Data are collected through a quarterly survey of all enterprises in manufacturing (including mining and quarrying) with at least 10 employees, approx. 3,000 units. Reported data are validated, by checking against previous reports as well as against other sources. Data are then aggregated by industrial groupings as well as commodity groups. Series with seasonality are seasonally adjusted.
The frame population for these statistics are all kind of activity units (KAU's) with main activity in mining and quarrying or in manufacturing and having at least 10 employees. The population is selected annually, based on the employment registered for 3rd quarter of the year before the reference year. The information on industrial classification is based on the Statistical Business Register as of the beginning of the reference year. Data is collected from approx. 3000 units who are part of the survey.
The data are collected quarterly.
Data collection is conducted by means of electronic survey forms. From 3rd quarter 2014 also electronic reporting through idep.web.
The web-questionnaire contains automatic validation of reported data. If data are very different from the data reported by the same company for the last period, the respondent will be asked to check data again and to provide an explanation for the change.
In Statistics Denmark the data are validated through a number of controls that check against last period as well as against other companies reporting under the same codes (unit price control). Reporting under product codes that are not typical for the NACE (activity) of the reporting units, are also subject to control.
Data are also checked against other sources, especially the Industrial Turnover Index (part of STS) and the VAT-based statistics on enterprises' sales - both at micro (enterprise) and macro (NACE) level. These checks are especially useful for finding underreporting.
After validation, missing reports are imputed. Imputations re-use the latest reports from the units, which have not yet reported. No imputations are made for new units in the statistics, which have not previously reported data.
Missing quantity data are estimated based on reports on the same CN codes from other units in the same quarter. If there are not any other sufficient reported data from which to make estimates, quantity is not estimated for these codes and will be missing in published tables.
For the annual Prodcom submission to Eurostat, all missing quantities are estimated using supplementary sources (Trade in goods, Prodcom data from other countries). Also for Prodcom, data for 'total production' (T-codes in the Prodcom list) are estimated as being equal to 'sold production'. Companies are not required to report total production. Data are also estimated for 'z-components', which are Prodcom codes that are more detailed than CN. This estimation is based on the distribution within the corresponding z-aggregate code in EU.
There is no grossing up.
Seasonal adjustment is carried out using X-12 ARIMA from the Demetra software.
For aggregated series, indirect seasonal adjustment is carried out. This means that seasonal adjustment is carried out only at the lowest level of detail published data. Aggregate seasonally adjusted series are created by summing of underlying seasonally adjusted series.
Some series have not been considered suitable for seasonal adjustment and are therefore not adjusted.