data are collected and published according to:
List of Products of the European Community (PRODCOM) (corresponding version of each year);
List of Products of the European Community (PRODCOM), National version, with additional codes for nacional needs (corresponding version of each year);
Statistical Classification of Economic Activities in the European Union, 2nd revision (NACE Rev. 2);
Statistical Classificatin of Products by Activity, Version 2.1. (CPA 2.1.).
The survey covers NACE Rev. 2 sections B and C, with sections 07 - 33 and NACE class 38.32 of section E.
Since 2006, the survey covers all industrial enterprises and enterprises with secondary industrial activity with more than 10 employees. In some cases, the sample included companies with a less number of employees.
All industrial enterprises are sampled to achieve 90% of each 4-digit level NACE class or sufficient degree of representativeness required at CPA class level.
3.4. Statistical concepts and definitions
The purpose of the statistics is to report, for each product in the PRODCOM list, how much has been produced in the reporting country during the reference period. It means that PRODCOM statistics relates to products (not to activities) and are therefore not strictly comparable with activity-based statistics such as Structural Business Statistics. The NACE codes on which PRODCOM codes are based merely serve to identify the enterprises that should be monitored in this survey.
The products: the PRODCOM List defines the products to be included in the survey. There are approximately 4000 headings representing manufactured products and some industrial services.
The values and the volume of production: the value is expressed in national currency but where necessary converted to EURO by Eurostat. From year 2014 Latvia's national currency is EURO. The volume is expressed in a unit specified for each product.
The volume unit: the measurement unit, such as kilograms, square metres etc. used to indicate the volume of goods produced.
Production type:
Sold production - represents the quantity in the volume unit specified in the corresponding PRODCOM List and value in Thsd Euro of sold production and industrial services. The value and volume of the product sold by the enterprise;
Production under sub-contracted operation - represents the quantity in the volume unit specified in the corresponding PRODCOM List and value in Thsd Euro;
Actual production - the volume of all production of the product of PRODCOM codes, including both the proportion that is sold and the proportion that is retained by the enterprise for adding to stocks, using in further processing etc..
3.5. Statistical unit
Economically active enterprises the main or secondary economic activity of which is manufacturing.
The reporting unit is - Enterprise = Kind of activity unit (KAU).
The observation unit is - Kind of activity unit (KAU), principal and secondary activities.
3.6. Statistical population
The population for the statistics are enterprises with industrial activity as main object of activity and non-industrial enterprises with industrial activity as secondary object of activity; enterprise must have at least 10 employees.
In some cases, the sample included companies with a less number of employees. The population is selected annually from the Statistical Business Register.
3.7. Reference area
Industrial production on national level - LATVIA. No regional breakdown.
3.8. Coverage - Time
The period observed is one calendar Year.
Latvian industrial products statistics date back to 2000; The annual data can be consulted in electronic format in EUROSTAT DATABASE.
Electronically, data from 2007 onwards are available on Official statistics portal, Official statistics of Latvia CSB Database. Data based on NACE Rev. 2., CPA 2.1.
3.9. Base period
Not applicable.
Sales of manufactured industrial products is measured in Thsd Euro and in physical measurement unit required by the Nomenclature of Industrial Production (PRODCOM), specific for each product.
For value (sales): Thsd EURO, excl. VAT and excise duties
The reference period for data submitted to Eurostat PRODCOM is the calendar year.
Current reporting period is year 2024.
6.1. Institutional Mandate - legal acts and other agreements
This survey is carried out in compliance with following regulations:
1. at EU level:
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;
Commission Implementing Regulation (EU) 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 statistics;
Commission Implementing Regulation (EU) 2022/2552 of 12 December 2022 laying down the technical specifications of data requirements for the detailed topic industrial production statistics establishing the industrial products classification breakdown, pursuant to Regulation (EU) 2019/2152 of the European Parliament and of the Council and amending Commission Implementing Regulation (EU) 2020/1197, as regards the coverage of the product classification (Text with EEA relevance) - Please click this website;
Commission Implementing Regulation (EU) 2023/138 of 21 December 2022 laying down a list of specific high-value datasets and the arrangements for their publication and re-use (Text with EEA relevance) Please click this website for more information.
2. at the National level Legislation: LV STATISTICS LEGISLATION:
Statistics Law Nr. 2015/118.3 issued on 01 January 2016. The purpose of this Law is to provide statistics on economic, demographic and social phenomena, and processes taking place in the public, and also the environment.
6.2. Institutional Mandate - data sharing
Not applicable at Member States level. Separate sets of aggregated data are sent to the institutions under a written agreement.
7.1. Confidentiality - policy
Confidentiality of individual data is protected by Statistics Law:
Section 7. Competence of the Statistical Institution in Production of Official Statistics.
(2) The statistical institution shall;
8) Ensure statistical confidentiality in accordance with the procedures laid down in this Law.
Section 17. Data Processing and Statistical Confidentiality.
Section 19. Dissemination of Official Statistics:
(1) The statistical institution shall disseminate official statistics in a way that does not allow either directly or indirectly identify a private individual or a State institution in cases other than those laid down in Section 25 of this Law;
(2) The statistical institution shall publish the official statistics which have been produced within the framework of the Official Statistics Programme in a publicly available form and by a predetermined deadline on the portal of official statistics. Until the moment of publication of official statistics this statistics shall not be published.
CSB has introduced Quality Management System (QMS). The system is directed towards providing high user satisfaction and ensuring compliance with regulatory enactments. Based on the structure of Generic Statistical Business Process Model (GSBPM), QMS defines and at the level of procedures describes processes of statistical production as well as sets the persons responsible for the monitoring of processes at all stages of the statistical production. QMS defines the sequence how processes are implemented (i.e., activities to be performed (incl. verifications of processes and statistics, sequence and implementation requirements thereof, as well as persons responsible for the implementation)), procedures used in the evaluation of processes and statistics, as well as any improvements needed.
Since 2018, QMS of the CSB has been certified by the standard ISO 9001:2015 “Quality Management Systems. Requirements” (certified scope: Production of official statistics – planning, development, data acquisition, processing, analysis and dissemination).
Latvia applies the principle of the active confidentiality in PRODCOM. Statistical data shall be considered confidential if they directly or indirectly allow for identification of the private individuals or State authorities regarding which personal statistical data have been provided. Confidential data are treated by suppression. Data are confidential if there are 3 or less enterprises or one enterprise accounts for more then 80% or two of them more than 90%. Confidentiality rules are applicable for value and volume data. Confidentiality has been solved by aggregation of single headings. Also, confidentiality is applied for data of individual enterprises.
8.1. Release calendar
All official statistics are published according to the data release calendar, at 13:00 Latvian time.
Statistical release dates and times are pre-announced in the data release calendar.
Statistical dissemination policy defines general principles of statistical data dissemination, availability of CSB`s products and services for data users, communication with data users, cooperation with the media, availability of individual data for scientific and educational purposes, as well as most important activities in 2024.
The first PRODCOM data from are sent to Eurostat on 30 June of the reference year + 1.
Revised data is resent to Eurostat in accordance with the CSB Work plan.
Annually collected data are available twice a year (T + 6m - provisional data, T + 11m - final data) based on headings from the PRODCOM List. PRODCOM data are submitted annually to Eurostat and published annually.
10.1. Dissemination format - News release
New Release not published.
PRODCOM data is prepared twice a year (T + 6m - provisional data, T + 11m - final data) only for Official statistics portal and is available on-line via Statistics database.
10.2. Dissemination format - Publications
New Publications not published.
PRODCOM data is prepared twice a year (T + 6m - provisional data, T + 11m - final data) only for Official statistics portal and is available on-line via Statistics database.
10.3. Dissemination format - online database
Data is available after the latest PRODCOM classification codes. Information is published for only actually existing products. As about 80% of the collected information is confidential and taking into account that the new PRODCOM indicators on the work of subcontractors created an additional amount of confidential data, CSB databases will continue to publish information - the Total sold production volume and value and industrial services. Starting with 2021 data a new table was created for the 2021 data, which meets the PRODCOM requirements of the new FRIBS Regulation.
It is possible to use remote access to anonymized individual data in research. Depending on the additional data processing methods applied, the datasets are available for use on the researcher's infrastructure (Off-site) or on the remote access system of the Central Statistical Bureau (On-site). The data are available if the application is filled in and the contract is concluded in case of a positive decision from the Central Statistical Bureau. Anonymized individual data can only be used for scientific or research purposes; moreover, research results have to assure benefit to all society.
Individual data, or microdata, are records from surveys, population censuses, or registers on individuals, households, or enterprises.
10.5. Dissemination format - other
Data are sent to Eurostat, and information on industrial production is available on the homepage of the European Union (EUROSTAT) Statistical Office.
If data users need more detailed data, they can find it in the publications above, or it is possible to ask for data at the product level through our information center.
User support: (Please check the link below for more information).
We will consult you as soon as possible and free of charge.
Custom made data may be delivered on request.
In this case we will propose and confirm with you a quote before delivering the data. More info on this may be found in Information requests.
If the data can be produced, the department prepares and supplies it by request, as a paid service.
10.6. Documentation on methodology
Statistical questionnaires including methodological guidelines and explanations of variables and methodological explanations, can be found on this website.
The work is primarily based on Eurostat methodology and guidelines. Additional consultations take place through correspondence or phone consultations.
10.7. Quality management - documentation
The quality of the statistics is assessed in accordance with the existing requirements of external and internal regulatory enactments and in accordance with the established quality criteria.
The CSB has developed and introduced Project Documentation System where all statistical products (surveys and calculations) are described by production processes thereof. These national standard quality reports are published in CSB webpage in Latvian. Quality report of PRODCOM statistics is under section nationally standartized reports of quality.
Regulation (EC) no. 223/2009 of the European Parliament and the Council on European Statistics states that European Statistics shall be developed, produced, and disseminated on the basis of uniform standards and of harmonized methods. In this respect, the following quality criteria shall apply: relevance, accuracy, timeliness, punctuality, accessibility, clarity, comparability, and coherence.
In order to ensure the preparation of higher quality statistics, the CSB in its activities strives to comply with the European Statistics Code of Practice and continues to implement elements of the quality management system. More information on quality statistics can be found in the "Quality documentation for statistical institutes."
The quality of statistical information and its production process is ensured by the provisions of the European Statistics Code of Practice. In 2007, a quality management system (aligned with the requirements of the international quality management system standard ISO 9001) was enclosed into Statistics Latvia. Quality Declaration of the European Statistical System, United Nations Fundamental Principles of Official Statistics, Recommendations of the OECD Council on Good Statistical Practice - QUALITY ASSURANCE FRAMEWORK. Please click on this website for more information.
The quality indicators are calculated taking into account Eurostat methodology for the calculation of quality indicators and documented in the Project's Documentation System QUALITY ASSURANCE FRAMEWORK. Please click on this website for more information.
The PRODCOM survey is based on annual information. PRODCOM data is checked in several ways:
a) PRODCOM data are produced in close cooperation with STS, enabling the data reported in the two surveys to be checked against each other;
b) PRODCOM data are compared with the enterprises that submitted foreign trade and customs statistics;
c) PRODCOM data are compared with SBS data;
d) PRODCOM also uses the administrative data (VAT) in the validation procedures.
PRODCOM staff applies its own data checks by comparing unit values across enterprises, across time, and also some additional algorithms. Any identified outliers are reported to the declarant, asking for an explanation or a correction.
11.2. Quality management - assessment
Quality of statistics is assessed in accordance with the existing requirements of external and internal regulatory enactments and in accordance with the established quality criteria.
Regulation (EC) no 223/2009 of the European Parliament and of the Council on European statistics states that European Statistics European statistics shall be developed, produced and disseminated on the basis of uniform standards and of harmonised methods. In this respect, the following quality criteria shall apply: relevance, accuracy, timeliness, punctuality, accessibility, clarity, comparability and coherence.
The quality of statistical information and its production process is ensured by the provisions of the European Statistics Code of Practice. Prodcom data are collected electronically. The electronic questionnaire provides a number of arithmetic and logical controls, both mandatory and optional between the items in each form and between the forms in the whole annual report. There are a number of arithmetic and logical controls inside the PRODCOM form. The system that supports this electronic questionnaire calculates both the totals and the unit price.
The PRODCOM questionnaire cannot be filled-in successfully before all errors inside the questionnaire, detected by the checking program, have been corrected. Besides, the supplied PRODCOM data are cross checked against the previous year data, to identify the outliers.
If there are interlinked errors, these are displayed after the validation of the whole set of reports.
The information quality is measured by quality key indicators, like: the number of filled-in questionnaires, number of imputed missing indicators, reporting time and the necessary duration to fill-in the questionnaire.
Special mathematical programs were created to check and compare the data for different periods and sections. Correct coding of goods is verified in correlation with foreign trade data codes.
12.1. Relevance - User Needs
The main users of PRODCOM statistics:
External (their needs are satisfied without breaching the confidentiality principle):
Governmental authorities, public administration (central and local) - Latvian market statistics for specific products or product groups; investigate the developments in the industrial structure and the sales of goods;
Trade associations, research institutions, students - Latvian market statistics for specific products or product groups;
Enterprises - interested in industry data to be able to plan for future developments;
Mass media - interested in production of certain products, sales;
Embassies - Latvian market statistics for specific products or product groups;
International institutions (EUROSTAT, United Nations, FAO) - need internationally comparable figures in Latvian industrial production.
Internal:
Weighing system for producer price index (PPI);
ICT (Information and communications technology) for Trade and Services statistics section;
SBS.
12.2. Relevance - User Satisfaction
The mission of the CSB is to provide users of statistical information with independent, high-quality official statistics for decision-making, research, and discussions.
You can provide your opinion on data quality to e-mail: pasts@csp.gov.lv
We don’t receive any special feedback from our users, and no user satisfaction survey has been done for PRODCOM statistics.
Official Statistics Portal traffic is monitored. There are website visitor opinion polls, general opinion polls on the products and services of Statistics Latvia, target user group opinion polls, and other surveys.
12.3. Completeness
The data is available annually and in accordance with legal requirements. Considering the large amount of confidential data, CSB publishes only data of total sold products and industrial services in its own databases.
The CSB provides Eurostat all the data requested by the PRODCOM Regulation. All requested data are delivered to Eurostat, adding a flag of confidentiality where it is the case. But some of our PRODCOM codes exist only to satisfy national needs.
13.1. Accuracy - overall
The overall accuracy is affected by the non-response of the respondents, in which case the missing records are obtained by applying the necessary imputation methods.
Sampling is done by using the NACE (Rev.2) level while taking most of the sales in terms of value for the companies whose summed-up sales are covering at least 90% of the NACE class annual sales volume.
A census of all enterprises with more than 10 employees and essential total turnover is taken from the Statistical Business Register and tax authorities for PRODCOM sampling.
The issue of non-response is treated while collecting the questionnaire (logical checks, contact with respondent), being covered by estimations.
Questionnaires are collected and checked by the special office staff. The questionnaire and collecting system provide a number of arithmetic and logical controls. Staff is in close contact with the respondents.
Central staff checks the preliminary results. Final results are approved and prepared for publication.
For large companies, the company's annual reports and balance sheets must be submitted much later than the enterprise's production was terminated. The information required for the CSB PRODCOM report is, therefore, the company objects to providing this information sooner than the prepared annual balance sheet. This fact affected the annual industrial production survey data collection, including the response rate and quality check comparing the survey data with annual reports of enterprises.
At the end of June, the non-responding companies were sent warnings about the onset of administrative liability if reports are not submitted with the task to do so by August 25. The results will be visible in the revised data.
About 8% of the large companies in the sample have not yet submitted data and have not yet been imputed, as data are gradually being provided. That's why there could be large revisions of industrial production statistics indicators, which are difficult to assess in the present situation.
About 17% of all enterprises were projected to have imputations using data from other surveys to reduce the burden on enterprises. The response rate of the 2024 survey to the PRODCOM survey was 83.2% of all sampled enterprises.
13.2. Sampling error
Sampling error is not relevant.
Sampling errors do not occur in the survey. The sample desing applied is a cut-off sample, which means it is a full coverage survey with a cut-off threshold. There is no grossing up for units below the threshold. It is therefore not relevant/possible to calculate sampling error.
13.3. Non-sampling error
Over-coverage errors in 2024: 1.03%.
Comment: Over-coverage errors mainly occur if observed units are registered in the activity that we observe but perform some other activity that is not the subject of our observation.
Under-coverage rate: is not measurable due to lack of information.
Comment: The under-coverage errors may occur if non-observed units have not registered their activity or registered it incorrectly. As a result, we also don't have information about the mentioned units, and we don't ask them to fill in the survey.
Non-response rate in 2024:
Unweighted response rate - 79.3%.
Weighed response rate- 83.2%.
Unplanned imputations rate- 2.08% from the number of companies included in the sample, carried out until 30 June 2024.
Planned imputationsrate- 14.4%.
Unweighted imputation rate - 16.25%.
Multiple listing rate - not applicable. The reason for absence is that every observed unit has to fill the survey in only once, and one of the validations in our system does not allow submitting it more than once. So if any information in the survey is incorrect, our statisticians communicate with the units by phone and make corrections in the existing database entry. For each unit we have only one database entry.
To ensure the high quality of data, data control is carried out in several phases. The first phase consists of data control at the enterprise level and aggregation at the product level, with data comparison with values reported in other surveys. In the second phase the quality control is carried out in the industry and construction statistics section, where data are analyzed and possibly corrected. The data checking includes:
Comparison with previous period;
Comparison of unit value;
Comparisons with other surveys.
The measurement units are the same as in the PRODCOM list. There are some problems when the measurement units mentioned in the list are different from units used by enterprises. In order to help enterprises to fill questionnaires correctly, the staff of the industry and building statistics section have studied problems with the measurement units and created recalculation coefficients from one measurement unit to another.
Data should be available for every enterprise involved in the PRODCOM survey. Data of missing units are replaced from the PRODCOM survey of the previous year, if it is available.
To increase the response rate, contacts are done by phone calls and also via e-mail messages.
For non-response cases we apply estimation to the value and volume data, using:
Data of the previous year;
Monthly data (value of production and sold production);
SBS data;
The product's historical data of the enterprise;
The average price of other similar respondents;
Foreign trade data;
Customs data.
Company annual balance sheet; management report.
14.1. Timeliness
The data are prepared in accordance with the deadlines set by the EU regulations and the CSB work plan.
Preliminary data
At the end of June, after the reference year, preliminary annual data are available. The Regional Data Collection and Processing Centre checks preliminary data according to the data editing validation program.
PRODCOM data are submitted to Eurostat T + 6 months (30th of June) after the end of the reference year.
Preliminary data are available on the website of the CSB at the end of July T + 7 months.
Final data
At the end of November the final annual production data are available. Differences between preliminary and final data are:
Enterprise data is given after the deadline;
Corrections of errors found in the second phase of data validation by the Industry and Building Statistics section;
The missing data is replaced.
PRODCOM final data are available on the CSB website at the end of November, T + 11 months after the reference year.
PRODCOM estimates are usually validated and uploaded onto Eurostat's website around the same time that CSB publishes the updated PRODCOM data.
According to the data revision policy, the data can be audited within 3 years after the first audit, and if major changes are detected, the data is sent again.
14.2. Punctuality
The transmission of data to EUROSTAT is in accordance with the transmission program.
For the reference year 2024, the provisional data were transmitted on 27 June 2025.
As the data is collected once a year, the data collected and transmitted in June is very preliminary, and high-quality data can be provided only in November.
Therefore, the data are sent to Eurostat every recurrent November, and only after that is the quality of the data objectively assessed. Thus, the data submission schedule to Eurostat is approximately as follows:
T + 6 months (T = reference year): provisional results;
T + 11 months (T = reference year): second provisional results;
T + 30 months (T = reference year): final results.
Statistical information is published in the Official Statistics Portal Database in accordance with an approved release calendar.
15.1. Comparability - geographical
Sold production, exports and imports by PRODCOM list for EU countries.
PRODCOM data can only be compared with other EU countries.
15.2. Comparability - over time
The extensive revision of NACE in 2007 led to major changes in PRODCOM estimates as they were calculated starting with 2008.
Data according to the new NACE Rev. 2 version were recalculated, starting from 2007.
Data for NACE Rev. 1 is available from 1999 to 2007.
Table RUA010 - 25 years;
Table RUA020 - 18 years;
Table RUA040 - 3 years.
The data are comparable because the structure and data set of the data published in the CSB databases will not be changed due to the large volume of confidential data.
For implementing Commission Implementing Regulation (EU) 2020/1197 Annex Table 26 requirements for statistical indicators of PRODCOM, there will be a break in the data series, as production under subcontracted operations was collected separately from production produced for own needs (starting in 2021).
15.3. Coherence - cross domain
Consistency checks are done in correlation with STS & SBS data to ensure the accuracy of the returned data. The value of production for all products in the same 4-digit NACE class can be summed and compared with national turnover in that class according to Structural Business Statistics. Cross-checks are made between SBS, external trade, and STS at micro and macro levels.
15.4. Coherence - internal
We check product code comparability between different versions of PRODCOM, then for each of them we test the indicators of production and sales values, as well as the unit price.
Variable checking in time series is done using an interval of 3 years.
In line with the strategic directions of the European Statistics System and the latest trends in statistical production, continuous use of information acquired in regular CSB surveys and proportionate reduction of the response burden are among the key CSB priorities. In cooperation with holders of administrative data and in line with the competences provided for in the Statistics Law, CSB is striving to solve the issues related to the use of administrative data sources, thus aiming to acquire as comprehensive and high-quality administrative data as possible, allowing it to reduce response burden on enterprises and households. CSB measures to improve use of administrative data and reduce response burden.
Reference period 2024
Burden of the reporting units:
Number of reporting units that have reported - 1922;
Annual number of questionnaires per unit - 1;
Time spent for one questionnaire on average (h) - 1.24 h;
Total time spent (h) - 2383.6 h.
Number of reporting units that should report - 2310 (Without the planned imputations).
Frequency of the survey - annual.
Operational costs:
Work product
Costs, EUR (National level)
Spent time (National level)
Percentage of work for EU products
Costs, EUR (EU level)
Spent time (EU level)
Survey
24 765
2 432
60%
1459.44
14859.14
PRODCOM
24 166
1 465
60%
878.964
14499.61
PRODCOM List
1 435
51
90%
45.765
1291.104
PRODCOM statistical development and nec works
2 084
115
90%
103.185
1875.573
Cost items are not available to the employee.
In line with the strategic directions of the European Statistics System and latest trends in statistical production, continuous use of information acquired in regular CSB surveys and proportionate reduction of the response burden are among the key CSB priorities.
17.1. Data revision - policy
Revision policyis an important component of good governance practice addressed more and more often in the international statistical society. The objective of the Revision policy is to lay down the order of review or revision of the prepared and published data. The first chapter of the present document explains the terms applied in the Revision policy, the second chapter characterizes shortly the CSB revision policy, whereas the third chapter stipulates the revision cycle of the statistical data prepared by the CSB.
In June, the data were transmitted to Eurostat, and in July, the published data on the CSB database are preliminary. The final data can differ from preliminary data at the end of November because of data corrections. Reported data for the previous year are checked systematically by the data collection center because large companies have a different balance of the submission deadline, and hence the PRODCOM survey they submitted only in August. At the same time the survey is also checked by the survey manager. The basic controls are already embedded in the electronic reporting and processing system, which enters ISDAVS. The data are compared with data from annual and monthly performance statistics reports and foreign trade data as well.
Transmitted to Eurostat:
Data of one reference period is revised as follows:
T + 6 months (t = reference year): provisional results;
T + 11 months (t = reference year): second provisional results. The end of November;
T + 30 months (t = reference year): final results.
Non-scheduled revision:
This can happen in exceptional cases, when there have been extreme changes from enterprises for 3 previous years and if it is necessary, data will be modified. In this period ir can turn out necessity of data correction of previous year's, as well.
17.2. Data revision - practice
After amendments in legal acts and detection of significant errors, the revisions of statistical indicators are performed.
Provisional survey estimates are transmitted to Eurostat in June, which is 6 months after the end of the reference period.
Intermediate estimates are sent 11 months after the end of the reference period.
A final set of estimates is sent 30 months after the end of the reference period, if deemed necessary.
18.1. Source data
Data are compiled from the CSB annual statistical new report form 1- Industry "industrial production and services".
Data for the reference year are obtained from economically active enterprises whose main or secondary activity is industry according to NACE Rev. 2 sections B and C and class 38.32 of section E and who are employing 10 or more persons in their industrial production.
In separate sectors, with an aim to ensure at least 90% of the national production volume in each class of the NACE Rev. 2 sectors during the reference year, enterprises employing fewer people are also included.
Paper and electronic questionnaires could be used for data collection.
From 2005 - 2007, industrial enterprises and establishements which according to the Standard Classification of Activities (NACE Rev.1.1) perfomed one or more activities belonging to sections "Minig and Quarrying" (C) and "Manufacturing" (D) were included in the survey. Before 2005, "Electricity, gas and water supply" (E) section was also included but in the National PRODCOM version, we have included products important to the country, including peat and its substrates, because the peat is not an energy product in Latvia, but 99.999% is used in agriculture and an important part of Latvia's economy
The survey covers all enterprises with 10 or more persons employed in the industrial sector. To ensure reliable data, we retain the 90 % rule and in some cases we include smaller eneterprises to cover 90% of the NACE 4-digit classes NACE 07-33 and NACE clase 38.32 of the net turnover.
There are about 2310 units in the survey.
18.2. Frequency of data collection
PRODCOM survey in Latvia is a annual survey.
18.3. Data collection
Data are collected from the CSB annual survey "Survey on production and sales of industrial goods, industrial services provided" (statistical report form 1- Industry). Most data is submitted in the form of an e-report (81.2%), other forms of submission (mail, e-mail, telephone) are less common (18.8%).
Data concerning statistics in accordance with PRODCOM are collected and processed at first in the Data Collection Centre.
The CSB of Latvia uses an e-statistics questionnaire named "Electronic data collection (EDC) system", which can be found together with the instructions for the companies at the CSP home page.
The list of all products is available in the web questionnaire, and the list of all products with corresponding CN codes is available on the website. Part of the logical errors are checked during the process of filling in the questionnaire: Please click on this website.
18.4. Data validation
The CSB uses special software for data entry for processing with automatic report management and data validation tools - Integrated Statistical Data Management System (ISDMS, LV - ISDAVS). The data submitted by the respondent are compared with the previous year and other reports.
The ISDAVS is divided into the following business application software modules, which have to cover and support all phases of the statistical data processing:
Core metadata base module;
Register module;
Data entry and validation module;
Date aggregation module;
Data analysis module;
Data dissemination module;
User administration module.
Part of the logical errors are checked during the process of filling in the questionnaire. The CSB ISDMS system has more automatic controls that spot eventual errors. If the data collector considers these indeed as being errors, they contact the companies and, if necessary, ask for data correction.
The data validation contains:
Validity of each attribute collected within the questionnaire (e.g. enterprise ID, NACE, etc.);
Logical checks between indicators inside the questionnaire;
Comparison over time (previous year);
Cross-survey checks (STS, SBS).
Comparison between enterprises belonging to the same category.
18.5. Data compilation
Revision of the published data is carried out if significant mistakes in enterprise reports are found or if the respondent specifies some information.
Revised data are published at the next publication time, and the last three years are revised.
Received data are checked at the Regional Data Collection and Processing Center.
A special program is checking the similarity of PRODCOM's total industrial output versus STS & SBS data at the enterprise level.
Checks are made against previous returns in order to spot the inconsistencies, and, when necessary, the enterprises are contacted and asked to recheck/correct the data they submitted.
Results are aggregated at the Nomenclature of Industrial Products code level (which is aligned with the PRODCOM list). All results are presented in the form of absolute figures. Quantitative data on production and sold production of industrial products and services are shown at the level of the product or service.
The following steps can take place at the level of the Data Collection and Processing Center:
receive the e-survey or paper questionnaire by e-mail;
data entry in a local database;
running of the IT tools for detecting the errors, and data are corrected where necessary;
checks against SBS data are done, and data are corrected where necessary, after a discussion with the enterprise.
At the Central Statistical Office, the following actions are taking place:
checks made against previous years' data, and where necessary the enterprises are contacted through the Data Collection and Processing Center;
for all enterprises, data from Monthly Industrial Production is compared to ensure consistency between the sources;
for unit non-response cases, there are done imputations from Monthly Industrial Production or the company's annual balance sheet and foreign trade data (if they are available).
When the PRODCOM survey population is selected from the Business Register, a detailed analysis is carried out by Business Register and Industry staff regarding the new births. If there are issues detected, they are fed back to the Business Register.
18.6. Adjustment
Not applicable.
The imputation method of non-response is used to fill in the missing indicators.
The imputation of missing data is based on other administrative sources (STS) and the time series (previously reported data by the same enterprise), SBS, Foreign Trade statistics, and Balance sheet.
Since this is an annual survey, there is no need for seasonal adjustment.
No comment.
European Union (EU) survey providing statistics on the production of manufactured goods. It is based on a list of products called the PRODCOM list; for each product in the list, the statistics show the amount produced in each year in Latvia and whole Europe.
The list aims to include all manufactured products. But to keep it manageable, similar products are grouped into single items. The list is updated every 2 to 3 years – it currently contains 4043 items.
PRODCOM data are collected according to the EU Regulations:
Regulation (EU) 2019/2152 of the European Parliament and of the Council of 27 November 2019 on European business statistics;
The indicators requested are: value and volume of industrial production and/or actual production in Latvia during the reference period.
The sample comprises all industry legal units that are representative for the national economy and of each produces good included in the PRODCOM List.
Companies are addressed by the letter and asked to fill in a web form with information of their probable produced goods during the referense period.
Response is checked and analysed. Estimations are done for missing values, results are validated. Results are disseminated and published on the site - Official Statists Portal Official Statistics of Latvia. Please click the Statistics database.
25 August 2025
The purpose of the statistics is to report, for each product in the PRODCOM list, how much has been produced in the reporting country during the reference period. It means that PRODCOM statistics relates to products (not to activities) and are therefore not strictly comparable with activity-based statistics such as Structural Business Statistics. The NACE codes on which PRODCOM codes are based merely serve to identify the enterprises that should be monitored in this survey.
The products: the PRODCOM List defines the products to be included in the survey. There are approximately 4000 headings representing manufactured products and some industrial services.
The values and the volume of production: the value is expressed in national currency but where necessary converted to EURO by Eurostat. From year 2014 Latvia's national currency is EURO. The volume is expressed in a unit specified for each product.
The volume unit: the measurement unit, such as kilograms, square metres etc. used to indicate the volume of goods produced.
Production type:
Sold production - represents the quantity in the volume unit specified in the corresponding PRODCOM List and value in Thsd Euro of sold production and industrial services. The value and volume of the product sold by the enterprise;
Production under sub-contracted operation - represents the quantity in the volume unit specified in the corresponding PRODCOM List and value in Thsd Euro;
Actual production - the volume of all production of the product of PRODCOM codes, including both the proportion that is sold and the proportion that is retained by the enterprise for adding to stocks, using in further processing etc..
Economically active enterprises the main or secondary economic activity of which is manufacturing.
The reporting unit is - Enterprise = Kind of activity unit (KAU).
The observation unit is - Kind of activity unit (KAU), principal and secondary activities.
The population for the statistics are enterprises with industrial activity as main object of activity and non-industrial enterprises with industrial activity as secondary object of activity; enterprise must have at least 10 employees.
In some cases, the sample included companies with a less number of employees. The population is selected annually from the Statistical Business Register.
Industrial production on national level - LATVIA. No regional breakdown.
The reference period for data submitted to Eurostat PRODCOM is the calendar year.
Current reporting period is year 2024.
The overall accuracy is affected by the non-response of the respondents, in which case the missing records are obtained by applying the necessary imputation methods.
Sampling is done by using the NACE (Rev.2) level while taking most of the sales in terms of value for the companies whose summed-up sales are covering at least 90% of the NACE class annual sales volume.
A census of all enterprises with more than 10 employees and essential total turnover is taken from the Statistical Business Register and tax authorities for PRODCOM sampling.
The issue of non-response is treated while collecting the questionnaire (logical checks, contact with respondent), being covered by estimations.
Questionnaires are collected and checked by the special office staff. The questionnaire and collecting system provide a number of arithmetic and logical controls. Staff is in close contact with the respondents.
Central staff checks the preliminary results. Final results are approved and prepared for publication.
For large companies, the company's annual reports and balance sheets must be submitted much later than the enterprise's production was terminated. The information required for the CSB PRODCOM report is, therefore, the company objects to providing this information sooner than the prepared annual balance sheet. This fact affected the annual industrial production survey data collection, including the response rate and quality check comparing the survey data with annual reports of enterprises.
At the end of June, the non-responding companies were sent warnings about the onset of administrative liability if reports are not submitted with the task to do so by August 25. The results will be visible in the revised data.
About 8% of the large companies in the sample have not yet submitted data and have not yet been imputed, as data are gradually being provided. That's why there could be large revisions of industrial production statistics indicators, which are difficult to assess in the present situation.
About 17% of all enterprises were projected to have imputations using data from other surveys to reduce the burden on enterprises. The response rate of the 2024 survey to the PRODCOM survey was 83.2% of all sampled enterprises.
Sales of manufactured industrial products is measured in Thsd Euro and in physical measurement unit required by the Nomenclature of Industrial Production (PRODCOM), specific for each product.
For value (sales): Thsd EURO, excl. VAT and excise duties
Revision of the published data is carried out if significant mistakes in enterprise reports are found or if the respondent specifies some information.
Revised data are published at the next publication time, and the last three years are revised.
Received data are checked at the Regional Data Collection and Processing Center.
A special program is checking the similarity of PRODCOM's total industrial output versus STS & SBS data at the enterprise level.
Checks are made against previous returns in order to spot the inconsistencies, and, when necessary, the enterprises are contacted and asked to recheck/correct the data they submitted.
Results are aggregated at the Nomenclature of Industrial Products code level (which is aligned with the PRODCOM list). All results are presented in the form of absolute figures. Quantitative data on production and sold production of industrial products and services are shown at the level of the product or service.
The following steps can take place at the level of the Data Collection and Processing Center:
receive the e-survey or paper questionnaire by e-mail;
data entry in a local database;
running of the IT tools for detecting the errors, and data are corrected where necessary;
checks against SBS data are done, and data are corrected where necessary, after a discussion with the enterprise.
At the Central Statistical Office, the following actions are taking place:
checks made against previous years' data, and where necessary the enterprises are contacted through the Data Collection and Processing Center;
for all enterprises, data from Monthly Industrial Production is compared to ensure consistency between the sources;
for unit non-response cases, there are done imputations from Monthly Industrial Production or the company's annual balance sheet and foreign trade data (if they are available).
When the PRODCOM survey population is selected from the Business Register, a detailed analysis is carried out by Business Register and Industry staff regarding the new births. If there are issues detected, they are fed back to the Business Register.
Data are compiled from the CSB annual statistical new report form 1- Industry "industrial production and services".
Data for the reference year are obtained from economically active enterprises whose main or secondary activity is industry according to NACE Rev. 2 sections B and C and class 38.32 of section E and who are employing 10 or more persons in their industrial production.
In separate sectors, with an aim to ensure at least 90% of the national production volume in each class of the NACE Rev. 2 sectors during the reference year, enterprises employing fewer people are also included.
Paper and electronic questionnaires could be used for data collection.
From 2005 - 2007, industrial enterprises and establishements which according to the Standard Classification of Activities (NACE Rev.1.1) perfomed one or more activities belonging to sections "Minig and Quarrying" (C) and "Manufacturing" (D) were included in the survey. Before 2005, "Electricity, gas and water supply" (E) section was also included but in the National PRODCOM version, we have included products important to the country, including peat and its substrates, because the peat is not an energy product in Latvia, but 99.999% is used in agriculture and an important part of Latvia's economy
The survey covers all enterprises with 10 or more persons employed in the industrial sector. To ensure reliable data, we retain the 90 % rule and in some cases we include smaller eneterprises to cover 90% of the NACE 4-digit classes NACE 07-33 and NACE clase 38.32 of the net turnover.
There are about 2310 units in the survey.
Annually collected data are available twice a year (T + 6m - provisional data, T + 11m - final data) based on headings from the PRODCOM List. PRODCOM data are submitted annually to Eurostat and published annually.
The data are prepared in accordance with the deadlines set by the EU regulations and the CSB work plan.
Preliminary data
At the end of June, after the reference year, preliminary annual data are available. The Regional Data Collection and Processing Centre checks preliminary data according to the data editing validation program.
PRODCOM data are submitted to Eurostat T + 6 months (30th of June) after the end of the reference year.
Preliminary data are available on the website of the CSB at the end of July T + 7 months.
Final data
At the end of November the final annual production data are available. Differences between preliminary and final data are:
Enterprise data is given after the deadline;
Corrections of errors found in the second phase of data validation by the Industry and Building Statistics section;
The missing data is replaced.
PRODCOM final data are available on the CSB website at the end of November, T + 11 months after the reference year.
PRODCOM estimates are usually validated and uploaded onto Eurostat's website around the same time that CSB publishes the updated PRODCOM data.
According to the data revision policy, the data can be audited within 3 years after the first audit, and if major changes are detected, the data is sent again.
Sold production, exports and imports by PRODCOM list for EU countries.
PRODCOM data can only be compared with other EU countries.
The extensive revision of NACE in 2007 led to major changes in PRODCOM estimates as they were calculated starting with 2008.
Data according to the new NACE Rev. 2 version were recalculated, starting from 2007.
Data for NACE Rev. 1 is available from 1999 to 2007.
Table RUA010 - 25 years;
Table RUA020 - 18 years;
Table RUA040 - 3 years.
The data are comparable because the structure and data set of the data published in the CSB databases will not be changed due to the large volume of confidential data.
For implementing Commission Implementing Regulation (EU) 2020/1197 Annex Table 26 requirements for statistical indicators of PRODCOM, there will be a break in the data series, as production under subcontracted operations was collected separately from production produced for own needs (starting in 2021).
