Skip to content

Methodology - monthly sales indices in services and index of services production

(covering sections H + I + J + L+ M + N without CZ-NACE 72, 75) in the CZ-NACE classification (Czech version of the NACE Rev. 2 classification)


I Basic definition of the measured economic activities

According to the most general definition, the term services means activities classified to the sections H to S of the Classification of Economic Activities, CZ-NACE (i.e. the Czech version of the NACE Rev. 2). The scope of economic activities measured by monthly statistical questionnaires results from current regulations of Eurostat for short-term statistics, which do not require data on all economic activities. With regards to the requirements, the short-term statistics of services provides information on the development of sales in enterprises the principal (prevailing) activity of which is in: transportation and storage (CZ-NACE section H), accommodation and food service activities (CZ-NACE section I), information and communication (CZ-NACE section J), real estate activities (CZ-NACE section L), professional, scientific and technical activities (CZ-NACE section M without 72 and 75), and administrative and support service activities (CZ-NACE section N).


II Data source

1  Statistical survey

The “SP 1–12” statistical survey with annexes, which is common for industries (economic activities) of trade, accommodation and food service activities (hotels, restaurants), transportation and storage, information and communication, and market services, is a data source for the calculation of the monthly sales index. Aggregate sales from the sale of products, services, and goods in the respective month are measured monthly. An initial questionnaire, which is sent as an annex to the reporting units included for the first time in the sample contains indicators on principal (prevailing) activity of the reporting unit and on sales in individual months of the preceding year. Sales are reported excluding VAT.
Specimens of statistical questionnaires are available at:
http://apl.czso.cz/pll/vykazy/pdf1 (Czech only).

2 Administrative data sources, downloaded data

The task uses an administrative data source information from the General Financial Directorate value added tax (VAT). Since the year 2020, administrative data have been used not only to make a sample but also to calculate year-on-year sales indices. Part of the data is now modelled based on the TRAMO/SEATS method in the JDemetra+ programme based on monthly VAT tax returns. Therefore it was possible to significantly reduce the scope of the sample and thus reduce the burden on respondents.


III Population and sample creation, imputations and estimates of the non-surveyed part of the population

1 Population and sample creation

The population consists of units that are considered to be active, are classified to the aforementioned CZ-NACE activities, and do their business in order to make profit. Reporting units are selected from the (Statistical) Business Register based on their principal (prevailing) activity. Reporting units are selected by combining methods of a sample and an exhaustive (100%) survey. From 2009 to 2019, all units with an annual turnover of CZK 250 million or higher were included in the sample as well as units with 50+ employees. From 2020, criteria for a 100% sample are set for each CZ-NACE activity individually with regards to the amount of their annual turnover or the number of employees. As for other enterprises, proportional sampling is used related to the volume of sales known from an administrative data source. The probability of inclusion of a unit in the sample is directly proportional to the contribution of its sales to total sales in the given CZ-NACE activity. This is to secure that the units reporting above-the-average sales have more chances to be included in the sample than those with low sales, which are thus not exposed to unnecessary administrative burden.

The criterion for an inclusion of all units in the sample is also applied during the reference year; the population and the sample are thus regularly updated with newly born units, which comply with the criterion.


The sample does not include entities belonging to the non-business sphere (organisational units of the state, semi-budgetary organisations partially funded from the state budget or local budgets, and non-profit organisations). As for important units data of which have a significant impact on results for individual industries (economic activities), data are measured (surveyed) for activity units, i.e. in the breakdown by economic activity of the given unit.

2 Imputations and estimates of the non-surveyed part of the population

The aim of imputations is to impute missing individual data for units that did not report or for units that are not in the sample. Units are grossed up according to similar units in the group (stratum). The stratum is defined by industry (economic activity) and unit size.

Part of the data for units that are not in the sample is now modelled based on the TRAMO/SEATS method in the JDemetra+ programme based on monthly VAT returns. Data for the last month being processed are predicted by means of the TRAMO/SEATS method, in which parameters are adjusted every month based on current data. In the following month, the prediction is replaced by a model based on data submitted in monthly VAT tax returns for a selected group of enterprises in the given economic activity (industry).

3 Description of sales indices calculation

The sales index shows how sales changed (increased or decreased) in the reference period when compared to the comparison basis. Depending on the index type, the comparison basis is either the corresponding period of the previous year (year-on-year index) or the average period of the base year (fixed-base index).
The sales index is used for short-term development analyses and possible predictions of the future development in individual CZ-NACE activities.

Calculation of indices:
For each lowest aggregate of CZ-NACE, the y-o-y sales indices at current prices are calculated for individual months. For these CZ-NACE categories, y-o-y price deflators are used for individual months of the current year; for the base year, price deflators of individual months to the year’s average are used. Absolute values of monthly sales at current prices for the lowest CZ-NACE aggregates are converted into the price level of the base year using the method of chain-linked deflators. By the summation of the lowest aggregates of absolute values of sales at constant prices in individual months we get higher CZ-NACE aggregates from which we calculate y-o-y sales indices at constant prices. In the base year it is true that the sum of monthly sales of aggregated CZ-NACE categories at current prices is equal to the sum of their sales at constant prices. For deflation of sales to constant prices, price deflators excluding VAT related to the base year 2021 were used.

4 Description of calculation of services production

The Index of services production (ISP) measures the price adjusted output of the service industries and of services in total. The calculation of the Index of services production is based on sales from sale of goods and services and on sales from sale of goods for resale converted to constant prices, surveyed by means of the “SP1-12” questionnaire (report). The Index of services production is primarily calculated as a monthly base index, currently  the base period is the average month of the base year 2021, namely at the level of a two-digit division or a three-digit group of the CZ-NACE classification. When aggregating to a higher level (aggregation to the level of sections and to services in total) weights derived from the structure of the value added in the base year are used. In compliance with regulations of Eurostat, the Index of services production covers the following economic activities: transportation and storage (CZ-NACE section H), accommodation and food service activities (CZ-NACE section I), information and communication (CZ-NACE section J), real estate activities (CZ-NACE section L), professional, scientific and technical activities (CZ-NACE section M excluding 701, 72, and 75), and administrative and support service activities (CZ-NACE section N). The definition of services in total according to requirements of Eurostat for the Index of services production slightly differs from the definition of services in total for the indicator of sales at constant prices that we publish in the Czech Republic. The difference lies in exclusion of the CZ-NACE 701.

The Index of services production indicator only differs from the sales index at constant prices indicator by using of different weights. At the lowest level (of 2-digit or 3-digit CZ-NACE), both the sales index at constant prices and the Index of services production are the same. In higher aggregations, the indices differ due to the different weighting scheme (sales index – sales are the weights, the Index of services production – the value added is the weights).

5 Change of the base period in 2024

In 2024, the base period for short-term statistics changed, which is a standard step made usually every five years and co-ordinated within the European Statistical System.

  • The base period for fixed-base indices changed from the average of the year 2015 to the average of the year 2021.
  • New weighting schemes are used that are derived from results of the structural business statistics for the year 2021.

·         In compliance with the Eurostat manual on short-term statistics, new weights were used for recalculation of data back to the year 2020, which entailed a revision of data for 2020–2023.

  • Data for the years 2000–2018 were connected with updated results by means of conversion bridges by the annual overlap method. It is characteristic for this method that 2019/2018 year-on-year indices for the entire year cumulation remain after the connection the same as at the original data and the course of the series for the years 2000–2018 does not change either, i.e. after the connection the year-on-year indices remain unchanged. However, a consequence of the change is that historical series before the year 2019 lose their additivity; it means that they cannot be aggregated by means of the up-to-date weighting scheme.


IV Overview of basic published indicators

Year-on-year (sales) indices at current prices

Year-on-year (sales) indices at constant prices

Base (sales) indices at current prices

Base (sales) indices at constant prices

Year-on-year indices of (services) production at constant prices

Base indices of (services) production at constant prices

The mentioned indices are published in the form of unadjusted data, calendar-adjusted data, and seasonally adjusted data (including adjustment for calendar effects). Data are published monthly, quarterly, and annually.


V Retrospective corrections, revisions, estimate refinement procedure


In accordance with the CZSO Data Revision Policy, standard revisions are made in the “SP 1–12” survey with the aim to enhance quality of a previously published piece of data by inclusion in the processing the reports (questionnaires) that were delivered late, corrections of data that were misreported, and by inclusion of updated administrative data. Along with processing of data for each month (except for January), a revision of data for the previous month is made; for example, concurrently with processing of data for February, a revision of data for January is made. Final data are published following the processing of all months of the reference year, usually in March of the following year.

Along with publication of adjusted time series, data have been recalculated backwards as of January 2021. Together with a revision for a year, an adjustment model is changed and therefore the whole time series is recalculated, which is usually published in March of the following year (see Chapter VII Seasonal adjustment).

Usually every five years, the base period of short-term statistics is changed, which is a standard step co-ordinated within the European Statistical System (see Chapter III, point 5 Change of the base period in 2024).


VI Comparability

1 Comparability over time

The data come from the same data source and there were no methodological changes in the survey; therefore, they are completely comparable over time.

2 Comparability with other outputs (outcomes)

Results of monthly surveys may differ from results of published annual surveys. Monthly data are required (in order to meet deadlines for publication of outputs according to the release calendar) within deadlines when enterprises do not have precise figures for the reference period available yet and therefore they are replaced by an informed guess. Moreover, during the final processing, which is made two years after the end of the reference year, data from annual surveys are modified according to the latest administrative data available.

3 International comparability

In the European Union, the short-term statistics domain is governed by the valid Regulation (EU) 2019/2152 of the European Parliament and of the Council of 27 November 2019 on European business statistics, repealing 10 legal acts in the field of business statistics. Under this Regulation, Member States of the EU are obliged to provide monthly information on the development of turnover in trade (at current and constant prices) and results of the development of turnover and production for economic activities of transport and services.


VII Seasonal adjustment

The size of sales during a year in some industries (CZ-NACE economic activities) strongly depends on the season (e.g. air transport etc.). In order to find out long-term trends but also to be able to compare month-on-month or quarter-on-quarter developments, the CZSO uses seasonally adjusted data, in which the part of sales caused by a different number of working days in a month and by seasonal fluctuation is separated from the original “rough” series, using a mathematical model. After the seasonal adjustment is made, not only y-o-y but also m-o-m (q-o-q) development can be compared.
Along with publication of adjusted time series, data have been recalculated backwards as of January 2021. Together with a revision for a year, an adjustment model is changed and therefore the whole time series is recalculated.

The TRAMO/SEATS method also recommended by Eurostat is used for seasonal adjustment. The CZSO uses the NbDemetra programme (2.2.2 version). An indirect method is applied – the seasonal adjustment takes place on the lowest source aggregates of the sales index and an adjustment of higher aggregations is a weighted average of adjusted source data.


VIII Data publishing

Monthly survey results are published:

1) in the Services news releases;
2) in time series in the Public database of the CZSO;
3) they are regularly sent to
Eurostat databases;
4) in other documents at
www.czso.cz.

IX Additional methodological information and external links

Weights of CZ-NACE economic activities in total sales in services in the base year (2021)

Eurostat: Data series metadata Turnover in services

Eurostat:
EU short-term statistics legislation

Eurostat:
Methodology of short-term business statistics (Interpretation and guidelines)


Contact person: Jana Gotvaldová, phone number: (+420) 274 052 691, (+420) 735 130 284,
e-mail: jana.gotvaldova@csu.gov.cz