Statistics Belgium - STATBEL

Economic Statistics

NG building Koning Albert II-laan 16 - 1000 Brussels

Output price index (afzetprijsindex/indice indice des prix à la production). Producer Price Indices. 

NACE Rev. 2.

Activities covered H494, H51, H521, H5224, H531, H532, J61, J62, J63, M71, M73, N78, N80, N812, sum of (H501 and H502), sum of (M69 and M702) of NACE Rev. 2.

Size classes covered: (Turnover>=3.9 millions € or 20 employed persons ) + (Turnover >=1million).

Prices of services produced by Belgian enterprises.

The output price is based on weights based on:

-Value added figures delivered by the National Bank of Belgium (€ zone/no € zone),

-VAT (aggregate weights),

Planned changes in information collected: none

Accounting conventions: the prices of products are collected according to the definitions in Regulation CR 1503/2006.

Reporting unit: the reporting unit is the enterprise.

Observation unit(s): the observation unit is the local kind-of-activity unit.

All enterprises with H, J, M and M activities in Belgium (services).
In practice the sample taken from the univers based on ESE ("enquête naar de structuur van de ondernemingen").

 All regions of Belgium are covered.

Estimations for some sectors since 2006.
Results based on price collection for all sectors since 2013, supplemented with estimations for a.o. water and air transport.

2015

Indices based on price changes measured in euro and other common currency.

Periodicity is quarterly.

The legal basis for this indicator is the European Business Statistics (EBS) Regulation (EU) 2019/2152 on 27 November 2019, followed by the Commission Implementing Regulation 2020/1197.

The Belgian law (03/07/2012) about short-term price surveys makes it obligatory to respond to surveys for enterprises with turnover >1 million euros.

The resulting indices are transmitted to Eurostat, and disseminated at the same moment as publication to the National Bank of Belgium and internally to be used as deflator.

There is a national law concerning the confidentiality of data (statistical law of July 4, 1962): data from reporting units which are individual or which can result in individual data may not be disseminated without permission of the reporting unit. In practice this means indices are not disseminated for sectors where:
— There are only one or two reporting units;
— There are three reporting units but one of them represents 70% or more;
— There are four or more reporting units but one of them represents 80% or more.
Confidential indices are sent to Eurostat flagged as confidential data.

Confidential data are treated by suppression (see 7.1): confidential indices are sent to Eurostat flagged as confidential data and are not visible in publications on the national website. 

Release dates are fixed in advance for a calendar year. A release schedule of all indicators can be found at: https://statbel.fgov.be/en/calendar .

To access from the main page www.statbel.fgov.be: choose your language, click on the link 'release calendar' on the bottom right of the page. 

https://statbel.fgov.be/en/calendar

Simultaneous release to all interested parties: data are transmitted to Eurostat when they are published in Belgium.

Identification of internal government access to data before release: the Economics Ministry's press department is provided with a copy of the press release.

Transmission to Eurostat and further use of the statistics: data are transmitted to Eurostat when they are published in Belgium. The transmission is done by use of EDAMIS using SDMX file format.

The level of detail corresponds to the STS-requirements for medium countries.

In a near future the level of detail will correspond to the aggregate of NACE Sections H+I+J+L+M (excl. M701, M72 and M75) + N, Sections and Divisions of NACE: H, I, J, L, M (excluding M701, M72 and, M75) and N.

Quarterly.

Identification of ministerial commentary on the occasion of statistical releases: no ministerial commentary is attached to the release of data by the statistics office.

Name of national paper publications: the output price index is published in press release, static tables, excel tables.

The press release is a text on the web page that contains a tables concerning the global index and information on the evolution of the important sectors.

Name of national electronic dissemination: Statbel/Be stat.

Not available.

Not available.

Indices are transmitted to Eurostat to be used in calculating European aggregates and to be released as national data.

Planned changes in national dissemination methods: none.

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

available on:

https://statbel.fgov.be/en/themes/indicators/prices/service-price-indices#documents

https://statbel.fgov.be/fr/themes/indicateurs-conjoncturels/prix/indices-des-prix-pour-les-services#documents

https://statbel.fgov.be/nl/themas/conjunctuurindicatoren/prijzen/prijsindexen-voor-diensten#documents

Description of standard tables produced:

available on:

https://statbel.fgov.be/en/themes/indicators/prices/service-price-indices#figure

https://statbel.fgov.be/fr/themes/indicateurs-conjoncturels/prix/indices-des-prix-pour-les-services#figures

https://statbel.fgov.be/nl/themas/conjunctuurindicatoren/prijzen/prijsindexen-voor-diensten#figures

Not yet available for the general public, only internal.

A great effort was made to optimize data collection and calculation methods (websurvey in XBRL, with fixed procedures for doubtfully large price changes including extensive descriptions of products and reasons for quality changes, calculations at 8-digit product level, etc.). For each step of the production chain, the data are controlled. At present no explicit standard quality control checks are carried out, but evolutions of the different sectors is closely watched.

Once the figures produced, they are validated by our internal validation service before publication.

Checks carried out along the production chain of the indices and these are finally validated by our validation service before diffusion.
Doubtfully large changes in price evolutions (+-25%) are eliminated, when there is reason to believe the comparability of the product is not guaranteed.

Belgian National Bank, Eurostat, Federations, Enterprises for contract prices updating, other.

No measure of user' satisfaction but no complaints either.

Fully compliant with all STS requirements:

First reference period for numerous series: minimal Q1 2006 and Q1 2013, which is in line with derogation of CR 606/2001.

In principle, a cutt-of sample is used in two stages: at enterprise level and product level. But collection difficulties due to transfer prices, unique products, etc. influence this method.

Statistical accuracy is inherently more difficult to assess for price indexes than other statistics due to the complex nature of evolution of average price changes and statistical problems in estimating of data that is not covered by the sample (extrapolation).

Accuracy decreases at higher levels of detail of geographic and product aggregation due to the increasingly smaller sizes of the price samples for lower levels of aggregation. Errors can occur in price collection and editing, or in making quality adjustments to estimate "pure price change", higher level aggregate indexes are likely to be of better quality than lower level indexes because any distortions due to errors are more likely to cancel out.

Sampling error for the producer price survey is difficult to quantify because product and enterprise samples are based on judgmental rather than probability sampling methods.

There are around 1100 prices are collected by around 700 enterprises. This results in the coverage of the requested service sectors.

Efforts are made to increase the sample size and the quality of the prices collected.

Non-sampling error is reduced using a websurvey where the survey questionnaire is filled in directly by the contact person of the enterprise. The XBRL-program contains extensive automatic verifications of the provided data (including a comparison with the data of the previous month). The user is obliged to provide an explanation if large changes occur. In case of questionable data without satisfying explanation an intervention by phone will be necessary (e.g. when unit prices or mixed products are suspected).

Response rate : about 85%

Actions to speed up or increase the rate of response : contacts by phone, email, websurvey.

Results are not recalculed after the first release, except if substancial errors are detected afterwards.

Timeliness: the output price index is released in the last day of the quarter following the reference period.

Timetable of data collection:reporting units are contacted by phone or websurvey during the first three weeks after the reference period.

Data collection is normally closed around 2 months after the reference period. Validation of the resulting indices by internal procedure starts during the last month in the quarter following the reference period.

Transmission delays are short but very rare.

The ESS definitions are applied in the whole country.

The only recent break in the the time series is caused by the passage from NACE rev.1 to NACE rev.2 in 2003 for the more detailed NACE’s.

Dissemination of information that support statistical cross-checks and provide assurance of reasonableness : none

Confrontation with other data sets: none.

No regular confrontation is made, but comparisons are made on an ad-hoc basis, especially when results seem contrary to expectations.

These include comparisons with EU-aggregates and neighboring countries.

Coherence problems are possible between aggregates and subaggregates due to chain-linking.

A rough estimate results in 250 days FTE for all recurrent tasks related to data collection and for tasks related to quarterly calculations and recurrent methodological actions on an annual basis. This includes STS and national needs, which generally overlap.

Only if important problem arises, revisions are made. Revision is not common policy.

Non-scheduled revisions may occur due to errors discovered in the input data after results are considered definitive. In this case, explanations are given in the press release.

Routine revisions due to late reception of price data are included in the next reference period.

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

Provision of information about revision and advance notice of major changes in methodology: revisions and methodological changes are announced at the same time as they take place, if possible in advance of the change.

Data have not been revised during the period of reference, MAR/MR=0.

Type of source: survey.

Frame on which the source is based: DBRIS (belgian enterprises register).

Sample or census: cut-off sample based principally on turnover.

Criteria for stratification: criteria for stratification.

Threshold values and percentages: none.

Frequency of updating the sample: annually and ad hoc replacement of failing enterprises.

Data collection is quarterly. 

Questionnaires used in the survey: XBRL websurvey using a different form for new enterprises with assistance for choosing relevant products.

Planned changes in national questionnaires: none in the near future.

Data collection media: web and phone.

Planned changes in data collection methodology: none.

Checks are carried out at the time of data collection and throughout the production chain indices. These are also validated by another service before distribution.

Collected data are daily transferred from the operating system in a datawarehouse. An automatic verification of the input data is effectuated.

Then, a SAS program allows to check the untrustworthy the price evolutions and aggregated indices upt to 4-digit NACE-level to identify problems. If a problem is detected, the collect center is contacted. In function of the response of our collect center (and possible contact with the enterprise responsible), the declaration is maintained, re-estimated or removed for the index calculation.

Final tables and press releases are validated by our validation service: format, content, missing information, layout of press release, are verified.

If results appear abnormal, the validation service recontacts the responsible for verification.

Estimates for non-response: imputation based on prices of similar products.

Estimates for grossing-up to population levels: not relevant.

Type of index: the index is a Laspeyres chain index. Quarterly evolutions are chained to reflect the evolution since baseyear.

Method of weighting and chaining: the weights are value added.

Planned changes in production methods: none.

WDA, SA and other calculations : none

Not available.