The availability of Dutch census microdata Eric Schulte Nordholt Senior researcher and project leader of the Census Statistics Netherlands Division Social and Spatial Statistics Department Support and Development Section Research and Development Workshop on Communication and Dissemination of Census Results in Geneva 16 May 2008

2 Contents Historical introduction Registers used for the virtual census Micro linkage Social Statistical Database Publicity about Dutch censuses Harmonisation Microdata availability Statistical Disclosure Control

3 Historical introduction Till 1899: Ministry of Home Affairs 1899: 8 th Census 1971: 14 th Census Till 1995: more and more surveys Last twelve years: moving to a register-based statistical office Reasons: Unwillingness (non-response) Reduction of response burden Reduction of expenses

4 Registers used for the virtual census External registers (maintenance by register holders): Population Register (PR), 16 million records demographic variables: sex, day of birth, marital status, country of birth etc. Fiscal administration (FIBASE), jobs, 7.2 million records and pensions and life insurance benefits, 2.7 million records Social Security administrations, 2 million records, auxiliary information integration process Internal registers (maintenance by Statistics Netherlands): Jobs file (employees), 6.5 million records and Self-employed persons, 790 thousand records dates of job, branch of economic activity General Business Register, records size class, (economic) activity Housing Register, about 7 million records housing variables

5 Micro linkage Linkage key: Registers Social security and Fiscal number (SoFi), unique since 26 November 2007: Citizen Service Number Surveys Sex, date of birth, address (postal code and house number) Linkage key replaced by RIN-person Linkage strategy Optimizing number of matches Minimizing number of mismatches and missed matches

6 Social Statistical Database Social Statistical Database (SSD): Set of integrated microdata files with coherent and detailed demographic and socio-economic data on persons, households, jobs and benefits No remaining internal conflicting information SSD-set: Population Register (backbone) Integrated jobs file Integrated file of (social and other) benefits Surveys, e.g. LFS Combining element: RIN-person

7 Publicity about Dutch censuses The Dutch Virtual Census of 2001 was a successful alternative for a traditional census Tables: GB/menu/themas/dossiers/volk stellingen/publicaties/2005- virtual-dutch-census-art.htmhttp:// GB/menu/themas/dossiers/volk stellingen/publicaties/2005- virtual-dutch-census-art.htm Book: GB/menu/themas/dossiers/volk stellingen/publicaties/2001-b57- e-pub.htmhttp:// GB/menu/themas/dossiers/volk stellingen/publicaties/2001-b57- e-pub.htm

8 Harmonisation (1) More information about the Dutch traditional Censuses (including those of 1960 and 1971): For 1960 and 1971 the same variables as for 2001 if not available: constructed based on existing variables in Census data Variables not internationally harmonised (e.g. sex, age, marital status, household position, country of birth, economic status, household size and country of citizenship) same classification and priority rules as for 2001

9 Harmonisation (2) Household size and country of citizenship: missing for 1960 Religious denomination (philosophy of life): only for 1960 and 1971 Place of residence one year prior to the census: only for 2001 International classifications Branch of current economic activity: ISIC / NACE Occupation: ISCO-COM Level of educational attainment: ISCED

10 Harmonisation (3) SexXXX AgeXXX Country of citizenshipXX Marital statusXXX Household positionXXX Religious denominationXX Country of birthXXX Household sizeXX Place of residence one year prior to the census X Economic statusXXX Level of educational attainment XXX OccupationXXX Branch of current economic activity XXX

11 Microdata availability One percent samples for three years (1960, 1971 and 2001) IPUMS (Integrated Public Use Microdata Series): Weighting to population totals Protecting according to rules for public use microdata files with Mu-ARGUS Microdata sets for all three years available for research! DANS (Data Archiving and Networked Services):

12 Statistical Disclosure Control (1) Microdata under contract (MUC): 1.No direct identifiers 2.Rule against spontaneous recognition: each combination of an extremely identifying variable, a very identifying variable and an identifying variable should occur at least 100 times in the population 3.Extension of this rule: maximum level of detail of some variables (occupation, level of education, branch of economic activity) is determined by the most detailed direct regional variable 4.Each region that can be distinguished in the microdata should contain at least 10,000 inhabitants 5.No direct regional variables in panel data

13 Statistical Disclosure Control (2) Identifying variables Direct (formal) identifiers Name, address, citizen service number, … Indirect identifiers, differentiated into Extremely identifying (E) Very identifying (V) Identifying (I) V E I

14 Statistical Disclosure Control (3) Examples of identifying variables Extremely identifying: Regional variables (residence, work, …) Very identifying: Sex, nationality + Extremely identifying variables Identifying: Age, occupation, education + Very identifying variables E V I

15 Statistical Disclosure Control (4) Public use microdata files: 1.Microdata must be at least one year old 2.No direct identifiers or direct regional variables 3.Only 1 kind of indirect regional variables. Values of indirect regional variables sufficiently scattered. Each area should contain at least 200,000 persons in the target population and should consist of municipalities from at least six of the twelve provinces. No dominating municipality in any area. 4.At most 15 indirect identifiers 5.No sensitive variables

16 Statistical Disclosure Control (5) Public use microdata files (continued): 6.Sampling weights should not provide additional identifying information 7.Rule against spontaneous recognition: at least 200,000 individuals in the population for each category of an identifying variable 8.Another rule against spontaneous recognition: at least 1000 individuals in the population for each category in the crossing of two identifying variables 9.At least 5 households per combination of categories of household variables 10.Records should be in random order

17 Statistical Disclosure Control (6) Microdata for remote analyses Remote execution: Scripts are sent (on line) to Statistics Netherlands and applied to the microdata; SDC is applied before returning the results (Compare with on-site microdata) Remote access: On-line access to confidentialized microdata sets (Compare with microdata under contract or on-site)

18 Time for questions and discussion