Avenida de Manoteras 50-52 - 28050 Madrid
The Industrial Production Index (IPI) is a short-term indicator that measures the monthly evolution of the productive activity of the industrial branches, excluding construction, contained in the National Classification of Economic Activities 2009 (CNAE-2009).
This is a survey aimed at industrial establishments, which provide information on the quantities produced of each of the products selected in the indicator basket and manufactured by the establishment. With this information the basic indices of each product are developed, and by aggregation those of the different activities classified in the CNAE-2009.
On a monthly basis, the indices and their monthly, annual and accumulated variation rates are published for different disaggregation levels of activity according to the CNAE 2009, for the national whole and by Autonomous Communities. In addition, aggregate information is published according to the economic destination of the goods (consumer goods, capital goods, intermediate goods and energy).
Furthermore, national series adjusted for calendar effects and for seasonal and calendar effects are calculated and published.
The following sections of CNAE-2009 are included:
B: Mining and quarrying.
D: Electricity, gas, steam and air conditioning supply.
For section E: Water supply; sewerage,
waste management and remediation activities, research is carried out on division 36: Water collection, treatment and supply
Information unit: The Council Regulation concerning short-term statistics (Regulation 1165/98) establishes that the basic statistical unit (or information unit) is the unit of economic activity. It is defined as that which carries out a single activity, at the level of four digitsâactivity classâof CNAE-2009, included in sections B, C, D and E.
In practice, the information unit of the IPI is the establishment.
The establishment is the real unit that best fits the unit of economic activity defined in the regulation and is the unit to which the questionnaires are addressed.
The target population of the survey is the group of companies and establishments whose main activity is included in Sections B, C, D and E (division 36) of the National Classification of Economic Activities (CNAE-2009). That is, the survey covers mining and quarrying; manufacturing; electricity, gas, steam and air conditioning supply; and water collection, treatment and supply.
The survey covers the entire national territory, except Ceuta and Melilla.
It calculates indices for the national whole and for the 17 Autonomous Communities.
The IPI began to be calculated in 1975, in base 1972.
Until base 1990, quarterly indices were calculated with monthly advances.
As from base 1990 (bases 1990, 2000, 2005, 2010 and current base 2015) the periodicity of the indicator is monthly.
The base period is 2015.
In accordance with Council Regulation (EC) No. 1165/98 of 19 May 1998 concerning short-term statistics, as amended, inter alia, by Regulation (EC) No. 1158/2005 of the European Parliament and of the Council of 6 July 2005, base changes are made every five years, with base years being those ending at zero or five. The indices must be adapted to the new base year within three years after the end of that new base year.
In each branch of activity researched in the survey, a group of representative products are chosen, for which the respondents are asked to indicate the production carried out each month.
Depending on the characteristics of the activities and the products investigated, the productions are collected in different units of measurement (kilograms, litres, square meters, kWh, pairs, units, etc.). In addition to the quantities produced, it is requested the value, expressed in euros, of these productions.
Some activities, due to their peculiarities and/or characteristics of their productions, are researched on the basis of the hours worked, or exclusively using the production value of the articles selected to represent them.
The data requested from the respondents, relating to the quantities and/or values of what is produced for the articles that form part of the indicator basket, and which are manufactured in the establishment in question, have as reference the complete month immediately prior.
Data referred to the period: Mensual A: 2021 MES: 01
The compilation and dissemination of the data are governed by the Statistical Law No. 12/1989 "Public Statistical Function" of May 9, 1989, and Law No. 4/1990 of June 29 on “National Budget of State for the year 1990" amended by Law No. 13/1996 "Fiscal, administrative and social measures" of December 30, 1996, makes compulsory all statistics included in the National Statistics Plan. The National Statistical Plan 2009-2012 was approved by the Royal Decree 1663/2008. It contains the statistics that must be developed in the four year period by the State General Administration's services or any other entity dependent on it. All statistics included in the National Statistics Plan are statistics for state purposes and are obligatory. The National Statistics Plan 2017-2020, approved by Royal Decree 410/2016, of 31 October, is the Plan currently implemented. This statistical operation has governmental purposes, and it is included in the National Statistics Plan 2017-2020. (Statistics of the State Administration).
The IPI is subject to Council Regulation (EC) No. 1165/98 of 19 May 1998 concerning short-term statistics, as amended by Regulation (EC) No. 1158/2005 of the European Parliament and of the Council of 6 July 2005, which establishes the common framework for the production of Community statistics on the short-term evolution of the economic cycle.
The Spanish version of these European Union standards is accessible at
The IPI obtains all its information through the specific survey carried out by the INE for this statistic, without the collaboration of any other institution.
Through the collaboration agreements signed with the statistics institutes of the Autonomous Communities, information from the survey is sent to them, complying at all times with the requirements established to preserve statistical secrecy.
The Industrial Production Index (IPI) is a statistical operation included in the National Statistical Plan subject, therefore, to Law 12/1989 of May 9 of the Public Statistical Function and, therefore, its data is protected by statistical secrecy at all stages of its development
Its dissemination, as in this statistic, has a monthly frequency
All information related to this indicator is published on the INE website. The following publications can be found there:
- Press release, which highlights the most significant statistical data and the components that most influence the evolution of the indicator in the reference month, as well as.
- Main results, which contains the tables attached to the Press Release.
- Technical data sheet, with the main characteristics of the survey
- Methodology, in which the methodological characteristics of the indicator are explained in greater detail
- Overview of the Industry, monographic document dedicated to the analysis of this sector in the economy.
All these publications can be consulted at the following link:
European data on the Eurostat website, where you can access the information that the different countries of the European Union provide on this indicator.
INEbase is the system the INE uses to store statistical information on the Internet. It contains all the information the INE produces in electronic formats. The primary organisation of the information follows the theme-based classification of the Inventory of Statistical Operations of the State General Administration . The basic unit of INEbase is the statistical operation, defined as the set of activities that lead to obtaining statistical results on a determined sector or subject based on the individually collected data. Also included in the scope of this definition are synthesis preparation.
The results of the survey are available from 1975 to the present day.
It contains the indices and the different variation rates for different levels of functional and geographical disaggregation, and the weighting structure used in the calculation of the index.
The same information also appears for the different previous bases of the IPI (Base 1990, Base 2000, Base 2005 and Base 2010).
Microdata are not accessible to the public.
An anonymised microdata file is not released, only these are provided to the Regional Statistics Institutes with which a collaboration agreement has been signed for the transmission of said information, by virtue of the Framework Collaboration Agreement between the National Statistics Institute and the Central Statistics Offices of the Autonomous Communities (OCECAS).
There is the possibility of requesting tailor-made information from the INE User Assistance Service. When dealing with and processing these requests, the corresponding limitations on confidentiality or accuracy will be taken into account.
The documentation on methodology can be consulted at:
On the basis of Council Regulation (EC) No. 1165/98 of 19 May 1998 concerning short-term statistics, as amended, inter alia, by Regulation (EC) No.1158/2005 of the European Parliament and of the Council of 6 July 2005, the European Commission (Eurostat) assesses the quality of the transferred data and every three years will submit reports to the Council and the European Parliament on the quality of European statistics. For this purpose, each country provides the information requested by the Commission. Eurostat provides information on the main quantitative indicators, calculated on the basis of data provided by the Member States, which can be consulted at the following link: http://ec.europa.eu/eurostat/data/database
The IPI is prepared in accordance with Community guidelines in compliance with the European Statistics Code of Practice adopted by Eurostat.
Fields 10.6 to 17 of this document are the user-oriented quality report for this operation.
Quality assurance framework for the INE statistics is based on the ESSCoP, the European Statistics Code of Practice made by EUROSTAT. The ESSCoP is made up of 16 principles, gathered in three areas: Institutional Environment, Processes and Products. Each principle is associated with some indicators which make possible to measure it. In order to evaluate quality, EUROSTAT provides different tools: the indicators mentioned above, Self-assessment based on the DESAP model, peer review, user satisfaction surveys and other proceedings for evaluation.
The production process of the IPI is designed to guarantee the quality of the information used and of the results obtained from it.
The IPI is prepared in accordance with Community guidelines, complying with the European Statistics Code of Practice adopted by Eurostat
For this purpose, different quality controls have been designed at all stages of the process:
Comparison and contrast of the data provided by the respondent with the historical information of the same unit, analysing the variations and asking the respondent for an explanation of the causes that motivate large oscillations in production.
Detection of invalid values.
Estimation of non-response.
Supervision and inspection of field work.
Other permanent controls on the flow of information.
In order to guarantee the quality of this statistical operation, the results are also compared with other statistical sources, among which stand out: ITI (Industrial Turnover Indices), IPRI (Industrial Price Indices) and/or the structural surveys of the industrial sector carried out by the INE (Structural Business Statistics of the Industrial Sector and the Industrial Products Survey). When discrepancies are detected with any of the sources mentioned above, the available information is analysed in detail in order to explain the causes of said discrepancies.
In addition , the results are also contrasted with the Industrial Turnover Indices (ITI) and the Industrial New Orders Received Indices (INORI) as, from the point of view of the temporary succession of business activity, the INORI can be considered an advanced indicator of the IPI, which in turn would be a preliminary indicator of the ITI.
The framework Regulation 1165/1998 stipulates the implementation of a continuous evaluation of the quality of the data that each Member State produces and sends to Eurostat.
The IPI continuously monitors the quality of statistics, focusing on improving coverage, timeliness, comparability and data analysis.
In base 2010, we started studying division 36: Water collection, treatment and supply, within Section E of the CNAE 2009, and indices adjusted for seasonal effects were calculated, in addition to the gross indices and those adjusted for calendar effects that were already obtained previously. These adjusted series begin in January 1992.
For the base 2015, we have begun to study some activities that were not previously analysed in the IPI, such as the group 268: Manufacture of magnetic and optical media, and the indices of base 2010 have been linked to offer the user long series to facilitate the study and analysis of the industry.
The survey responds to the information needs of the main users. Among them, we can mention:
· Ministries and other public bodies.
· Autonomous Communities
· Researchers and universities.
Each of these users has different needs according to the destination and usefulness of the information they need. For this reason, tailor-made information is often provided.
The INE has carried out general user satisfaction surveys in 2007, 2010, 2013, 2016 and 2019 and it plans to continue doing so every three years. The purpose of these surveys is to find out what users think about the quality of the information of the INE statistics and the extent to which their needs of information are covered. In addition, additional surveys are carried out in order to acknowledge better other fields such as dissemination of the information, quality of some publications...
On the INE website, in its section Methods and Projects / Quality and Code of Practice / INE quality management / User surveys are available surveys conducted to date.(Click next link)
The persons responsible for the survey are in permanent contact with the main users, in order to meet any specific information need.
Likewise, given the possibility that there are unattended requests due to their complexity, in each base change these are evaluated as well as any suggestions made by the main users. Most of these demands are fulfilled.
In the 2016 User Satisfaction Survey (USS2016), in which users were asked their opinion on the statistics of the National Statistical Plan, the Industry group, in which this operation is included, received a rating of 3.78 out of 5.
The survey responds to all information requirements, both of national and international regulations.
The IPI is governed by Council Regulation (EC) No.1165/98 of 19 May 1998 concerning short-term statistics, as amended, inter alia, by Regulation (EC) No.1158/2005 of the European Parliament and of the Council of 6 July 2005. The requirements contained in both regulations are met by this indicator.
The indicator R1 is 100%, R1 being the rate of mandatory statistical results available, which is calculated as the quotient between the number of data provided and the number of data required by the applicable regulations.
The design of the statistics for the compilation of the IPI guarantees the reliability and accuracy of the calculated indices.
In all the phases of the process of obtaining the indices validity controls and analysis of the information are carried out. We also clean the errors and impute the lack of response to obtain a high degree of statistical reliability.
The main source of error may be the lack of response, but we have no evidence that the lack of response is distributed in such a way as to generate bias in the indices or in their evolution.
The IPI is not a sample survey, so the concept of sampling error cannot be applied.
It is not possible to obtain sampling errors, since the sample is not probabilistic. The sample is based on the cut-off method, which is considered the most appropriate given the characteristics of this statistic.
During the entire statistical process, there is a control of non-sampling errors.
Coverage: The framework is the establishments whose main activity falls within sections B, C, D or E (division 36) of the CNAE-2009 and which belong to companies with 20 or more employees.
Total lack of response: The non-response taking place is less than 5% (A4=5%) at the time of publication.
This non-response is reduced to less than 1% in the two subsequent periods, causing slight modifications in the indices already published; the results with all this new information received after the first publication are updated with the dissemination of results of the corresponding subsequent months.
In order to try to reduce the lack of response, measures have been taken such as facilitating completion over the Internet by sending in advance the access codes to the application, generating reminders to respondents who have not responded and extending the period of data collection (without delaying the period of dissemination).
Imputation: We have established processes of automatic imputation of non-response, based on historical information provided by the same respondent and supplemented with information relating to the period we are trying to estimate and the situation of the sector to which it belongs.
Editing and cleaning: The information of the establishments is edited, confirmed and verified that due to their influence, impact or exceptional variations exceed certain established limits.
Collection instruments: the collection is multi-channel; the respondent is offered the possibility of replying by e-mail, postal mail, telephone, fax and Internet. The collection is by self-completion, with some exceptions.
The IPI is published around 37 days after the reference month, thus meeting the deadlines set by Eurostat for the availability of this statistic (TP1=37).
In the last quarter of each year the INE publishes the availability calendar of short-term statistics in which it indicates the exact publication dates for the following year.
The IPI is published in accordance with this short-term statistics availability calendar established by the INE.
The survey is designed homogeneously in all geographical areas for which it is calculated, in terms of methodology, design, information collection process, analysis, and data verification and cleaning. This guarantees the comparability of the results between the different Autonomous Communities.
Comparability between EU countries is ensured thanks to Council Regulation (EC) No. 1165/98 of 19 May 1998 concerning short-term statistics, modified by Regulation (EC) No. 1158/2005 of the European Parliament and of the Council of 6 July 2005, which provides homogeneity to the statistics with the rest of the European Union countries that disseminate the same information for their respective industrial sectors
The IPI was first published in 1975. The base changes carried out since then (base 1990, base 2000, base 2005, base 2010 and base 2015) have been modifying some methodological aspects of the survey, which has meant a certain degree of rupture in the series. These have been conveniently treated to offer a series linked from the first year of publication of the survey to the present time for the main aggregates.
In January 2021 the number of comparable data from the series linked to older available information is 553 months (from January 1975 to January 2021) (CC2=553).
Comparing the overall results of the IPI, a similar evolution can be observed with the number of employed persons in Industry published by the Economically Active Population Survey (EAPS).
From a sectoral point of view, there is a high degree of consistency between the evolution of production in major sectors (such as the automotive sector, electrical energy, chemical industry, etc.) and the results provided by the sectors themselves. Likewise, there is also a close relationship between the evolution of the different short-term indicators related to Industry (Turnover Index, Industrial Price Index).
Analysing the evolution of the annual averages of the indices, we observe the coherence between the structural surveys of the industrial sector (Structural Business Statistics of the industrial sector and Industrial Products Survey) and the annual results of the IPI.
The data used for calculating the IPI are obtained through a specific survey for this statistic, subjecting it to the same processes of analysis, validation and imputation, which gives them complete internal consistency.
The estimated budget appropriation necessary to finance this statistic foreseen in the 2021 Annual Programme is 1,303.26 thousand euros.
The work load for the industrial establishments to which we request information has been reduced in recent years, since the implementation of a system that offers the possibility for respondents to reply via the Internet which, coupled with the possibility of using other means such as email, fax or telephone to respond, has considerably reduced the time and effort that the respondent must devote to answering the questions in the questionnaire.
The INE of Spain has a policy which regulates the basic aspects of statistical data revision, seeking to ensure process transparency and product quality. This policy is laid out in the document approved by the INE board of directors on 13 March of 2015, which is available on the INE website, in the section "Methods and projects/Quality and Code of Practice/INE’s Quality management/INE’s Revision policy" (link).
This general policy sets the criteria that the different type of revisions should follow: routine revision- it is the case of statistics whose production process includes regular revisions-; more extensive revision- when methodological or basic reference source changes take place-; and exceptional revision- for instance, when an error appears in a published statistic-.
At present it is possible to review published data without a time limit.
However, it is usual that at the time of publication of the indices relating to a given month, the indices of the two immediately preceding months are updated, mainly due to the new information incorporated as a result of reduced non-response.
Any change in the series of data published due to the revision process is announced on the INE website as well as in the data tables contained in the Press Release issued each month.
After publishing the indices relating to a given month, new information corresponding to the lack of response is incorporated, and we continue carrying out tasks of analysis and verification of data that can cause modifications and corrections of the initial information. These processes cause changes in the published indices. They usually affect the two months prior to the one being calculated.
The MAR indicator, defined as the average of the absolute value of the differences, for Gneral index, between the first data published for each month and the last data published for that month, calculated for the last 30 months published, July 2018 to December 2020, has a value of 0.3342
The RMAR indicator, defined as the quotient between the sum of the absolute value of the differences between the first data published for each month and the last data published for that month, and the sum of the last data published for each month, calculated for the last 30 months published, July 2018 to December 2020, has a value of 0.0033.
The framework of the survey is the Central Business Register (CBR) which contains information on companies with data on identification, location and territorial distribution, and classification by size and economic activity.
For each product in the indicator basket, a number of establishments that manufacture it is selected, trying to represent 90% of the production value of that article in the base year. This information is obtained from the Annual Industrial Products Survey.
The indicator basket is composed of approximately 1000 industrial products and the number of establishments participating in the survey is close to 11,500 units.
Data collection is carried out monthly
The reporting establishments send their data via the Internet, by ordinary mail (questionnaires filled in paper), by fax or by e-mail, according to their choice.
Occasionally, data are also collected by telephone if the respondent has not sent them within the deadline by any of the above ways.
Currently, the number of respondents using the Internet to complete the survey questionnaires is just over 86%.
In the questionnaire completion phase, an inconsistency detection system is used so that the respondent is warned and required to confirm or modify the information provided.
When this information is recorded by INE's own staff, there is a recording control system that warns of possible inconsistencies that may arise. In this process, for those data in which there are discrepancies, the staff responsible for collecting the information contacts the respondent to confirm or modify the information provided and facilitate the explanations or circumstances that determine those data.
Once all the information has been compiled, we carry out a data coverage control, in order to guarantee the completeness of the recorded data, as well as to detect duplicates and coverage errors, lack of response, etc.
With the information received at the INE collection centres, the data cleaning process begins. The process consists of two phases: in the first, a microcleaning system, or microdata cleaning, is carried out, while the second consists of an analysis for different levels of aggregation, or macrocleaning.
The micro-cleaning consists of checking the validity of the data coming from each establishment, taking into account the historical series provided by it. The analysis establishes month-on-month and year-on-year comparisons, so that the data is automatically validated when its evolution is repeated periodically.
The second part of the cleaning is performed once the data is processed together. With the aggregate information, we perform a centralised cleaning, in which we carry out a manual correction of the errors detected in the main variables and an automatic cleaning of the rest of the variables. Unlike microcleaning, at this phase, the calculations take into account the weights of each product or group of products and the activities; variation rates for different levels of aggregation are also considered, and so on. In cases where information is available from other sources, a consistency process is carried out between these and the results of the survey.
To carry out the seasonal adjustment of the IPI series, the INE standard for the adjustment of seasonal and calendar effects has been followed.
Calendar effects are defined as the impact produced in the time series of a variable due to the different structure presented by the months (or quarters) in the different years (both in length and in composition), if the rest of the factors that influence said variable remain constant.
The IPI is a very sensitive indicator to the calendar effects, since one more holiday in a specific month means a significant decrease in the overall production in that month.
In order to correct this problem and to obtain a series that compares the variations of the industry's value added over time in a homogeneous way, the series is adjusted taking into account the following calendar effects: working days, Easter and leap year. In order to collect these effects, regARIMA models have been used with four intervention variables centred on the calendar effect.
Once the calendar effects have been eliminated, the seasonal effects indices are adjusted. Seasonal fluctuations are movements that occur with similar intensity in each month, each quarter or each season of the year and are expected to continue occurring.
Seasonally adjusted series, i.e. adjusted for seasonal and calendar effects, provide an estimate of what is "new" in a series (changes in trend, cycle and irregular components).
Series of indices adjusted for calendar effects, and for seasonal and calendar effects or seasonally adjusted, are published together with the gross indices series, in order to allow as complete an analysis as possible of the industrial situation.