Statistical processing

Source data

The data source for passenger and goods data is questionnaires to train operators including private railways and light rail lines. The data source for investments is partly the train operators and partly infrastructure managers. Other data sources are the Danish Transport and Construction Agency. Main aggregates provided to Eurostat for the purpose of EU regulation 2018/643 or Common Questionnaire Eurostat/ITF/UNECE on inland transport statistics can be found in tables BANE31 (rail traffic), BANE25 (rail transport of passengers) and BANE1 (rail transport of goods) disseminated by Statistics Denmark, among others.

Frequency of data collection

Passenger and goods data are collected quarterly. Other data are collected annually.

Data collection

Data from train operators and infrastructure managers are collected through a so-called upload solution via the public data collection portal, http://www.Virk.dk.

Data from other public authorities are in some cases collected through e-mails.

Data validation

The purpose of data validation is to ensure a correct statistics.

In each report, validation consists of

• Internal consistency check: Data are checked for internal consistency, i.e. coherence between different related pieces of information within the questionnaire, e.g. with reported number of passengers, passenger-km should also be filled.
• Development: The development in the times series for each data provider in particular from previous quarter and from the same quarter last year are checked in order to detect erroneous reports or get explanations on unusual events.

This can lead to contact of the reporting company for getting more correct data.

The compiled statistics are checked for Development: The development in the time series in particular from previous quarter and from the same quarter last year are checked in order to detect erroneous reports or get explanations on unusual events.

Data compilation

No additional data compilation are done besides data validation. There is no need for imputation or enumeration since data collection covers the full population and is complete.

Adjustment

No seasonally adjustments are made. The data are evaluated regularly to examine if stable seasonality exists and seasonally adjustment is possible.