Statistics Portugal (Instituto Nacional de Estatística - INE)

Economic Statistics Department / Sectoral Business Statistics Unit

Departamento de Estatísticas Económicas / Serviço de Estatísticas Setoriais das Empresas

Av. Antonio José de Almeida
PT-1000-043-Lisboa
Portugal

The PRODCOM survey is conducted by Statistics Portugal (INE). This is an annual survey of the value and volume of products produced by enterprises in Portugal during the reference year.

It is carried out in compliance with EU Council Regulation on the Establishment of a Community Survey of Industrial Production (No.3924/91), repealed by the Regulation (EU) 2019/2152 of the European Parliament and of the Council of 27 November 2019 on European business statistics.

For reference period 2021 and onwards, according to Commission Implementing Regulation EU 2020/1197 (EBS Regulation), the current survey collects PRODCOM data on the physical volume and the value for Sold Production and Production under Sub-contracted Operations. The Actual Production refers to the actual volume of production.

Reported data include:

• Volume of Sold Production
• Value of Sold Production
• Volume of Production under Sub-contracted Operations
• Value of Production under Sub-contracted Operations
• Actual Production

The Prodcom survey is based on the Prodcom List, consisting of about 4000 products (Commission Implementing Regulation (EU) 2022/2552 of 12 December 2022). The 8-digit codes used in the PRODCOM List are derived from the 6-digit CPA (Community Classification of Products by Activity) headings and hence the 4-digit NACE (European Classification of Economic Activities). From 2008 onwards, the Prodcom code is linked to NACE Rev. 2 and to CPA 2008 (to CPA 2.1 from 2016).

The Prodcom list is related to Combined Nomenclature (CN). Almost every Prodcom 8-digit code covers one or more CN 8-digit headings, thus enabling the support for a correct classification.

The national classification:

The Portuguese list is based on the European PRODCOM list. To consult the more specific national classification with 12-digit sub-headings and extra headings used in data collection, please see Lista nacional de produtos produzidos, 2022 (V05225).

The survey covers all industrial enterprises which are wholly or primarily engaged in industrial production and industrial services in the Mining, Quarrying, and Manufacturing industries of Structural Business Statistics (SBS).

Prodcom covers sections B, C and E of NACE Rev.2.

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. This means that Prodcom statistics relate to products (not to activities) and, therefore, are not strictly comparable with activity-based statistics such as Structural Business Statistics. The NACE codes on which Prodcom codes are based are only used to identify the enterprises that should be surveyed.

The EBS regulation (2020) stipulates country-level business statistics on industrial production to be collected for three variables:

• 251001 Sold production, defined as sold (invoiced) production, which may be carried out under the primary or secondary activities of the enterprise. It includes production sold (invoiced) between different kind-of-activity units belonging to the same enterprise.

Units: national currency (thousands) and (except for industrial services) quantity as defined in the PRODCOM List in force at the end of the reference period

• 251002 Production under sub-contracted operations, defined as the production under sub-contracted operations which has been sold (invoiced) to the principal, in line under the conditions for sub-contracted operations. The production may be carried out under the primary or secondary activities of the enterprise.

Units: (except for industrial services) national currency (thousands) and quantity as defined in the PRODCOM List in force at the end of the reference period.

• 251003 Actual production, defined as production carried out during the reference period and within the economic territory of the country. It includes those products which, either in the kind-of-activity unit itself, or in another kind-of-activity unit belonging to the same enterprise:
  • are intended for sale,
  • are processed into another product
  • are fitted into another product, or
  • are put into stock.

Units: quantity as defined in the PRODCOM List in force at the end of the reference period.

The reporting unit is a proxy to KAU, principal and secondary activities.

The observation unit is the legal unit.

Enterprises whose principal activity, or one of its secondary activities, is listed in section B, C or E of the classification of economic activities in the European Community (NACE Rev.2).

Industrial production on national level.

Portugal statistics on industrial production date back to 1992.

Not applicable.

For value: in thousands EUR

For volume: physical units indicated in the Prodcom list (kg, m², number of items, etc.). For more info about the units - please see the annex below.

Latest data refers to the calendar year 2022.

This survey is carried out in compliance with following regulations:

- At EU level:

• EU Council Regulation (EEC) No 3924/1991 of 19 Dec, on the establishment of a Community Survey of Industrial Production (PRODCOM). repealed by the Regulation (EU) 2019/2152 of the European Parliament and of the Council of 27 November 2019 on European business statistics.
• Commission Implementing Regulation EU 2020/1197 of 30 July 2020 laying down technical specifications and arrangements pursuant to Regulation (EU) 2019/2152 of the European Parliament and of the Council (referred to as the EBS regulation). 
• 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.

- At national level:

• Law nº 22/2008 (Official Journal (OJ) no 92 1st Series, of 13th May 2008) - Law of the National Statistical System: it defines the general basis of the National Statistical System.

Not applicable.

Policy on data confidentiality is covered by Law No 22/2008 of 13th of May. The Law of the National Statistical System establishes that following data should be confidential:

 1. Individual statistical data.

 2. Statistical data which can be matched in a way that enables the identification of a specific statistical unit.

 (in both cases if the legal unit doesn’t released de data).

Note: if a national data was previously indicated to Eurostat as being confidential, this should not be subsequently disseminated in any other public documents.

Policy of Statistical Confidentiality

Statistics Portugal applies the principle of the active confidentiality on PRODCOM.

The Statistics Portugal policy on confidentiality of Prodcom data is that a specific code is flagged as confidential if there are less than 3 companies reporting the prodcom code. However, we ask all companies of the sample if they allow the disclosure of the information. If they agree, the disclose of the data is evaluated.

Nevertheless, at an aggregate level, some Prodcom codes may need to be hidden, in order not to identify the confidential primary code.

Main reference: Handbook on Statistical Disclosure Control (2010).

Releases from Statistics Portugal are announced in the official release calendar available online for the releases in the current calendar year.

• The provisional data on the reference year is published in June/July (t + 6 or 7 months, t = reference year).
• The final data on the reference year is published in December (t + 12 months, t = reference year).

Official release calendar is placed on the Statistics Portugal website.

The data are disseminated to all users at the same time, through the Statistics Portugal website.

The data are released simultaneously to all interested parties by issuing a press release and updating the information on the database of indicators, both available in Portuguese and English.

A calendar of dissemination is available at the beginning of each year. If there are any changes to the calendar dates, an explanation is presented, and the calendar is adjusted accordingly.

Annual data.

The dissemination on the website of Statistics Portugal is twice a year, in June/July (provisional data for n+1) and in December (final data for n+1).

Industrial production statistics – press release 2022 – provisional data (link).

From 2021 onwards, Publications are not available.

The following data sets are available on Statistics Portugal website:

• Sales of products (€) by industry by Product type (by CAE Rev. 3); Annual
• Sales of products in industry by Product type (by CAE Rev. 3); Annual
• Produced products in industry by Product type (by CAE Rev. 3); Annual

No access to microdata.

Anonymised microdata are available and restricted to accredited researchers.

Eurostat database:

http://ec.europa.eu/eurostat/data/database

The methodological document is available on Statistics Portugal website at (Annual survey on industrial production – code 169) at Metadata system.

The main documentation is an internal desk manual describing the statistical production process, micro and macro validation rules and criteria, and timings procedures called “service levels”. 

Prodcom data are published with a high level of detail, its accuracy depending on the quality of the data, insured by various checkings. Prodcom data are produced in close cooperation with the SBS data, enabling the reported figures of the two sources to be checked against each other. Prodcom also uses the external trade statistics to validate its figures.

Statistics Portugal - Quality chart

Prodcom data is collected electronically. The electronic questionnaire provides several arithmetic and logical controls, both mandatory and optional between the items in each form and between the forms in the whole annual report. If there are interlinked errors, these are displayed after the validation of the whole set of reports. 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 crosschecked against the previous year data, to calculate rate changes and indentify possible outliers.

Main reference: ESS Handbook for Quality Reports.

The main users of PRODCOM data are:

• Institutions at European level

- Eurostat;

- United Nations;

- FAO;

- OCDE.

• Institutions at national level

- Portuguese Environmental Agency;

- Associations;

- Researchers and students at international or national level.

• Internal (inside National Statistic System)

- National Accounts Department of Statistics Portugal;

- Other departments of Statistics Portugal;

- Banco de Portugal/National Bank;

- Regional directions;

- Directorate-General for Energy and Geology.

No user satisfaction survey has been done for this specific statistic.

Nevertheless, there is a certain consistency in the requests for information from users.

The legal acts are fully implemented. 

The statistics on industrial output covers all the industrial production in Portugal.

Provisional data:

The response rate to the PRODCOM Survey, for 2022 provisional data, was of 84% (93% of turnover).

The non-response units (units with no information or not usable information) were imputed with the last year response, updated with the SBS information (rate of change for each unit), or estimated based on SBS information, corresponding to 6% of total of product sales. 

All enterprises that are not included in the sample, are estimated using product sales from SBS data. The SBS estimation rate corresponded to 7% of total of product sales.

External data sources are used for the mining industries (only available in December).

Since total industrial production is checked versus SBS totals, the accuracy is high. The information is obtained for all units of the SBS (industrial activity) (see also 13.2. Sampling error).

The sample is designed considering the SBS information. All reference universe (SBS-with industrial sales) is taken into consideration for the selection. Sampling errors are not calculated.

The most common types of non-sampling errors are: measurement errors and processing errors.

Measurement errors occur because companies report incorrect information about the products produced. The Prodcom list (and national list) is only used by the companies for the response to this survey. The measurement errors may include errors in the identification of industrial product codes, measurement units or incorrect conversion between measurement unit, among others. To minimize these measurement errors, customized questionnaires by pre-printing national codes for each NACE are made available, tables and correspondence tables for download and a support team is available by phone or email. Also the check with NC codes of international trade data is done (when applied).

To reduce the processing errors, micro and macro checks are performed at different aggregation levels, between previous and reference year data, and with other sources (i.e. business surveys, SBS and external trade statistics).

When statistics are not consistent, the units are contacted. 

The response rate to the PRODCOM Survey, for 2022 provisional data, was of 84% (93% of turnover).

For non-response units or no valid response to the survey - data were imputed with the last year response, updated with the SBS information (rate of change for each unit), or estimated based on SBS information. 

The units that are not in the sample are estimated using SBS data (product sales value) and taking into account the distribution of products in each Nace.

Through this process, information is obtained for all the units of the sampling base (population).

The web questionnaire was made available at middle of February.

PRODCOM data are submitted to Eurostat within t+6 months.

Annual data of the Portugal industrial production statistics are released on Statistics Portugal website on the scheduled date:

• The provisional data on the reference year is published in June/July (t + 6 or 7 months, t = reference year).
• The final data on the reference year is published in December (t + 12 months, t = reference year).

There have been no delays in recent years.

The statistics are usually published without delay in relation to the scheduled date.

If there are any delays, an explanation is presented and the calendar is adjusted accordingly on Statistics Portugal website.

On an European level, compliance with PRODCOM regulation allows comparability of data with other EU countries.

According to EBS regulation (2020), from reference year 2021 onwards, new variables were transmitted to Eurostat, distinguishing subcontracting production and sold production. Only data for Actual Production variable is comparable with previous years.

Cross-checks are made between SBS, external trade and STS at micro and macro level. The macro checks involve examining the aggregated returns for PRODCOM at NACE level and ensuring that returns are consistent. The cases with spotted differences are further analysed and, if necessary, corrected as well.

National statistical outputs are consistent.

National statistical outputs should not be compared with Eurostat database.

Main references: Handbook for Monitoring and Evaluating Business Survey Response Burdens (Eurostat, 2007), International Standard Cost Model Manual (SCM network)

The burden has been reduced by decreasing the sample at 60% (since 2012) and by implementing the on-line questionnaires, with on-line validation (diminishing the errors and consequently reducing the time spent for contact validations).

Statistics Portugal revisions policy.

Data transmitted at the end of June are provisional and final data are sent in December.

Statistics Portugal will provide revised versions of the final data when relevant.

We collect PRODCOM information by intermediate of a survey.

Sample conditions:

A) For enterprises classified under industrial activities, the sample is divided in two components:

      i) exhaustive component: include all enterprises with turnover higher than 10 million euros, or higher than 1 million for some specific activities which are relevant for National or Agricultural Accounts purposes;

     ii) non exhaustive component: all remaining enterprises are sorted in descending order of their turnover, then selected considering the weight of the exhaustive component (for each activity):

a. equal or more than 80%: enterprises are included till 15% of turnover is achieved;

b. equal or more than 60% and less then 80%: enterprises are included till 35% of turnover is achieved;

c. less than 60%: enterprises are included till 50% of turnover is achieved.

Furthermore, we guarantee at least 5 enterprises in each activity and inclusion of some special enterprises that, even if they were not selected considering the previous conditions, are relevant at a product level. 

B) For enterprises classified under non industrial activities, all enterprises are selected if sales of products are equal or higher than 5 million euros. Furthermore, we also include enterprises that proved to be relevant in the last year's PRODCOM report (more than 2.5 million euros). 

For this survey we use SBS information (sales of products) to select the enterprises. A sample is selected and, using the product structure resulted out of responses, we apply it to the remaining enterprises that were not selected.

With this method we had a major reduction in the sample size (approx. 60%) compared to the previous methodology (before the year 2012), and the quality was improved, getting a better coherence with SBS and achieving a better coverage in some specific products.

Annual.

Data are collected through web-questionnaires. The web-questionnaires and the filling-in instructions are available on Statistics Portugal website (WEBINQ - choosing "IAPI" - Portuguese acronym for "Survey for Industrial Production"). 

The questionnaires are customized for each activity, containing the entire list of products within the corresponding Nace division.

The online questionnaire includes consistency checking and validation of data, and quality and integrity are improved by the ability to compare with previous data. 

After successful completion of the whole annual report a unique ID code is obtained.

Reference: The Handbook of Recommended Practices for Questionnaire Development and Testing Methods in the ESS (Eurostat, 2005).

The on-line questionnaire contains automatic validation of registered data. If data reveal high variations (considering the previous year report) or outliers, the company is contacted and validation/justification is requested.

Statistics Portugal validates the data through several controls that perform a check comparing with last periods, as well with other enterprises, reporting under the same codes, such as the unit price control.

Data are also checked versus other sources, especially the Industrial Turnover Index (part of STS) and SBS or external trade, at micro (enterprise) and macro (NACE) level.

Once the micro data quality is fulfilled, imputation and estimation procedures can be performed. For each enterprise, SBS sales answer is distributed using the previous year's products answer structure. For all other units which did not respond last year, the total response in the activity for the reference year is used to distribute the products. All SBS enterprises are considered to calculation.

Results are aggregated at PRODCOM (or national product and activity) level and macro analysis are performed, like cross-checking with last year information and STS results.

Note: SBS information used correspond to year 2021 in the moment of providing 2022 provisional data. For PRODCOM 2022 final data, SBS for 2022 will be available.

Main reference: Survey sampling reference guidelines from Introduction to sample design and estimation techniques (Eurostat, 2008).

Not applicable.

Provisional data do not include Mining and Quarrying products (only available in December).

Data on Production under Sub-contracted Operations, despite the efforts made for the reference year of 2022, still does not cover all national production.