ISTAT - Istituto Nazionale di Statistica
Euro-SDMX Metadata Structure Definition (ESMS_MSD 3.0 ESTAT)
Turnover in industry
2018 - A0
1. Contact
1.1 Contact organisation

Istat - Italian National Statistical Institute

1.2 Contact organisation unit

SED - Division for short-term business statistics

1.3 Contact name

Process manager: Anna Ciammola

1.4 Contact person function

Process manager: Anna Ciammola - Researcher, Division for short-term business statistics.

1.5 Contact mail address

Via Tuscolana, 1788 00173 Rome Italy

1.6 Contact email address

Process manager email: ciammola@istat.it

1.7 Contact phone number

Process manager telephone: +390646736659

1.8 Contact fax number
2. Metadata update
2.1 Metadata last certified

26/04/2018

2.2 Metadata last posted

26/04/2018

2.3 Metadata last update
26/04/2018
3. Statistical presentation
3.1 Data description

Industrial turnover index

The main topics observed are: Industrial enterprise turnover, New orders received in industry
3.2 Classification system

NACE Rev. 2.

3.3 Coverage - sector

NACE Rev. 2 Sections B and C.

Indices for sector 07.2 are not compiled since it is not significant.

Indices for secotors 05.1,05.2,07.1 and 09.9 are not compiled since phenomeon does not exist.


3.4 Statistical concepts and definitions

Turnover includes the total invoiced by the observation unit during the reference period and referred to market sales of goods or services supplied to third parties. Turnover also includes all other charges (transport, packaging, etc.) applied to the customer, even if these charges are listed separately in the invoice.

Turnover excludes VAT and other similar deductible taxes directly linked to turnover as well as all duties and taxes on the goods or services invoiced by the unit. Reduction in prices, rebates and discounts as well as values of returned packing must be deducted.

More details are available in the Commission Regulation 1503/2006.

The indices of domestic and non-domestic turnover are split according to the first destination of the product based on the change of ownership. The destination is determined by the residency of the third party purchasing goods and services. Non-domestic turnover is further sub-divided into turnover towards to euro-zone countries and to all other countries. 

3.5 Statistical unit

The observation unit is generally the enterprise.

In some special cases, the observation unit is the activity close to the kind-of-activity unit (KAU).

The observation unit is the same as the reporting unit.

3.6 Statistical population

The following rules are applied to define the statistical population of each 3 digit NACE sectors:

A)    Enterprises with at least 20 employees.

B)     Enterprises with less than 20 employees if rule A) does not guarantee a statistical population of at least 20 statistical units.

C)     All the enterprises for very small sectors with less than 20 enterprises.

The total number of enterprises is about 29,500 out of 391,700 enterprises in the Italian territory whose main activity belongs to NACE sections B and C according to the last official release of the business register (reference year 2017).

3.7 Reference area

Italy without geographical breakdown

3.8 Coverage - Time

Since January 2000.

3.9 Base period

Year 2015=100

4. Unit of measure

Index

5. Reference Period

Month

6. Institutional Mandate
6.1 Institutional Mandate - legal acts and other agreements

Legal basis:

National level: The survey is compulsory as stated every year in a Decree of the President of the Republic (D.P.R.).

European level:

Council Regulation No 1165/1998 Council Regulation No 1165/1998 of 19 May 1998 Introducing short-term statistics at European level;

Regulation (EC) of the European Parliament and of the Council 1158/2005  (Council Regulation No1158/2005) amending Regulation 1165/98 introducing the European sample schemes, industrial import prices, output prices for services and other changes.

Commission Regulation 1503/2006 (Commission Regulation 1503/2006) defining variables and frequency of data compilation, repealing new orders received for building construction and new orders received for civil engineering

Commission Regulation 656/2007 (Commission Regulation 656/2007 )    on the definition of main industrial groupings (MIGS) in NACE Rev. 2.

Commission Regulation 472/2008 (Commision Regulation 472/2008 ) introducing the new base year 2005 and the statistical classification of economic activities, NACE Rev. 2, into short-term statistics.

Commission Regulation 1178/2008 (Commission Regulation 1178/2008 ) introducing further adaptations for European sample schemes in relation to the new economic classification.

Commission Regulation  461/2012 ( Commission Regulation 461/2012) repealing industrial new orders

 

Data provision is mandatory. Penalties are foreseen for non-respondent large enterprises with at least 100 employees.

6.2 Institutional Mandate - data sharing

Not available

7. Confidentiality
7.1 Confidentiality - policy

Confidentiality provisions are explicitly stated in the Istat President’s letter attached to data collection questionnaire along with references to different legal acts on statistics.

Links to relevant legal acts on statistics are also listed on the website of Sistan - National Statistical System - (http://www.sistan.it/index.php?id=203).

Several national legal acts guarantee the confidentiality of data requested for statistical purposes. According to art. 9, paragraph 1 of the Legislative Decree n. 322 of 1989, personal data cannot be disseminated but in aggregated form, in order to make it impossible to make any reference to identifiable individuals. They can only be used for statistical purposes. Legislative Decree n. 322 of 1989, art. 6 bis and Legislative Decree n. 196 of 2003 Annex A3 (Code of conduct and professional practice applying to the processing of personal data for statistical and scientific research purposes within the framework of the national statistical system), art. 8, provide that the exchange of personal data within the National Statistical System (Sistan) is possible if it is necessary to fulfil requirements provided by the National Statistical Programme or to allow the pursuit of institutional purposes. The supply of the identification data of statistical units is allowed within the framework of entities included in the National Statistical System if the requesting party declares that no identical statistical result can be obtained otherwise. Regarding subjects who do not belong to Sistan, Article. 7 of the Code of conduct (Decree n. 196/2003, Annex A3) states that it is possible to transmit individual data files without direct identifiers within the framework of specific laboratories set up by entities included in the National Statistical System, under certain conditions and only if that the data are protected by the application of different statistical methods that make it highly unlikely the identification of statistical units.

7.2 Confidentiality - data treatment

9 of 101 elementary series are confidential according to three digit NACE Rev. 2, for domestic, non-domestic and euro area turnover. Non confidential data are available at http://dati.istat.it/?lang=en

According to the article n. 9 of the Legislative Decree n. 322 of 6 September 1989 data collected by statistical offices within the statistical surveys included in the National Statistical Programme may not be disclosed other than in aggregated form such that no reference to identifiable people can be extracted. Furthermore, they may be used only for statistical purposes. Data may not be communicated or disseminated either to any external subject, public or private, or to any department of the public administration other than in aggregate form and using modalities which prevent the identification of the people involved. In any case, data cannot be used to identify again the people involved. The Code of Conduct annexed to the Legislative Decree no. 196 of 30 June 2003 (Personal Data Protection Code) provides special rules concerning the processing of personal data for statistical purposes within Sistan. In order to make statistical secrecy and protection of personal data effective, Istat is currently taking appropriate organisational, logistical, methodological and statistical measures in accordance with internationally established standards.

In accordance with the Legislative Decree no. 196 of 30 June 2003 (Personal Data Protection Code) and subsequent modifications and additions, respondents are informed of their rights and obligations with regard to the provision of information, and they are assured that the information they provide will be used for statistical purposes only.

All euro area/non euro area time series are confidential (confidentiality is planned to be removed).
8. Release policy
8.1 Release calendar

Every year in December ISTAT publishes a release calendar providing the precise release dates for the coming year. The calendar is distributed to the press and is available free of charge to interested parties.

8.2 Release calendar access

The release calendar is available on the ISTAT website https://www.istat.it/en/information-and-services/journalists/release-calendar

8.3 Release policy - user access

1)      Turnover indices and new orders indices are released on the Istat datawarehouse (dati.istat.it) at 10:00 on the release day to all users.

2)      Turnover indices are sent to Eurostat using SDMX format through the EDAMIS web portal on the release day.

Turnover indices (general indices and MIGS, for domestic market, non-domestic market and total) are available in unadjusted, calendar adjusted and seasonally adjusted form. Total turnover indices referred to SNA/ISIC sub-sections are available in unadjusted and calendar adjusted form. All other indices are available only in unadjusted form.

New orders indices are available only in unadjusted form, with the exception of total indices for domestic, non-domestic and total market that are also disseminated in seasonally adjusted form.

9. Frequency of dissemination

Monthly.

According to the previous dissemination policy (till 2018), indices referred to June were provided only to Eurostat and the press release was not published in August.
10. Accessibility and clarity
10.1 Dissemination format - News release

Data are released simultaneously to all interested parties by issuing the press releases “Fatturato e ordinativi dell’industria” and "Industrial turnover and orders" posted on the Istat website at the pages https://www.istat.it/it/industria-e-costruzioni (Italian version) and https://www.istat.it/en/industry-and-construction (English version). Media are provided with the embargoed copy of the press release 30 minutes before to the actual dissemination.

Both versions of the press release include a brief methodological note, while the weighting structure and some aggregated time series (total indices and MIGS) are available only at the Italian web page.

Previous press releases are available at the web pages http://www.istat.it/it/archivio (Italian version) and http://www.istat.it/en/archive(English version) filtered through the tag “Fatturato e ordinativi” and “Turnover and orders”, respectively.
10.2 Dissemination format - Publications

Data are made available also through yearly publications:

1) Annual Report: Rapporto Annuale 2018

2) Italian Statistical Yearbook: Annuario Statistico Italiano 2018

10.3 Dissemination format - online database

Series are included in I.Stat, the Istat datawarehouse (I.Stat), theme “Industry and Construction”, sub- theme “Industrial new orders and turnover index” datasets “Industrial new orders-monthly data (base 2015), Industrial turnover – Monthly (base 2015)

The on-line database I.Stat is open and free, statistics are organised by theme in a two-level hierarchical tree. Data are presented in aggregate form in multidimensional tables; acting on variables and reference periods and arranging heads and sides users can customize tables and graphs.

Datasets can be searched by keyword, theme and region.

A wide range of standard metadata facilitates the retrieval and understanding of statistics by users.

More information available in the User Guide

10.4 Dissemination format - microdata access

Before data dissemination, validated microdata are stored in the repository of the Institute, ARMIDA (ARchive of validated MIcroData).

ARMIDA was established with the main objective of preserving and documenting the data produced by Istat surveys, and has subsequently supported the objective of disseminating data. The data stored in ARMIDA supplies, in fact, the different channels for the dissemination of microdata (to internal users according to the “Memorandum of access to microdata of ARMIDA”, to authorities in Sistan, for research files, for standard files, etc.).
10.5 Dissemination format - other

Data are available as national data in the Eurostat database (Eurobase, theme “Industry, trade and services”, sub-theme “Short-term business statistics”

10.6 Documentation on methodology

A short description of the methodology and the main features of the survey are contained in a technical explanatory note attached to the monthly press release. It is regularly updated.

The transition to a new base is generally documented through a technical note named “Nota informativa”. Concerning the introduction of base 2015=100, the Nota informativa 2018 is always available along with the monthly press releases.

10.7 Quality management - documentation

Quality documentation is available through SIQual, the Istat Information System on QUALity of statistical production processes (http://siqual.istat.it/SIQual/lang.do?language=UK ). It contains information on both statistical processes and on activities implemented in Istat in order to guarantee quality of the produced statistical information. 

11. Quality management
11.1 Quality assurance

Since the 90s Istat adopted a systematic approach to ensure quality in both statistical information and service to the community. For this purpose the Institute has defined a quality policy providing itself with appropriate tools as well as management changes to carry it out. Istat quality policy is coherent with the European framework developed by Eurostat, taking up its main principles and definitions. In 2005, the European Statistics Code of Practice (revised in 2011) established the principles to follow in order to ensure and strengthen both accountability and governance of the European Statistical System and the National Statistical Systems inside it.

Essential points of Istat quality policy are:

1)      Process quality: consisting in the production of accurate statistical information efficiently and effectively;

2)      Product quality: consisting in the dissemination of high-quality timely statistical data which are relevant for the users, also the potential ones;

3)      Documentation: consisting in the storage and availability of information necessary not only for a proper use of data but also to ensure transparency in all the production activities of statistical data;

4)      Respect for respondents: consisting in the reduction of response burden and in the respect of respondent's privacy;

5)      Strengthening of statistical literacy: consisting in promoting a proper use of statistical information in policy-making to better support decisions and policies;

6)      Users' orientation: consisting in making statistical information easily accessible and understandable and in satisfying user needs as much as possible.

For details: http://www.istat.it/en/about-istat/quality

11.2 Quality management - assessment

In 2011 this survey was submitted to an audit on quality in a testing phase http://www.istat.it/en/tools/data-quality/audit

As regards main issues of quality, index is compliant with a good standard. Eurostat's requirements in terms of time series are fulfilled, timeliness is respected and checks are implemented for monitoring cross-domain coherence.

The process was submitted to Quality statistical auditing for the 2010 edition

12. Relevance
12.1 Relevance - User Needs

 Main users of industrial turnover index are:

- Institutions: government departments, ECB, national central bank, international organisations, etc.
- Social actors: employers' organisations, trade unions, lobby groups, etc.
- Media
- Researchers & students
- Enterprises/businesses
- Internal users
- Eurostat

12.2 Relevance - User Satisfaction

Not available.

12.3 Completeness

European requirements are fulfilled

13. Accuracy
13.1 Accuracy - overall

 

Since a non-probability sampling method (the cut-off method) is used, it is not possible to compute sampling errors.

The main source of error is non-response.

In order to guarantee a satisfactory level of accuracy several checks and operations are implemented. Three of them are noteworthy:

1)      daily treatment of corporate events (merger, split-up, etc.);

2)      alignment of the sample to the reference business register in order to take into account its updates;

3)      yearly integration of the sample.

13.2 Sampling error

It is not possible to compute sampling errors because a non-probability sampling method (cut-off) is used.

13.3 Non-sampling error

When the first release of indices is released, about 45 days after the end of the reference month, the response rate reaches little more than 90% in terms of firms and little more than 95% in terms of turnover value (referred to the base year).

Many efforts are carried out in order to reduce non-sampling errors:

1) in the collection phase the use of an electronic questionnaire helps detecting potential mistakes (respondent’s attention is drawn to values exceeding certain thresholds based on past values);
2) an effective and complex reminder campaign, aimed at increasing the response rate, is implemented via e-mail and phone, according a strict          calendar defined at the beginning of each year;
3) in the micro-editing phase potential errors are detected considering the contribution of each respondent to the year-on-year growth rate of its own 3      digit NACE sector and intensive follow ups by phone are addressed to the selected units to obtain clarification/confirmation/correction (an ongoing          experiment is comparing this approach with a more sophisticated selective micro-editing based on probabilistic models);
4) the macro-editing considers the contribution of each sector index to the year-on-year growth rates of more aggregated indices according a schema      allowing both top-down and bottom-up checks.

14. Timeliness and punctuality
14.1 Timeliness
The publication of the final index takes place about 45 days after the end of the reference month, 15 days before the deadline stated in the European regulation.
14.2 Punctuality

Releases are delivered on time according to the calendar set annually.

15. Coherence and comparability
15.1 Comparability - geographical

European definitions are used and they apply in the whole national territory.

15.2 Comparability - over time

Consistent time series data are available for a long period of time (since January 2000). When changes in source data, methodology and statistical techniques are introduced, historical series are reconstructed as far back as possible. 

15.3 Coherence - cross domain

A deflated version of turnover indices (obtained firstly dividing domestic and non-domestic 3 digit NACE turnover indices by the respective producer price indices and secondly aggregating the resulting indices) is compared with industrial production indices.

These comparisons show a good level of coherence for main aggregates.

15.4 Coherence - internal

 

Aggregates are always consistent with their sub-aggregates since the former are derived as weighted averages of the latter.

Internal coherence is also guaranteed for calendar and seasonally adjusted indices as the indirect approach is used for the treatment of aggregates.

16. Cost and Burden

The cost estimate is compiled in terms of total number of hours worked (THW). It is equal to the product of three terms: (total) Annual Working Days (AWD), (total) Hours Worked per Day (HWD), Number of Persons involved in the Survey (NPS).

AWD

HWD

NPS

Cost estimate (THW)

220

7.2

10

15,840


The burden is applied to respondent, i.e. the person who fills in the questionnaire on behalf of the enterprise. The burden has been estimated  in terms of total number of minutes taken to fill in a single monthly questionnaire and it is less than 30 minutes, according to the familiarity with this activity and the complexity (amount and type) of data for the single enterprise.

The questionnaire proposed to respondents in December does not point out any difference between beginners and experts.

Type of Respondent

Burden estimate (TNM)

Beginner

burden ≤ 30 min.

Expert

burden ≤ 30 min.

17. Data revision
17.1 Data revision - policy

Unadjusted data

Routine revisions

1)      Monthly revision: indices referred to month m are revised after one month when indices referred to month m+1 are released. They take into account late respondents (estimated values for missing responses are replaced by reported figures) and correction from respondents.

2)      Once a year, in November, data are revised in order to take into account changes due to:

a)      late respondents and correction from respondents;

b)      corporate events (merger, split-up, etc.);

c)      updating of business registers.

 

Non-scheduled revisions

Due to unforeseeable events such as errors or accidents, they are communicated through an ad hoc note made available on the website.

 

Major  revisions

Performed every five years, when of a new base year is introduced, they take into account new weighting systems and sample adjustments.

Major changes in methodology, sources and statistical techniques are announced in ad hoc publications, together with the revision horizon.

Advanced notification of methodological changes is also provided through seminars and papers disseminated throughout the scientific community.

 

Calendar and seasonally adjusted data

The revision policy is based on the partial concurrent approach, that is specifications are revised annually (generally when indices referred to September are released), while parameters of reg-Arima models are re-estimated monthly.

Concerning the revision horizon, the whole calendar and seasonally adjusted series are always revised as suggested by the methodological unit in charge of the seasonal adjustment. 
17.2 Data revision - practice

Documentation

A section named “Revisioni” (Italian version) or “Revisions” (English version) is included in the press release referred to month m+1, reporting revisions of year-on-year (month-on-month) growth rates computed on calendar (seasonally) adjusted turnover indices referred to the previous month m. For new orders indices revisions on year-on-year growth rates are computed on unadjusted indices.

Once a year, when indices referred to September are released and time series are revised since January 2015, the section contain further tables where previous and current year-on-year growth rates on unadjusted indices are reported for totals and MIGS since January of the current year.

A section called “La revisione degli indici” (Italian version) or “Revision policy” (English version) is included in the methodological note attached to the press release. It contains details on revision policy, sources of revisions, periodicity, etc.

 

Vintage database and dissemination

Vintages referred to unadjusted, calendar adjusted and seasonally adjusted time series and information about treatment specifications are systematically stored in an internal vintage database (implemented in Oracle). They are made available to external users on request.

 

Revision analysis

Availability of vintages stored in an Oracle database allows revision analysis for unadjusted, calendar adjusted and seasonally adjusted data. However, since the above revision policy was introduced in January 2018 (before unadjusted data had been revised once a year), time series of homogeneous 1-step revisions are too short to compute reliable revision measures: Mean Revision (MR), Mean Absolute Revision (MAR), Relative MAR (RMAR%) and Maximum of Absolute Revisions (MaxAR).

Such measures are reported below, but they are not to be used either for comparisons or for assessment of turnover index reliability.

 

Revision measures on total turnover index

January 2018-January 2019 excluding August 2018 whose revision is not coherent with the other revisions.

1)      Year-on-year growth rates on unadjusted data

MR = -0.092

MAR = 0.175

RMAR% = 4.5

MaxAR = 0.8

2)      Year-on-year growth rates on calendar adjusted data

MR = -0.067

MAR = 0.150

RMAR% = 4.2

MaxAR = 0.7

3)      Month-on-month growth rates on seasonally adjusted data

MR = -0.075

MAR = 0.125

RMAR% = 10.8

MaxAR = 0.5
18. Statistical processing
18.1 Source data

The data are collected through a statistical survey.

The frame on which enterprises are sampled is based on the business register managed and yearly updated by Istat (Archivio Statistico delle Imprese Attive - ASIA). The industrial turnover is a cut-off survey, with a non-probabilistic sample. For each 3 digit NACE group (whose statistical population is defined according rule A) of item 3.6), enterprises are ranked according to the percentage of the turnover they represent in the sector. Then the highest ranked units are drawn until the threshold of 70% of the turnover is reached. As a result about 7,800 units are surveyed each month (out of 29,500 units, see item 3.6).

The sample is refreshed every year, usually on the occasion of the annual revision released in November. Very frequent updates are needed to handle almost daily corporate events.

Criteria for stratification: not applicable

18.2 Frequency of data collection

Monthly

18.3 Data collection

Data are collected through two questionnaires: one is for enterprises that are required to submit both turnover and new orders and the other is for enterprises that are required to submit only turnover.

Self-administered data collection via electronic transmission. Data collection is carried out through a web portal called “Portale delle Imprese” https://imprese.istat.it/. Respondents need to login in order to access the web questionnaire.

The deadline to fill in the questionnaire is the 20th day after the end of the reference month. However, a 25-day grace period is granted.

Previously filled in questionnaires can by modified by respondents whenever they need in order to correct mistakes, to revise preliminary data, etc. 

18.4 Data validation

Time series checks are used for plausibility of data validated (more details are available at the item 13.3 Non sampling errors). Integrity of files structure and used codes is ensured by extractions made from a database respecting integrity constraints.

18.5 Data compilation

Data for non-respondents are generally estimated using the year on year growth rate of the respondent enterprises belonging to the same NACE 3 digit sector. In case of corporate events or dominant enterprises, missing data are not estimated automatically.

Aggregated indices are derived according the Laspeyres formula with a fixed base (2015=100) using elementary indices referred to 3 digit NACE groups for domestic and non-domestic market.

The weighting system refers to the base year and is based on the enterprises’ turnover from Structural Business Statistics data and on exports from Foreign Trade Statistics.

18.6 Adjustment

 

Data are disseminated adjusted for calendar effects (total indices and MIGs by market, B and C sections  and two letters SNA/ISIC categories only total) and for seasonality (total indices and MIGs by market). The procedure TRAMO-SEATS+, version 942 for Linux, is used.

When calendar effects (working days, Easter and leap year) are significant, the adjustment is performed by using external regression variables for the Italian specific calendar and for leap year and the default options for Easter.

Outliers (additive outliers, temporary changes and level shift) are automatically detected generally using the default critical values, while possible seasonal outliers and ramps are always specified manually.

Both additive and multiplicative decompositions are used.

In order to guarantee internal coherence, the direct approach is used to adjust MIGs (both domestic and non-domestic market) and two letters SNA/ISIC categories (only total), whereas the indirect approach is preferred to adjusted the remaining series.

Whenever indirect adjustment is performed, a residual seasonality test is performed and checked.

Details concerning revision policy of calendar and seasonally adjusted data are available at the item 17.1. Data revision – policy

19. Comment

None