STATISTICS AUSTRIA

Directorate “Business Statistics” - Indicators, STS Coordination

Guglgasse 13, 1110 Wien, Austria

It is the objective of the production index to measure changes in the volume of output in monthly intervals. The production index is also used for estimation purposes in national accounts.

A common survey for industrial and construction output is used.

NACE Rev. 2

Activity coverage: Sections B to F of NACE Rev. 2 on 2-digit level.

Size coverage: Employment-size-classes with at least 20 persons employed and turnover-size-classes with a turnover threshold of EUR 1,5 million excl. VAT  per year for NACE 05-42 and EUR 2,5 million excl. VAT per year for NACE 43, taking into account that 90% for NACE 05-42 respect. 60% for NACE 43 of national production in each NACE Division should be represented.

The index shows the evolution of the physically measurable value added at basic prices. The coverage is about 90% (in production value) of the total production of NACE Rev.2 Sections B, C, D, E and F.

Definitions correspond to the Commission Regulation No. 1503/2006 (Variable No. 110).

In the monthly STS-survey the "Production in the reporting period" is collected as follows:

1. Own output intended for sale (with reference to commodity list 1)

2. Own output for further processing

3. Own output intended for in-house sales and services

4. Subcontracted work carried out by the observation unit as a subcontractor (referring to commodity list 1)

5. Production sold (in accordance to commodity list 1 and 2)

6. Production intended for sale (in cases of PRODCOM-references)

The basis for the calculation of the production index is the "technical production" (the sum of points 1, 3 and 4) and if the technical production is not available the production sold (point 5) is used.

Information about the different variables and their definitions can also be found on the website of Statistics Austria: 

https://www.statistik.at/fileadmin/shared/QM/Standarddokumentationen/U/std_u_konjunkturindikatoren_prod-bereich_basis-2015_oenace-2008.pdf

https://www.statistik.at/fileadmin/shared/QM/Standarddokumentationen/U_en/engl_std_u_konjunkturindikatoren_prod-bereich_basis-2015_oenace-2008.pdf 

Reporting unit: either the enterprise itself or the KAU (in case of multi-activity enterprises with a principal activity outside the NACE Rev.2 Sections B to F)

Observation unit: KAU

The target population (NACE Sections B to F) is approx. 80,400 (effective 12/2022)  single- and multi-establishment-(multi-activity-) enterprises (NACE Sections B to E: 38,100 enterprises; NACE Section F: 42,300 enterprises);

Approximately 10,700 establishments (Betriebe; KAU) are involved in the calculation of the production index (NACE Sections B to F) (effective 2022); for NACE Sections B to E: 6,000 establishments and for NACE Section F: about 4,700 establishments

Data source: Business Register.

The geographical area covered is Austria and its nine federal provinces (Bundesländer).

NACE Rev.2
Base 2015: from 01/2015 onwards

Base 2010: from 01/2010 until 12/2017
Base 2005: from 01/2009 until 12/2012; backcasted data back from 01/1996

NACE Rev.1.1
Base 2005: from 01/2005 to 12/2008
Base 2000: from 01/2000 to 12/2007
Base 1995: from 01/1996 to 12/2002

Base year: 2015

Reference year: 2022

STS-indicators are published as indices at t+40.

Absolute figures for STS in production and construction are published nationally at t+90.

The production index is calcuated and published monthly.

Legal basis:

The "Federal Statistics Act 2000" ("Bundesstatistikgesetz 2000", Federal Law Gazette I No. 163/1999) passed in August 1999 is in force since January 2000. The "Bundesstatistikgesetz 2000" was consolidated to the "Bundesstatistikgesetz 2000 - konsolidierte Fassung 2009" (BGBl. I No. 163/1999 as amended by BGBl. I No. 136/2001, BGBl. I No. 71/2003, BGBl. I No. 92/2007, BGBl. I No. 125/2009, BGBl. I Nr. 111/2010, BGBl. I Nr. 40/2014, BGBl. I Nr. 30/2018 and BGBl. I Nr. 32/2018).

EU regulation (current and historical) 

In addition there is a national regulation concerning the monthly sample survey on short-term statistics for NACE Sections B to F: "Konjunkturstatistik im Produzierenden Bereich", BGBl. II No. 210/2003 as amended by BGBl. II No. 70/2005, BGBl. II No. 315/2007 and BGBl. II Nr. 327/2013.

Obligation on units to provide data:

There is a legal obligation for the units to provide data. Any respondent refusing to provide the required information may be punished by the local administrative authority.

STS data are transmitted, in addition for Eurostat, directly to other international organisations like OECD, UN and Eurostat.

The general obligation to publish statistics and the strict provision on statistical confidentiality is regulated by the “Federal Statistics Act 2000” ("Bundesstatistikgesetz 2000") in the consolidated version of "Bundesstatistikgesetz 2000 - konsolidierte Fassung 2009” (BGBl. I No. 163/1999 as amended by BGBl. I No. 136/2001, BGBl. I No. 71/2003, BGBl. I No. 92/2007, BGBl. I No. 125/2009, BGBl. I Nr. 111/2010, BGBl. I Nr. 40/2014, BGBl. I Nr. 30/2018 and BGBl. I Nr. 32/2018).

The protection of personal data is covered by the “Data Protection Act 2000” ("Datenschutzgesetz 2000 (DSG 2000)", Austrian Federal Law Gazette I No. 165/1999 last amended by BGBl. I No. 14/2019).

Aggregations of data including less than 3 establishments are considered confidential and are therefore not published.

A release calendar covering release dates of the first/second half of the year is published on the website of Statistics Austria.

https://www.statistik.at/en/medien/release-calendar

Simultaneous release to all interested parties:

No users have prior access to the data before its general release. Data are made available to all users simultaneously in the Statistics Austria press release, which is disseminated by the Austrian Press Agency. The press release is also available on the website of Statistics Austria.

Transmission to Eurostat and further use of the statistics:

According to the release calendar data are transmitted to Eurostat at the same time of national publication 40/70 days after the end of the reference month. At the time of national publication  unadjusted as well as working day, seasonally and trend-cycle adjusted data are transmitted to Eurostat via eDAMIS (without the breakdown for the 9 "Bundesländer"/provinces) using SDMX. The level of detail corresponds to the 2-digit-level of NACE Rev. 2 and aggregations (MIGs,  total industry (Eurostat: Sections B to D without D353 and E, National: Sections B to E)).

The production index is further used for estimation purposes in national accounts and is also transmitted to the Austrian National Bank, OECD and UN.

Monthly

Data are made available in the Statistics Austria press release, which is disseminated by the Austrian Press Agency. The press release is also available on the website of Statistics Austria.

Frequency: monthly

Activity Coverage: NACE Rev. 2 Section B to F (splitted in Section B to E and Section F); 5 MIGS (capital goods, consumer durable and non-durable consumer goods, intermediate goods, energy);

Length of time series: month, compared to corresponding month of the previous year as well as to the previous month

Presentation: calendar adjusted, seasonal adjusted

• Press releases
• STATcube
• "Statistics in short" in "Statistische Nachrichten" (monthly)
• Facts & Figures ("Österreichischer Zahlenspiegel")
• Austrian.Data.Figures.Facts
• "Statistisches Jahrbuch Österreichs 20xx" (Austrian Statistical Year Book) - chapter 20 and 43
• Austrian Economic Atlas (Wirtschaftsatlas Österreich)

Data are released in the online database „STATcube” on the website of Statistics Austria:

http://statcube.at/statcube/opendatabase?id=dekjiprodindex2015

Frequency: monthly

Activity Coverage: NACE Rev. 2 Section B to F (F splitted in building construction and civil engineering), NACE Rev. 2 Division 05 to 43; MIGS (capital goods, consumer durables and non-durables, intermediate goods, energy) and selected aggregates;

Length of time series:

- from 01/2009 to 12/2012 (NACE Rev.2, Base 2005); backcasted data to 1996

- from 01/2010 to 12/2017 (NACE Rev.2, Base 2010)

- from 01/2015 (NACE Rev.2, Base 2015)

 Presentation: unadjustedf, calendar adjusted, seasonally adjusted, trend cycle, nine federal provinces (Bundesländer; NUTS2)

Not available.

Data are sent to Eurostat to be used in European aggregates and/or to be released as national data.

Dissemination of documentation on methodology and sources used in preparing statistics:

Standard-Documentation: covers different aspects of a statistical product like administrative information, conceptual aspects, production of the statistics and publication of resulting figures. Complementing the detailed information on all phases of the statistical production process and the description of the statistical concepts as well as the applied methodology the last chapter refers to quality.

Konjunkturindikatoren im Produzierenden Bereich – Basisjahr 2015 

Konjunkturindikatoren im Produzierenden Bereich – Basisjahr 2010

Konjunkturindikatoren im Produzierenden Bereich - Basisjahr 2005 - ÖNACE 2008

Konjunkturstatistik im Produzierenden Bereich ab 2008

Methodological Papers:

• Statistische Nachrichten 7/2018: Konjunkturindikatoren im Produzierenden Bereich: Neues Basisjahr 2015
• Statistische Nachrichten 7/2013: Konjunkturindikatoren im Produzierenden Bereich: Neues Basisjahr 2010
• Statistische Nachrichten 7/2009: Umstellung der Konjunkturindikatoren im Produzierenden Bereich auf die ÖNACE 2008
• Statistische Nachrichten 11/2007: Konjunkturindikatoren im Produzierenden Bereich: Neue Basis 2005=100
• Statistische Nachrichten 6/2005, S. 567ff.: Saison- und arbeitstägige Bereinigung des Produktionsindex sowie des Umsatzindex im Produzierenden Bereich
• Statistische Nachrichten 4/2004, S.340ff.: Wiederaufnahme der Berechnungen von Produktivitätsindizes mit der Basis 2000=100
• Statistische Nachrichten 10/2003, S. 776ff.: Konjunkturindikatoren im Produzierenden Bereich: Neue Basis 2000=100
• Statistische Nachrichten 6/1999, S. 479ff.: Neuberechnung des Produktionsindex mit der Basis 1995=100
• Statistische Nachrichten 5/1999, S. 382ff.: Arbeitstägige Bereinigung des neuen Produktions­index
• Statistische Nachrichten 10/1997, S. 866ff.: Neue Indizes im Sachgüterbereich – Konzepte und methodische Grundlagen

Further sources:

• „Beiträge zur österreichischen Statistik" (Contributions to Austrian Statistics):

- Konjunkturindikatoren (2000=100) Produktion und Dienstleistungen.
- Konjunkturerhebung im Produzierenden Bereich 200x: Band 1: Ergebnisse auf  Unternehmens- und Betriebsebene sowie Indizes

• "Monatliche Schnellberichte" (Monthly Rapid Reports):

Schnellbericht Konjunkturstatistik, Produzierender Bereich – Unternehmensdaten
Schnellbericht Konjunkturstatistik, Produzierender Bereich (Bergbau und Gewinnung von Steinen und Erden, Herstellung von Waren, Energieversorgung, Wasserver- und -entsorgung, Abfallentsorgung) – Betriebsdaten (exkl. Bauwesen)
Schnellbericht Konjunkturstatistik, Produzierender Bereich – Betriebsdaten (Bauwesen)

• IMF (SDDS)
• OECD Main Economic Indicators

Quality report: Documentation on methodology and sources (Standard-Dokumentation)
Standard-Dokumentation: covers different aspects of a statistical product like administrative information, conceptual aspects, production of the statistics and publication of resulting figures. Complementing the detailed information on all phases of the statistical production process and the description of the statistical concepts as well as the applied methodology the last chapter refers to quality.

Konjunkturindikatoren im Produzierenden Bereich – Basisjahr 2015

Konjunkturindikatoren im Produzierenden Bereich – Basisjahr 2010

Konjunkturindikatoren im Produzierenden Bereich - Basisjahr 2005 - ÖNACE 2008

Konjunkturstatistik im Produzierenden Bereich ab 2008

Quality checks and validation of data are done throughout the whole compilation process. This is described in the standardised metadata and quality report for short-term statistics concerning NACE Sections B to F on the website of Statistics Austria (Standard-Dokumentation):

Chapter 3 “Quality” of this national quality report contains the following points:

• relevance
• accuracy (sampling Errors, non-sampling-errors, revisions, …)
• timeliness and punctuality
• accessibility and clarity of the information
• comparability
• coherence with other statistics

Relevant changes are discussed with national experts and the Quality Committee of the Statistical Council of Statistics Austria for feedback and modification suggestions.

Indices are based on reliable data;

Publication of results are always punctual;

Further methodological details and other information can be found in point 13;

Multiple plausibility checks with different sources are done.

Short-term statistics are used by different national and international institutions and non-institutional users:

• Institutions: Federal Ministries, Federal Chancellery of the Republic of Austria, National Central Bank (OeNB), political institutions (e.g. parliament), local authorities, Austrian Institute of Economic Research
• International institutions: Eurostat, ECB, OECD, UN, IMF
• Social actors: social partners, trade unions
• Researchers and Educational Institutions
• Media
• Enterprises/businesses
• Internal users
• Public

No index for user satisfaction is available, but there are regular meetings with national experts and essential users to react to new requirements, if these are in contrast with legal necessities or not in constraints.

Every year an advisory board for enterprise statistics is held where concepts and new developments are presented and discussed.

The production index is fully compliant regarding STS-Regulation.

The overall accuracy could mainly be influenced by non-sampling errors due to a surveyed cut-off census. Accuracy can change by response rate, data collection and/or imputation errors. Checks are done on micro- and macro-level when data are processed.

As the data base of the index are absolute figures for STS in production and construction which are surveyed by cut-off census, it is not possible to indicate a classical sampling error.

Coverage errors

The survey is compulsory. The response rate for industry and construction is about 69.5% 40 days after the end of the reference period and about 96.7% 70 days after the end of the reference period. When the final index is compiled, it is around 98.9%. Missing responses are requested by telephone contacts followed up by two postal reminders.

• Coverage - classification errors and over coverage:
  • are observed especially at the reference periods of January due to changes of the respondent units (i.e. deaths of enterprises, changes in enterprise structures, new classifications).
  • are identified through ex post contacts to concerned enterprises and through comparison with registers and other secondary sources.
  • in general the survey results have to be corrected 0.2 - 0.4% downwards.
• Under coverage:
  • One of the reasons is the loss of responding units due to false classifications and the difficulty to find alternative enterprises during the reference year
  • yet it is not possible to quantify the undercoverage rate
• Multiple listings:
  • Due to duplication checks multiple listings are prevented.

Data collection errors

• Online Survey instrument: Misunderstanding of the questionnaire by respondent or missing values due to downtime of the questionnaire.

• Plausibility checks within the questionnaire at high variance with previous values.

• Questionnaire has to be competed without missing values and correct format (character or numeric).

• Respondent: transmission of erroneous data.

• Continuously quality- and plausibility improvements by staff and feedback by respondents.

• Hyperlink to questionnaires: https://www.statistik.at/en/ueber-uns/erhebungen/unternehmen/konjunkturerhebung-im-produzierenden-bereich

Unit and item non-response (missing data)

Reasons for Unit non-response and Item non-response are:

• Reporting delays

• Reporting refusals

• Non-response due to cessation of business

Imputation is performed by automation supported substitution methods.

Data processing errors

A lot of checks are carried out at the micro and macro data level. For example the following processing errors (“Aufarbeitungsfehler”) may occur:

A) Treatment on micro-data-level

• Human errors during the data editing process: these errors are often recognized with automated checks

• Imputation errors: the imputed value is not within a plausible range

• Plausibility errors: a lot of checks are carried out automatically (but under possibility of human interaction): e.g. check of completeness/ sums/ horizontal logical dependences/ vertical relations/ average rates/ minimum-maximum values,….

The qualified checking of original respondent data, contacts to reporting units for corrections and the usage of sophisticated plausibility routines shall minimize the processing errors on micro-data-level.

B) Treatment on macro-data-level

• Final checks with analyse-tables (aggregates / more complex relations). These tables include all variables of the STS-survey.

The macro data tabled are verified by computer programs but also by the staff whether these macro-data as publication figures look plausible. The persons responsible for the index calculation have their own computer programs to test the index-plausibility of the different data at 3- and 2-digit-level and for all aggregates.

If inconsistencies are detected the data must be verified at micro-level again by using the raw data of the questionnaire. Then the macro data are corrected by using a display editor and a display mask.

Afterwards, the plausibility check is started again until the figures look plausible.

About 50 cases of the original data are corrected (= number of corrected cases at the sample).

Model errors

• Model effects, like

Imputation errors: the usage of previous period values tends to result in under- or overestimating the real development (especially if big enterprises' volatile values are missing).

At the end of the reference month, e-mail-reminders are sent to the reporting units asking to fill out the electronical/web-questionnaire by the 15^th of the following month.

According to the release calendar the production index is published 40 days (preliminary results) and 70 days after the end of the reference month. In August of year t+1 the index of year t is considered to be final (response rate approximately 98.9%).

All deadlines are respected. There are no time lags between the actual delivery of the data and the target date when it should have been delivered.

Due to harmonised STS indices in the European Union, it is possible to compare calculated Austrian aggregates with those of other European countries. Moreover, the production index is provided to UN on ISIC Rev. 4 to enable further country comparisons.

Moreover, the Production index covers all nine federal provinces (Bundesländer; NUTS2) of Austria covering same concepts and definitions.

To ensure comparability over time, it is tried to keep the data base as steady as possible. With corrections of the base, changes are taken into account.

Moreover, STS indices are compared over time (previous month and year).

For NACE Rev.2, data from 1996 onwards is available (Base 2015: from 01/2015 onwards; Base 2010: from 01/2010 until 12/2017; Base 2005: from 01/2009 until 12/2012; backcasted data back from 01/1996).

There are no breaks in series.

Cross-checks with

• absolute STS data in industry and construction
• compare over period: compare with previous STS-values (previous month and year)
• SBS data (e.g. activity, turnover)
• Other surveys e.g. foreign trade statistics, surveys on material input

Cross-checks with other STS-variables, e.g. turnover, new orders surveys. Higher aggregates are coherent with the lower levels.

In the context of a co-operation contract between Statistics Austria and the Austrian Federal Economic Chamber signed in 2001, a system to monitor the development of the response burden was developed which was called “response burden barometer”. The response burden barometer provides a quantitative and objective indicator on the response burden and its development over time. The results for Short-term statistics in Industry and Construction can be found on the website of Statistics Austria: https://www.statistik.at/en/services/tools/services/response-burden-barometer

The costs and burden have declined since 2009 due to the implementation of the electronical/web questionnaires.

This revision policy is described in footnotes to the relevant tables and in the description of the respective statistics (http://statcube.at/statistik.at/ext/superweb/loadLocale.do?language=en&country=)

Methodological changes are announced at the time of change and published in the monthly bulletin "Statistische Nachrichten". There is at least one quarter advance notice of major changes in methodology by including footnotes in the respective tables.

Revisions are made regularly:

• preliminary data are published 40 days after the reference period (the data are marked as "preliminary data")
• revised data are published at t+70

The release calendar including revisions is published in advance.

The index becomes final in August of the following year.

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

In case of an error (non-scheduled revision), data are revised and published again.

Provision of information about revision and advance notice of major changes in methodology

In 2022, the monthly revisions were in the range of +/-1 comparing the annual rates of change of t+40 and t+70 for the unadjusted series of the total production index (B-F).

Because of working day and seasonal adjustment, the indices are revised backwards for the whole time series.

MR (2020-2022; cal. adjusted; monthly) 0.61

MAR (2020-2022; cal. adjusted; monthly) 1.37

Type of source: Statistical sample survey (cut-off census).

Frame on which the source is based: Business Register (UR - "Unternehmensregister").

Sample: The survey population is drawn from the business register as a non-representative, concentrated sample (cut-off sample) on the basis of employment and turnover size classes.

The target population (NACE Sections B to F) is approx. 80,400 (effective 12/2022)  single- and multi-establishment-(multi-activity-) enterprises (NACE Sections B to E: 38,100 enterprises; NACE Section F: 42,300 enterprises);

Approximately 10,700 establishments (Betriebe; KAU) are involved in the calculation of the production index (NACE Sections B to F) (effective 2022); for NACE Sections B to E: 6,000 establishments and for NACE Section F: about 4,700 establishments

Threshold values and percentages: Employment-size-classes with at least 20 persons employed and turnover-size-classes with a turnover threshold of EUR 1,5 million excl. VAT per year for NACE 05-42 and EUR 2,5 million excl. VAT per year for NACE 43, taking into account that 90% for NACE 05-42 respect. 60% for NACE 43 of national production in each NACE Division should be represented.

Frequency of updating the sample: Yearly.

Data are collected on a monthly basis.

For Sections B to F of NACE Rev. 2 there is one STS-survey ("Konjunkturerhebungen im Produzierenden Bereich") that collects information on production, turnover, new orders, and labour input on a monthly basis with a specific set of questionnaires, depending on the structure of the observation unit. The overall types of questionnaires are for one-establishment-enterprises, for multi-establishment (multi-activity) enterprises and for establishments/LKAU of multi-establishment/multi-activity-enterprises.

To make the provision of data easier for enterprises, Statistics Austria is keen to further develop electronical questionnaires. Therefore, in 2012, data collection for STS in Production and Construction was changed to electronical-/web-questionnaires. Paper questionnaires are only available on request.

As far as data validation is concerned the validation levels as defined by Eurostat are carried out:
The structure of the file and the format of the data is checked; plausibility checks and consistency checks are carried out.

More information on tools and rules used for validation can be found in point 13.3.

Estimates for non-response: Non-response is treated by imputation from the results of previous periods.

Type of index: The Austrian Production Index is a fixed base year Laspeyres (volume) index (current base 2015=100) whose weights and basket of goods are revised every five years.

Method of weighting and chaining: Gross production values at product level, and value added at aggregated level. The weights are based on gross value added at factor costs derived from structural business statistics and applied to deflated value relatives.

Frequency of weight update: every 5 years.

Initially, a constant basket of goods with constant weights over the index period (that is, until the revision of the base year) is defined. The product groups and the weights are determined by production values and the valued-added of each branch in the base year (currently 2015) and they together provide the index base. Production values are observed and are directly compiled by applying the Laspeyres formula (production of reference month t is set in relation to production in base period 0). The index numbers are built by deflating the production values. Deflators used are the producer price index, construction output price index, wholesale price indices, consumer price indices and the index of agreed minimum wages and salaries.
Working day, seasonal and trend-cycle adjustment are carried out by using X-13 ARIMA-SEATS.

No comment.