The Dutch virtual Census 2001: A new approach by combining different sources

Data from many different sources were combined to produce the Dutch Census tables of 2001. Since the last Census based on a complete enumeration was held in 1971, the willingness of the population to participate has fallen sharply. Statistics Netherlands found an alternative in the Virtual Census, using available registers and surveys. The table results are not only comparable with the earlier Dutch Censuses but also with those of the other countries in the 2001 Census Round. For the 2001 Census, more detailed information is required than was the case for earlier Census Rounds. The acquired experience in dealing with data of various administrative registers for statistical use enabled Statistics Netherlands to develop a Social Statistical Database (SSD), which contains coherent and detailed demographic and socio-economic statistical information on persons and households. The Population Register forms the backbone of the SSD. Sample surveys are still needed for information that is not available from registers. To achieve overall numerical consistency across the Census tables set of 2001, the methodologists at Statistics Netherlands developed a new estimation method that ensures numerically consistent table sets if the data are obtained from different data sources. The method is called repeated weighting, and is based on the repeated application of the regression method to eliminate numerical inconsistencies among table estimates from different sources. In 2003, data were combined to produce the Dutch 2001 Census tables. In the Netherlands, this was done using data that Statistics Netherlands already had available rather than by interviewing inhabitants in a complete enumeration. This way, the Dutch taxpayer received a much lower census bill. The costs for a traditional census would be about three hundred million Euros, while the costs using this method are 'only' about three million. The estimate includes the costs for all preparatory work such as developing a new methodology and accompanying software. The costs of the registers are not included, but the analyses of the results are. Registers are not kept up-to-date for censuses but for other purposes. Saving money on census costs is only possible in countries that have sufficient register information. As an example, we can compare the costs of the Dutch Virtual Census of 2001 with the costs of the traditional Census that was held in Canada. In Canada, the census costs amounted to approximately 450 million Euros. Canada has about 31.6 million inhabitants, twice as many as the Netherlands. Statistics Canada justifies the huge census costs by pointing out the enormous implications of the census results for the distribution of money among regions. Moreover, a virtual census would be impossible in Canada because of the lack of sufficient register data.