The Short-term Stock and Inventory Survey has two objectives. On the one hand, it aims to provide the necessary information to obtain a short-term indicator that measures the evolution of the value of inventory levels in the short term and, on the other hand, to supply information on changes in inventory levels as an input for National Accounts.
It is a statistic with direct data collection.
Value indices are published in which the information is presented in current terms (nominal), that is, without adjusting the effects on price variations in them, calculated as chain-linked indices using 2015 as the base period.
Currently, the monthly and quarterly indices on trade inventory levels are published quarterly and, subsequently, the indices on industry inventory levels are also released.
Bearing in mind the economic unit's main activity, classified and coded according to the National Classification of Economic Activity NACE Rev.2, indicators are obtained for:
In the future, indicators will be obtained for:
The Short-term Stock and Inventory Survey studies the population made up of economic units (establishments in the case of the industrial sector and companies in the trade sector) whose main activity, coded according to the National Classification of Economic Activity NACE Rev.2 , is included in the sections:
For economic units included in the target population whose main activity falls under the activities in section C of the NACE Rev.2, the establishment is used as a statistical unit (see the definition in section 3.4). Although, in general, the reporting unit is also the establishment, there are cases in which the company is the unit that provides information for all the establishments that it includes.
For the economic units included in the target population whose main activity is included in the activities of section G of the NACE Rev.2, the company is used as the statistical unit and the reporting unit (see the definition in section 3.4).
The target population of the study is made up of the economic units whose main activity, classified according to NACE Rev.2, is included in Section C: ‘Manufacturing’ except division 19: ‘Manufacture of coke and refined petroleum products’ and Section G: ‘Wholesale and retail trade; repair of motor vehicles and motorcycles’ except group 46.1: ‘Wholesale on a fee or contract basis’.
The geographic scope is made up of the entire national territory except Ceuta and Melilla. However, for statistical units whose main activity belongs to division 47 of the NACE Rev.2: ‘Retail trade, except for motor vehicles and motorcycles’ the aforementioned Autonomous Cities are also included.
The monthly data needed to prepare this statistical operation begin to be collected in the reference month corresponding to January 2013. The Short-term Stock and Inventory Survey was first published in December 2015, with 2010 being the base year at that time.
Currently, the base year is 2015, as the average of the indices of that year are equal to 100. The first publication with base year 2015 was published on 10 October 2018.
Indices corresponding to the new base of 2015 began to be published in 2018.
The Short-term Stock and Inventory Survey uses chain-linked indices in a way that:
Value indices and their monthly, quarterly, annual variation and year-to-date average rates.
The reference period of the inventory level is the last day of the month.
Data referred to the period: Trimestral A: 2019 TRI: I
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 Short-term Stock and Inventory Survey was favourably judged, on 26 June 2013, by the Permanent Commission of the Higher Statistical Council, the advisory body of the state statistical services and for the social involvement of respondents, producers and users of official statistics.
The Short-term Stock and Inventory Survey is a statistical operation included within the National Statistics Plan which is subject, therefore, to Law 12/1989, of 9 May, on the Public Statistical Function and, consequently, its data are protected by statistical secrecy in all stages of preparation.
All statistical staff have the obligation to maintain this statistical secrecy (art. 17.1 of the Public Statistical Function Law). In the specific case of this survey, only aggregated information is released.
The indices corresponding to the Short-term Stock and Inventory Survey are published quarterly.
Information related to this indicator is published on the INE website. The following publications and information can be found on said website:
All this information and these publications can be found at:
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.
Monthly and quarterly results for the period between the reference month corresponding to January 2013 and the last published month are available.
There is information on the indices and monthly, quarterly, annual variation and year-to-date average rates at different levels of disaggregation according to the main activity of the statistical unit and about the weighting structure used in the calculation of the aggregated indices at:
During 2018, the number of accesses to the INE website for consulting the tables containing information related to the Short-term Stock and Inventory Survey was:
And the number of accesses for consulting metadata has been:
However, in the specific case of the Short-term Stock and Inventory Survey, anonymous microdata are not accessible to the general public and are not disseminated through any means.
It is possible to request tailored information through the INE Information Area (https://www.ine.es/ss/Satellite?c=Page&p=1254735638180&pagename=ProductosYServicios%2FPYSLayout&cid=1254735638180&L=1).
When processing these requests, limitations on confidentiality and accuracy must be borne in mind.
The methodological manual of this statistical operation can be consulted at: https://www.ine.es/metodologia/t37/t3730063_2015.pdf
The completeness of the metadata, AC3, is the percentage of metadata provided in relation to the total metadata required in the standardised methodological report.
The completeness of the metadata of the Short-term Stock and Inventory Survey is AC3=100% because all sections of the methodological sheet were completed.
The Short-term Stock and Inventory Survey is prepared in compliance with the European Statistics Code of Practice that was adopted by the Statistical Programme Committee (predecessor of the European Statistical System Committee (ESSC)) in February 2005. The aforementioned Code, in which fifteen principles are established, has been adopted by INE as its own, in this way guaranteeing its fulfilment when establishing the general principles that regulate statistical production for state purposes.
Throughout this report (fields 10.6 to 17.2), different quality indicators and different explanations for the validations and quality management carried out for this statistical operation are presented.
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 development process of the Short-term Stock and Inventory Survey is designed to guarantee the quality of the information used, as well as that of the results obtained through said information. For this reason, in all stages of the process, various quality controls have been designed, such as the detection of invalid values, estimate of non-response and supervision and monitoring of fieldwork, as well as other permanent checks on the flow of information.
The Short-term Stock and Inventory Survey complies with the quality levels established by the INE.
The sampling size allows for the collection of information on a national level, down to the division level of the NACE Rev.2 in trade and the level of the main industrial groupings (MIGs) in industry.
In terms of the survey limitations, the inherent limitations to statistical operations due to sampling, such as non-responses, must be noted. Furthermore, in the trade portion, the sampling errors or variation coefficients of the estimates must be borne in mind.
Both limitations remain within reasonable limits.
The survey responds to the information needs of its main users. These include:
Every one of these users has different needs regarding the destination and use of the information they require.
The INE has carried out general user satisfaction surveys in 2007, 2010, 2013 and 2016 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 permanently in contact with its main users, with the aim of attending to any specific information need.
In addition, to deal with requests that may not be dealt with due to their complexity, whenever the base is changed these are assessed along with any suggestion made by the main users.
The survey responds to all the information requirements subject to national regulations.
The indicator R1: rate of available obligatory statistical results, which is calculated as the quotient between the amount of data provided and the amount of data required by the applicable regulations, has the value R1=100%.
The different survey processes are aimed at eliminating or minimising errors of this kind, both in the collection phase (monitoring of the response rate and control of filtering of errors) as well as in the later phases of imputation of non-response and the calculation of aggregated indices, which allows a high level of reliability for the statistical operation to be obtained.
The portion of the sample of the Short-term Stock and Inventory Survey formed by units whose main activity is classed as trade (section G in the NACE Rev.2) is probabilistic. However, the part of the sample formed by units whose main activity is industrial (Section C of the NACE Rev.2) is not probabilistic and, for this reason, sampling errors cannot be calculated for this.
More specifically, the sub-sample in which the inventory value of enterprises dedicated to trade is collected is based on samples of the Retail Trade Indices (RTI) and Services Sector Activity Indicators (SSAI), restricting them to the units whose main activity can be found within the target population and have a larger number of employed persons. For their part, the RTI and SSAI samples are also probabilistic and their sample designs are intended to minimise sampling errors in these.
In the case of the sub-sample in which the inventory value of establishments dedicated to industry is collected, this is determined from the sample of the Industrial Turnover Indices and Industrial New Orders Received Indices (ITI-INORI), whose main activity is within the target population and have a larger number of employed persons. For its part, the ITI-INORI sample is also not probabilistic as it is based on the cut-off method, which is considered to be the most appropriate given the sector's characteristics.
A non-sampling error check is carried out throughout the entire statistical process.
In each of the surveys in which questionnaires included questions on inventories (ITI-INORI, RTI and SSAI), a continuous quantitative evaluation is carried out of non-sampling errors and the bias risks associated with:
- Lack of coverage, excess coverage and duplicates in the framework
- Collection instruments
- Total non-response
- Partial non-response
- Editing, coding and imputation of data.
Subsequent analysis of the results of this measurement with the aim of carrying out actions to reduce the different types of errors.
Furthermore, an objective measurement based on the following quantitative indicators is carried out:
A2: Over-coverage rate
The over-coverage rate measures the proportion of eligible units , via the framework, that do not belong to the target population (they are outside of the scope).
For 2018, the over-coverage rate is A2 = 10.0%
A4: Non-response rate
This non-response rate is calculated as the percentage of the number of units without information or with non-usable information with regards to the total units that can be sampled (that is to say, without counting framework errors).
The average non-response rate, A4, for the results published on the inventory level in Trade in 2018 is:
- For the first published version: A4 = 3.6%
- For the latest published version: A4 = 3.4%
A5: Non-response rate by item
For the Trade inventory, this rate is calculated as the quotient between the units of the surveyed target population that did not respond to the question on the inventory level of merchandise at the end of the month and the units that were required to provide the aforementioned information.
The average non-response rate for merchandise inventories, A5, for the results published on the inventory level in Trade in 2018 is A5=1.5%
A7: Imputation rate
The imputation rate of Trade inventory measures the percentage of values assigned to the inventory level in the companies that lack these data, or where these data are invalid or inconsistent.
The average imputation rate of merchandise inventories, A7, for the results published on inventory levels in Trade in 2018 is A7 = 6.3%
In 2018, 105 days pass between the end of the calendar quarter and the publication of the results corresponding to this period.
The results of the Short-term Stock and Inventory Survey (ECSE) are published in accordance with what is provided for in the availability calendar of short-term statistics established by the INE in the last quarter of each year.
The ECSE is not subject to any specific European regulation as its results are not directly comparable to those published by other countries due to the fact that the methodology and the variables studied in each of these are not the same.
Although the survey has been designed homogeneously for the whole geographic territory, only indicators for the national total are published as it is not possible to release good quality results broken down by Autonomous Community.
The ECSE was published for the first time in 2015, with base year 2010 and in October 2018 results were published with base year 2015 for the first time. This base change modified some methodological aspects of the survey, which has created breaks in the series that have been suitably treated to offer linked series from the initial publication period of the survey to now.
The first reference month published with monthly indices on the inventory level is January 2013.
Comparability through time is measured through the CC2 indicator, which is the number of comparable elements of a time series from its last break.
The number of comparable data, CC2, is:
- for the monthly data until the reference month corresponding to December 2018: CC2=72.
- for the quarterly data until the fourth quarter of 2018: CC2=24.
The questions on inventory are included, depending on the main activity of each statistical unit, in the ITI-INORI, RTI and SSAI questionnaires and, for this reason, comparisons and relations can be carried out between the inventory variables and other variables, such as the turnover value, collected in the aforementioned questionnaires.
The estimates are completely coherent internally as they are based on the same set of data and they are calculated using the same estimation methods at all levels.
From the start, an attempt has been made to reduce the cost of this statistical operation as much as possible and, for this reason, instead of carrying out an ad hoc short-term survey to collect information relating to inventory value, the questions relating to these are included in a part of the sample of three existing surveys. Services Sector Activity Indicators, Retail Trade Indices and Industrial Turnover Indices – Industrial New Orders Received Indices.
The estimated budget appropriation needed to finance the survey, as provided for in the 2019 Annual Programme, is 64.35 thousand Euros.
Regarding the collection of data, completion via the internet is promoted as this is a flexible and secure method for respondents that, furthermore, allows for the provision of higher quality information. In any case, other methods are also available to the respondents (paper questionnaire via post, e-mail, fax, telephone, etc.).
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-.
The regular revision policy is that, in every publication, the indices from the last five months are revised, as these months are the only ones whose data could have changed when compared to the previous publication.
In this way, only the indices from the last five months are provisional, with the other indices being definitive.
The indices for each specific month will be provisional for five months. These indices will be revised in this time period, including changes regarding raw data (usually due to delays in the receipt of information or to corrections made to the primary data due to errors contained in these).
To measure the average revisions to the published index, we use the indicators A5_MAR (mean absolute revision), A6_RMAR (relative mean absolute revision) and A6_MR (mean revision).
For the annual rate of the total monthly trade index for the last 36 months (from January 2016 to December 2018):
A6_MAR = 0.005
A6_RMAR = 0.106%
A6_MR = 0.004
For the annual rate of the total quarterly trade index for the last 12 quarters (from Q1 2016 to Q4 2018):
A6_ MAR = 0.005
A6_RMAR = 0.097%
A6_MR = 0.004
Within the survey's framework is the Central Business Register (CBR), which is an organised register of information containing data on the identity, location, territorial distribution and classification by size and economic activity of companies and establishments.
Questions relating to inventories have been included in the sample of the three existing surveys carried out for many years by INE: Services Sector Activity Indicators (SSAI), Retail Trade Indices (RTI) and Industrial Turnover Indices – Industrial New Orders Received Indices (ITI-INORI).
More specifically, questions on inventories are included in questionnaires aimed at the following statistical units:
- Of the sample of Services Sector Activity Indicators: companies from divisions 45 and 46 (except group 46.1) with 10 or more employed persons).
- Of the sample of Retail Trade Indices: companies from division 47 with 10 or more employed persons including, furthermore, for groups 47.4, 47.5, 47.6, 47.7 (except class 47.79) companies that have between 3 and 9 employed persons.
- Of the sample of Industrial Turnover Indices - Industrial New Orders Received Indices: establishments whose main activity was included in section C (excluding division 19) that belong to companies with 50 or more employed persons and, in addition, the establishments of companies that have between 20 and 49 employed persons whose main activity is included in divisions 13, 14, 15, 16 and 31.
For this reason, the units that are included in the calculation of the inventory index are, approximately:
As mention before, the sample of this statistical operation comes from three short- term surveys prepared by INE:
- Retail Trade Index (RTI)
- Services Sector Activity Indicators (SSAI)
- Industrial Turnover Indices - Industrial New Orders Received Indices (ITI-INORI)
Each of them has its own sample design, wich can be consulted in the corresponding methodology published on the INE website.
Data is collected monthly.
Depending on the main activity of the statistical unit answering the questionnaire, one of three available models of questionnaires is used.
Thus in the case of companies that belong to the inventory sample and whose main activity is included in divisions 45 and 46 (except group 46.1), the same questionnaire is used as the one which collects the necessary information to prepare the Services Sector Activity Indicators; in the case of companies from division 47, the same questionnaire is used as that which collects the necessary information to prepare the Retail Trade Indices and, for the establishments from Section C (except division 19), the same questionnaire is used as that which collects the necessary information for the preparation of the Industrial Turnover Indices – Industrial New Orders Received Indices.
For this reason, the questionnaires of the three aforementioned surveys that are also intended for the Short-term Stock and Inventory Survey have been adapted to include various questions that enable the required inventory information to be collected.
Thus, a section that collects information on the amount of merchandise inventories at the end of the month is included in the questionnaires for the Services Sector Activity Indicators and the Retail Trade Indices and, for the questionnaire for the Industrial Turnover Indices – Industrial New Orders Received Indices, a section has been added in which information is collected on, on the one hand, the value of the inventories of raw materials, other supplies and merchandise and, on the other, the inventory value of products at the end of the month.
The respondent companies send the data via the internet; via email; via telephone; via fax or via ordinary post (questionnaires completed on paper).
During the completion phase of the questionnaire, a system for detecting inconsistencies is used whereby the respondent completing the questionnaire via the internet is alerted to any possible inconsistencies and, therefore, is required to confirm or modify the information provided.
When this information is recorded by INE's own staff, there is a control system that indicates possible inconsistencies that could arise. In this process, for data that contain discrepancies or anomalies, the staff responsible for the collection of information will contact the respondent to confirm or modify the information provided.
Once the information is compiled, a data coverage control is carried out in order to guarantee the completeness of the recorded data, as well as to detect duplicates and coverage errors, non-responses, etc.
Before starting the process that allows the indices that will be published on this statistical operation to be obtained, the non-response is analysed to impute a figure appropriate to those units that have not provided information corresponding to the reference month.
Later, the data filtration process is implemented with information received by INE collection centres. The process consists of two phases: in the first, a microfiltration system is carried out, or the filtration of microdata, whilst the second consists of an analysis for eachlevel of aggregation, or macrofiltration.
Microfiltration consists of verifying the validity of data from each unit, corresponding to the historic series provided by this. The analysis makes comparisons between months and years, so that data is validated without re-contact when its evolution is repeated periodically.
The second part of the filtration is carried out once the data is processed together. Centralised filtration or macrofiltration can take place with aggregate information. In contrast with microfiltration, weightings for each activity are part of the calculation at this stage, variation rates for different levels of aggregation are taken into account etc. In the cases in which information from other sources is available, a coherence procedure is carried out between these and the survey results.
With the aim of changing the base to the new base of 2015, weightings have been updated, data have been taken from the 2015 Structural Business Survey, in particular the inventory level at the end of 2015, and later these weightings are updated to December of year t-1 to obtain the weightings that are used in the calculation of the indices of year t.
Only information relating to the original series is released, which is why neither seasonal nor calendar adjustments are carried out.