Industrial production indices

Quality report
Period: Annual
Year: 2017

01. Contact
02. Statistical presentation
03. Statistical processing
04. Quality management
05. Relevance
06. Accuracy and reliability
07. Timeliness and punctuality
08. Coherence and comparability
09. Accessibility and clarity
10. Cost and Burden
11. Confidentiality
12. Comment

01. ContactTop
01.1. Contact organisation

Statistical Office of the Republic of Serbia (SORS)

01.2. Contact organisation unit

Industry, Construction and Energy Department,

Industrial Statistics Unit

01.3. Contact name

Jasmina Kostic - Simov

01.4. Contact person function

Head of Industry statistics unit

01.5. Contact mail address

Statistical Office of the Republic of Serbia, Milana Rakica 5, 11 000 Belgrade, Serbia

01.6. Contact email address

01.7. Contact phone number

+381 11 2411 852

01.8. Contact fax number

+381 11 2411 852

02. Statistical presentationTop
02.1. Data description

Industrial production index (IPI) is applied for measuring changes in the volume of industrial production in monthly periodicity. Indices of industrial production are derived from the Monthly Survey of Industry (IND1).

02.2. Classification system
  • National classification of economic activities – KD (2010) based on NACE Rev.2 classification (Statistical Classification of Economic Activities in the European Community, Rev.2).
  • Main Industrial Groupings (MIGs).
  • Nomenclature of industrial products for Monthly Survey of Industry (NIP)– 8 digits level (based on National classification of economic activities).
02.3. Coverage - sector

Enterprises with principal activity classified in NACE Rev.2 sections B (Mining and quarrying), C (Manufacturing), or D (Electricity, gas, steam and air conditioning supply, except group 35.3) of NACE Rev.2. Included are also selected business entities whose main activity are not in section B, C or D but that have significant industrial production in these sections (as secondary activity).

02.4. Statistical concepts and definitions

IPI measure the change in the volume of production of products (goods and services) according to the Nomenclature of industrial products for Monthly Survey of Industry. The Nomenclature covers products within sections B, C and D (Electricity, gas, steam and air conditioning supply, group 35.3 excluded). There are weights on product level. Quality change regarding physical volumes has being taken into account when changes occur by updating the weights.

The following variables are collected from each reporting unit for each industrial product in physical volume according to physical units defined by the NIP: Total production in reporting month, total production for period from the beginning of the reference year to the end of current month (cumulative), state of stocks of finished products at the end of reporting month and sale of products from the beginning of the year to the end of the reporting month (volume).

Production for own account and production on contract basis are covered.

Calculation of Industrial production index is based on physical volume of all produced products (with no matter whether products are sold, put into stocks or used for further production). The index is compiled in accordance with concept and definitions from STS European Communities Council Regulation (EC) No. 1165/98 concerning shortterm statistics and its amendments.

More information could be found on the SORS website       






02.5. Statistical unit

Observation units are enterprises with main activity in sections B, C and D (group 35.3 excluded) of NACE Rev.2. Also, for business engaged in industry, but with the main activity outside sections B, C and D (group 35.3 excluded) of NACE Rev. 2. Statistical unit is kind of activity unit (KAU).

02.6. Statistical population

Enterprises registered in sections B, C and D (group 35.3 excluded) of NACE Rev.2 and KAUs with industrial activity belonging to enterprises outside sections B, C and D (group 35.3 excluded) of NACE Rev.2.

In IPI calculation approximately 1440 enterprises and KAUs are involved. Business register is the frame for identifying enterprises and KAUs. The sample is derived from the national business register and it is continuously updated. All big and medium enterprises are included and some`` statistically important units`` by decision of statistical experts.

02.7. Reference area

Republic of Serbia.

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

Industrial production of the units located outside of the territory of the Republic of Serbia is not included.

02.8. Coverage - Time

There are the time series indices for the period Jan 2000–Dec 2017 on the current base year.

Time series are available as gross; seasonally and calendar adjusted indices; and  calendar adjusted, but not seasonally adjusted indices.  

02.9. Base period

Base period is average of previous year. Indices are published related to the previous year. Than indices for the period Jan 2000Dec 2017 are recalculated to the current base year.

03. Statistical processingTop
03.1. Source data

The data source is statistical survey known as ``Monthly survey of Industry IND-1``. The data are obtained from a monthly industrial survey for large and medium sized units (in accordance with the criteria of Business Register). Also, some small units are included according to expert judgment in order to achieve representativeness on division level.  It is cutoff survey. About 1440 enterprises and KAUs are surveyed every month.

03.2. Frequency of data collection

Data are collected monthly.

03.3. Data collection

Data are collected with a paper questionnaire (IND1).  Questionnaires are sent to reporting units by post for all 12 months at the beginning of the year. Also, the questionnaire is located on the website and reporting units can use it. Reporting units may send completed questionnaires by post, fax or e-mail. Telephone contacts are taken in order to increase response rate.

03.4. Data validation

The data entry, completeness check and statistical control are performed both by 16 regional offices of the SORS and by experts in National Statistical institute. Data validation is done during data processing: first, during data entry, then through the IT process of calculating the aggregates. All processing steps from validation to computing the Industrial Production Index is carrying out in automatic IT support system.  IT processing is carried out based on rules designed to detect errors. Some errors are ``warning`` some are ``of great importance`` (should be corrected).  The correction of some errors requires contact with the reporting units.

National data validation rules are very strict. There is a validity control of each variable collected within the questionnaire (production, stocks, sell) and connection between them on the unit level. There is a comparison over time (with previous months, with the same month / period of the previous year).

Also, there is validation of the aggregates. Data are verified with regard to the previous month, with regard to the same month of the previous year and also with regard to extreme values.

Before transmission to Eurostat, the structure of the data file and format is checked in detail. The file format for Eurostat is manually filled from national tables.

03.5. Data compilation

The IPI’s calculation is based on the change in the volume of selected representatives. The representatives are the products (8 – digit level of codes from National Nomenclature of Industrial Products). Production is collected in physical units. Also, production under sub–contracting is covered. Nonresponse is treated by the imputation of data. Two stage weighting system is used.

Compilation practice:

1. Total production is compiled for each product (aggregation of production of all producers). These are then multiplied by a weighting coefficient for product (estimated value added of individual products) to reach a "mass of value added" for all products. Then they are summed to the 3–digit level and 2–digit level of NACE Rev.2.

2. At the 3–digit level and 2–digit level indices are calculated. 2. These indices are multiplied to sections level, MIGs level and total industry level using value added weights of the appropriate 3 –digit level and 2–digit level of NACE Rev.2 from SBS.

In the first step indices at the 3–digit level and 2–digit level of NACE Rev.2 are calculated from volume data on production of individual product and appropriate weighting coefficients on product level using the Laspeyres formula. In a second step indices for sections, MIGs and total industry are calculated by aggregating the indices of the appropriate `` Groups`` of NACE Rev.2 weighted with the ``Group`` share of value added in the total value added.

Weighting coefficients on product level are updated every five years. For IPI calculation in 2017, weighting coefficients which are calculated on the basis of unit values of the PRODCOM survey for 2010 and estimates of value added on the 3–digit level and 2–digit level of NACE Rev.2 obtained from annual SBS for 2010 were used.

The value added weights (activity structure) are calculated from the gross value added at factor cost on the basis of appropriate information from the SBS and corrected by the volume index of production to get an approximation of value added of the previous year. The value added weights (activity structure) are revised annually at the beginning of each year for the calculation of indices in the current year.  

03.6. Adjustment

The data is seasonally and calendar adjusted. More information about the seasonal adjustment please see added file.

 Annexes :
 Seasonal Adjustment

04. Quality managementTop
04.1. Quality assurance

The SORS aims to establish quality management system relying on the European Statistics Code of Practice. Also, the SORS adopted the Recommendation 4, Eurostat Leading Expert Group on Quality that concerns the system of quality management and the implementation of Business Excellence Model of the European Foundation for Quality Management (EFQM BEM). The document of quality policy is available on the statistical website:



04.2. Quality management - assessment

Industrial production index in industry is based on reliable survey data. The level of accuracy is high. Publication of results is punctual, and easy assessable. Industrial production index calculation is based on recommended international methodology. It is internationally comparable since follows EU and relevant international concept, definitions and classifications. Comparability over time is good. Republic of Serbia has required length of time series. Comparability with other statistical domains primarily the turnover in industry is satisfactory.

05. Relevance Top
05.1. User needs

Monthly Industrial production index measures changes in industrial production among two different time periods. Industrial production index is used for monitoring of current economic developments and for shortterm forecasts. It is used by internal users (Quarterly National Accounts), national users (Serbian National Bank, Ministry of finance, other government bodies, representatives of local government, economic analysts in institutes, companies and financial institutions, media, wide public) and international users (Eurostat, UN, IMF).

05.2. User satisfaction

User satisfaction is measured on the basis of downloading the data and by Users Satisfaction Survey. Results of that survey are available on the statistical website:

Special user satisfaction survey regarding shortterm indicators was not conducted so far.

05.3. Completeness

All time series of Industrial production index: total industry, MIGs, sections and divisions based on NACE Rev.2 (current base year=100), are available since 2000 according to STS Requirements.

05.3.1. R1. Data completeness - rate

Not applicable.

06. Accuracy and reliabilityTop
06.1. Overall accuracy

Since the response rate for the Monthly Survey of Industry is about 95% to 99%, overall accuracy is very good.

06.2. Sampling error

Sampling error is not measured. Industrial Production Index is calculating based on cutoff survey volume data.

06.2.1. A1. Sampling error - indicators for P (producers)

Not applicable.

06.3. Non-sampling error

Response rate is very high–about 95%.

Actions to reduce the nonresponse include sending the informative reminder letters to the respondents, telephone calls, sometimes visiting in case of medium or large sized enterprises.

In the case of unit nonresponse, some estimation methods are used prior to imputation: based on previous month record, based on production trends of this unit from the beginning of current year up to the end of the previous month, or based on same month of the previous year record.

In the case of item nonresponse the missing items are requested by telephone calls.

Technical errors are recognized with automated checks which are included in data editing process. A lot of checks are carried out automatically with human interaction.

There are very detailed tables to be checked each respondent on product level to find possible discrepancies.

Some aggregate checks exist. Data are checking on different level of aggregations firstly by persons responsible for particular activity divisions, then by supervisors and head of the Unit in charge of IPI calculation.

06.3.1. Coverage error

Not applicable. A 2. Over-coverage - rate

Not applicable. A 3. Common units - proportion

Not applicable.

06.3.2. Measurement error

Not applicable.

06.3.3. Non response error

Not applicable. Unit non-response - rate

Not applicable. A5. Item non-response - rate

Not applicable.

06.3.4. Processing error

Not applicable. A 7. Imputation - rate

Not applicable.

06.3.5. Model assumption error

Not applicable.

06.4. Seasonal adjustment

The data are seasonally and calendar adjusted. More information in added file.

 Annexes :
 Seasaonal Adjustment
06.5. Data revision - policy

Data revision policy is defined by the document General Revision Policy that is available on the web site,

A Vintage database currently does not exist. Also, there are some procedures in the Industry Statistics Unit.  Industrial production indices for all months of the current year are published and treated as ``preliminary results``.  At the end of the year, after possible changes they ``become`` final. Only final indices are available into statistical database posted on the SORS website. Data revision calendar does not exist. The same revision policy is applied for publishing of national data and for data transmitted to Eurostat.

06.6. Data revision - practice

Revisions are realized monthly. Revisions due to errors are implemented immediately after detection. The most of revisions of Industrial Production Index are realized because of the availability of more complete data, or additional corrections from respondents. Estimates are replaced with definitive figures when they are available. The most of minor revisions are performed at the beginning of the year, especially for January (new reference period, exchange of units, increased nonresponse etc.). Size of revisions was not measured so far. Monthly, there are approximately 520 minor changes on product level. The most of them does not affect higher levels of IPI (total industry, MIGs, sections). Statistical releases for months February to December contains revised data for the previous month. SORS has no practice to publish final Industrial Industrial production index indices in ``new`` Release form, but put them into statistical database. The users are informed that indices published in Statistical Release are ``preliminary data`` that might be changed.  Minor IPI revisions are not explaining to the users. Revised data are marked in footnotes in the relevant tables of Monthly statistical bulletin.

Also, some revisions are realized annually, when data from Annual industrial survey (Prodcom) are available. There is a confrontation with Prodcom data on product level during the period from April to June.

Regular revisions are realized in years ending by 0 or 5 due to the change of base year and weights. Users are informed on those revisions in Note on methodology which is a part of the Statistical Yearbook of the Republic of Serbia and in Note on methodology which follows the Nomenclature of industrial products for Monthly industrial survey. Also, there is a note which follows the IPI in statistical database.

06.6.1. A6. Data revision - average

Not applicable.

07. Timeliness and punctualityTop
07.1. Timeliness

The Industrial production indices are firstly published on the last working day in a month regarding previous month data. Monthly indices are transmitted to Eurostat in a proper form within required deadlines.

07.1.1. TP1. Time lag - first result

Not applicable.

07.1.2. TP2. Time lag - final results

Not applicable.

07.2. Punctuality

All data are published according to the announced Publications calendar. Link

Every deviation from the plan published in the Publications Calendar or in Press Calendar is previously announced and explained.

Also, there are no deviations from the planned deadlines at any stage of survey implementation.

07.2.1. TP3. Punctuality - delivery and publication

Not applicable.

08. Coherence and comparabilityTop
08.1. Comparability - geographical

Industrial production index is representative only for the country level it is not representative for the regions of the country.

SORS applies methodology, which is in line with international standards to calculate Industrial production index. The application of the STS methodological guidelines ensures a good comparability between national data and European aggregates. 

08.1.1. CC1. Asymmetry for mirror

Not applicable.

08.2. Comparability - over time

The monthly industrial production indices are presented as time series from January 2000.

Monthly time series for IPI are based on NACE Rev.2 on total industry (B+C+D) level, sections B, C and D (group 35.3 excluded), MIGs, and divisions level.

The transition from NACE Rev.1 to NACE Rev.2 for the period from January 2000 to December 2010 was performed by back casting on micro level. The time series are posted on the SORS website and transmitted to Eurostat.

08.2.1. CC2. Length of comparable time series for P (producers)

Not applicable.

08.3. Coherence - cross domain

There is a comparison of Monthly Survey of Industry with Annual Survey of Industry (Prodcom data). 

Comparison with the monthly index of turnover in industry shows a good compliance for total industry level. Also, with annual SBS results regarding value added at factor costs. Annual SBS results are used as weighting coefficient for divisions, sections and MIGs level in Industrial production index calculation. 

08.4. Coherence - sub annual and annual statistics

Not applicable.

08.5. Coherence - National Accounts

Not applicable.

08.6. Coherence - internal

The Serbian Industrial Production Index is annual chain–linked Laspeyres index. The IPI higher level indices are annually chain–linked using an annual overlap (annual average of the previous year). The chain linking is performed to hierarchical level of NACE Rev.2 activity divisions, sections, MIGs and total industry. IPI is internally consistent within available time–series since January 2000 for industry total, divisions, sections and MIGs. It is compiled as unadjusted, WDA and SA indices.

IPI adjustments are made for the industry total, MIGs, sections and divisions using direct method i.e. IPI time series are aggregated by NACE Rev.2 and by MIGs and then seasonal adjustments performed independently at each aggregate level

Coherence is achieved by compilation methods and weighting system. IPI for various levels of the NACE Rev.2 are calculated in two stages according to the Laspeyres formula. In the first stage, indices are calculated from quantity data on production of individual products according to the National Nomenclature of Industrial Products and an adequate weighting coefficient, which represents an estimated value added of individual products. In the second stage, all indices of divisions and higher levels are weighted with shares of value added of individual activities of industrial production by the NACE Rev.2 levels.

09. Accessibility and clarityTop
09.1. Dissemination format - News release

Press Release and Statistical Release are available each month to all users, free of charge, at 12 o’clock on stated day in the Press Calendar and Publications Calendar on SORS website.

09.2. Dissemination format - Publications

Statistical Release is published every month at 12 o`clock on the day specified in Publications calendar. This release is available in paper and electronic form, bilingual (Serbian, English) and accessible on statistical website. Statistical release contains unadjusted index of industrial production for total industry (B+C+D), MIGs, sections B, C and D (group 35.3 excluded) and divisions.  There are four types of unadjusted indices: referent month compared to average of previous year; referent month compared to the same month of the previous year; period from the beginning of the year to the end of referent month compared to the average of previous year; and period from the beginning of the year to the end of referent month compared to the same period of the previous year. There are some series of seasonally and calendar adjusted industrial production indices for total industry (B+C+D), and for section C (Manufacturing).

Monthly statistical bulletin, it is complex publication in paper and electronic form, bilingual (Serbian, English) and accessible on statistical website. Table that presents industrial production indices is in the Industry chapter. The table contains unadjusted industrial production index for total industry (B+C+D), MIGs, sections B, C and D (group 35.3 excluded). In the current year monthly indices show changes compared to the average of the previous year. In the previous year, monthly index shows the change compared to the average for that year.

Statistical Yearbook of the Republic of Serbia - chapter Industry and Statistical Pocketbook of the Republic of Serbia comprises a summary of annual data of industrial production indices.

09.3. Dissemination format - online database

The database contains unadjusted indices of industrial production indices within the theme Industry. Industrial production indices are given for total industry (B+C+D), MIGs, sections B, C and D (group 35.3 excluded) and divisions. Industrial production indices are available from January 2000 to December of previous year. Also, annual indices from 2000 to the previous year are presented. All indices are available calculated on the base year. Also, indices calculated on the previous year as a base year are available. The database is available on line to all users. The frequency of updating is annually.

Link to the statistical database    

Additionally, time series for ‘’last 13 months’’ based on the current base year are available on SORS website :    (Additional tables)




09.3.1. AC1. Data tables - consultations

Not applicable.

09.4. Dissemination format - microdata access

Micro data are neither distributed nor provided to the users.

09.5. Dissemination format - other

Current data are sent monthly to Eurostat via eDamis. Also, there is dissemination on ad-hock request: Special tables may be obtained from the ”Relations with users and eservices".

09.6. Documentation on methodology

It is used the Eurostat`s document: Methodology of Shortterm Business Statistics, Interpretation and guidelines, 2006.

National methodological document, based on Eurostat`s document, is available on the statistical website:


09.7. Quality management - documentation

Not available.

09.7.1. AC 3. Metadata completeness - rate

Not applicable.

09.7.2. AC 2. Metadata - consultations

Not applicable.

10. Cost and BurdenTop
10. Cost and Burden

No information.

11. Confidentiality Top
11.1. Confidentiality - policy

National confidentiality policy is defined in Official statistics law (Official Gazette of the RS``, No. 104/2009)

11.2. Confidentiality - data treatment

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

12. CommentTop
12. Comment