The danish demographic database-principles and methods for cleaning and standardisation of data

Abstract

Since 2001 seven Danish censuses dating from 1787 till 1880 have been completely transcribed by volunteers. Due to this effort the research community now has access to a large number of demographic data. The census data were digitised according to the principle of literal data transcription in order to leave all interpretations to the users. The disadvantage of this solution is that it induces problems when creating aggregated statistics as the spelling of, e.g. position in household and occupations was not standardised which leads to great variation in the description of the same entities. In order to overcome this obstacle the data were cleaned and standardised. Standardisation consists of adding numeric codes for the gender, civil status and position in household. For occupations, HISCO has been applied to secure that the data can be used in comparative research.