Dutch Virtual Census Presentation at the International Seminar

Dutch Virtual Census Presentation at the International Seminar on Population and Housing Censuses; Beyond the 2010 Round 27 -29 November, 2012 Egon Gerards, The Netherlands

Introducing Dutch Virtual Census Short movie: Census Data http: //youtu. be/SLp. Dkcyenf 0 test Dutch Virtual Census – Egon Gerards 1

Dutch Virtual Census Presentation at the International Seminar on Population and Housing Censuses; Beyond the 2010 Round 27 -29 November, 2012 Egon Gerards, The Netherlands 2

Overview Ø The Dutch (Virtual) Census Ø Census based on the Social Statistical Database Ø Used methods Ø Advantages/disadvantages of a virtual census test Dutch Virtual Census – Egon Gerards 3

History of the Dutch Census Ø Traditional Census Ø Ministry of Home Affairs: 1829, 1839, 1849, 1859, 1869, 1879, and 1889 Ø Statistics Netherlands: 1899, 1909, 1920, 1930, 1947, 1960, and 1971 Ø Experience of 1971: Unwillingness (nonresponse) and reduction expenses Ø No more traditional censuses test Dutch Virtual Census – Egon Gerards 4

History of the Dutch Census Ø Alternative: virtual census Ø 1981 and 1991: Population Register and surveys development 90’s; More and more registers used in the Census Ø 2001 and 2011: based on an integrated set of registers and surveys: Social Statistical Database test Dutch Virtual Census – Egon Gerards 5

What is the Social Statistical Database? Definition: Comprehensive set of integrated micro-datafiles with coherent and detailed demographic and socio-economic data on persons, households, dwellings, jobs, and benefits Two versions of the SSD: Ø “fast” SSD (fast, regular statistics) Ø micro integrated SSD (high-quality, longitudinally consistent statistics) test Dutch Virtual Census – Egon Gerards 6

Facilitating use of administrative sources Ø Legal base (Statistics Act) Ø Public approval (‘Big Brother is watching you’) Ø Cooperation among authorities (mainly government organisations) Ø Comprehensive and reliable register system (administrative versus statistical quality) Ø Unified identification system (preferably unique ID -numbers) test Dutch Virtual Census – Egon Gerards 7

Census and SSD data sources Population Register Jobs file, containing all employees Self-employed file, containing all self-employed Fiscal administration Social Security administrations Pensions and life insurance benefits Housing registers Ø Labour Force Survey data around Census Day survey Ø Ø Ø Ø test Dutch Virtual Census – Egon Gerards 8

Combining sources; from data to tables Ø Micro linkage Ø Micro integration Ø Weighting technique test Dutch Virtual Census – Egon Gerards 9

Micro linkage Ø Linkage key Ø Registers: Citizen Service Number, unique Ø Surveys: Sex, date of birth, address (postal code and house number) Ø Linkage key replaced by RIN-person (confidentiality) Ø Linkage strategy Ø Optimizing number of matches Ø Minimizing number of mismatches and missed matches test Dutch Virtual Census – Egon Gerards 10

Micro integration aims at improving data quality in combined sources by searching and correcting for errors on unit level Ø Collecting data from several sources; more comprehensive and coherent information on aspects of a person’s life Ø Compare sources: coverage and conflicting information (reliability of sources) Ø Integration rules: checks, adjustments, imputations Ø Optimal use of information; quality improves test Dutch Virtual Census – Egon Gerards 11

Repeated weighting Ø Creating register-survey tables Ø Demand for overall numerical consistency Ø one figure for one phenomenon idea Ø all tables based on different sources (e. g. surveys) should be mutually consistent Ø Repeated Weighting (RW): technique to achieve numerical consistency test Dutch Virtual Census – Egon Gerards 12

Dutch Virtual Census Ø Ø Ø Collection of administrative registers Surveys only additional and existing No additional data collection Linking the sources Micro integration Estimation/Weighting test Dutch Virtual Census – Egon Gerards 13

Advantages Virtual Census Ø Ø Relatively cheap (small cost per inhabitant) Quick (short production time) Less problems with non-response It can be done permanently! test Dutch Virtual Census – Egon Gerards 14

Disadvantages Virtual Census Ø Dependent on register holders (statistics is not their priority) Ø Timeliness of registers Ø Concepts and population of registers may differ from what is needed (keep good relations with the register holders!) Ø Publication of small subpopulations sometimes difficult or even impossible because of limited information in already existing surveys test Dutch Virtual Census – Egon Gerards 15

Dutch population 1829 - 2011 test Dutch Virtual Census – Egon Gerards 16

Statistics Netherlands: microdata availability Ø More information about the Dutch traditional Censuses (including those of 1960 and 1971) http: //www. volkstellingen. nl/en/ Ø One percent samples for three years (1960, 1971 and 2001) IPUMS (Integrated Public Use Microdata Series) http: //www. ipums. org/international/index. html Ø Microdata sets for all three above years available for research! DANS (Data Archiving and Networked Services) http: //www. dans. knaw. nl/en/ Ø Centre for Policy Related Statistics; research for commissioned work and remote access to microdata for research: www. cbs. nl/cvb test Dutch Virtual Census – Egon Gerards 17

The Netherlands Ø Ø Ø 300 km long, 200 km wide Quarter of the land below sea level 16, 7 million people Densily populated: 500 persons / km 2 Kingdom: Queen Beatrix Thank you for your attention! test Dutch Virtual Census – Egon Gerards 18

More information Census 2001 Ø Tables 2001 http: //www. cbs. nl/nl. NL/menu/themas/dossiers/historischereeksen/publicaties/volkstelling-2001/2003 -volkstellingexcel. htm Ø Book and extra chapter 2001 http: //www. cbs. nl/nl. NL/menu/themas/dossiers/historischereeksen/publicaties/volkstelling-2001/2001 -b 57 -pub. htm test Dutch Virtual Census – Egon Gerards 19