Using www'ipums'orginternational a restrictedaccess website of anonymized, integrated census microda

1
Using www.ipums.org/international a
restricted-access web-site of anonymized,
integrated census microdata (for 1, 2, 3, 4, 5,
6, 7, 8 50 countries) Robert McCaa,
Steven Ruggles, Matt SobekUniversity of
Minnesota Population Centerrmccaa_at_umn.edu
Free Data!!!
2
Outline

• 1. What are census microdata?
• 2. What is IPUMS-International?
• Partners gt 50 official statistical agencies
• Goals inventory, preserve, anonymize,
  harmonize, disseminate (free of cost
  www.ipums.org/international)
• Principles respect, retain, harmonize, enhance,
  free research
• 3. How do we integrate?
• Use international standards
• Expert national assistance
• 4. Who are our users and what do they use it for?
• Major research universities in the US
  world-wide
• Policy researchers World Bank, WHO, etc.

3
What are census microdata?anonymized,
computerized census records of individuals,
households dwellings
Person number
Age
Sex

• 12100102600700720000011210000104
• 22200202600700720000011210000104
• 32300100600700720000012123000000
• 42300200400700000000000000000000
• 52300200200700000000000000000000
• 62300200000700000000000000000000

Researchers can
Study any desired set of characteristics.
Easier to harmonize than tables.
Facilitates comparative research.
4
IPUMS-International partners by stage (please
see Table 1)darkest green final stage (data in
dissemination)lighter green middle stage
(agreement signed)lightest green first stage
(agreement pending)
55 countries 3.5 billion people
5
INTERNATIONAL
IPUMS
8 countries available now (Table 2)1998
Colombia, National Institutes of Health, 1
country1999 International, National Science
Foundation, 7 countries Brazil, China, France,
Kenya, Mexico, USA, Vietnam30 country-projects
underway 2003 Latin America, NIH, 14
countries Argentina, Bolivia, Chile, Costa
Rica, Dominican Republic, Ecuador, El Salvador,
Guatemala, Honduras, Nicaragua, Panama,
Paraguay, Peru, Venezuela 2004 Europe, NIH, 16
countries Austria, Belarus, Bulgaria, Czech
Republic Germany, Greece, Hungary, Netherlands,
Poland, Portugal, Romania, Russia, Slovenia,
Spain, Turkey, UK17 country-projects to begin
next year 2005 Global, NSF, 17
countries Bangladesh, Canada, Egypt, Iran,
Iraq, Israel, Indonesia,
Madagascar, Malawi, Malaysia, Mongolia,
Pakistan, Palestinian Authority,
Philippines, Tajikistan,
Turkmenistan, Uganda
6
IPUMS-International a global collaboratory of
Official Statistical Institutes Universities
to

• 1. Inventory the worlds census microdata
• 2. Preserve endangered microdata and
  documentation
• 3. Integrate census microdata
• a. use standards of UNSD, Eurostat, ISCO, ISCED,
  etc.
• b. facilitate comparative research in time and
  space
• 4. Anonymize census microdata to preserve
  statistical confidentiality, using highest
  standards
• 5. Disseminate restricted access, custom extracts
  to approved researchers/research projects at no
  cost
• Demonstration

7
IPUMS-International principles

• 1. Respect absolute anonymity and confidentiality
• 2. Retain all original data, except adjustments
  to insure privacy (top codes, blurrings, masking,
  re-ordering, etc.)
• 3. Harmonize codes using international
  standardsoccupation ISCO, HISCO (detailed,
  general)education ISCED
  family IPUMS, etc.
  
• 4. Enhance with constructed variables (momloc,
  etc.)
• 5. Disseminate free of charge to reseachers who
  need the data and agree to abide by conditions of
  use

8
INTEGRATES
IPUMSi
StandardUN/Eurostat Principles Recs...
Census documentation compiled for Colombian
microdata
Photos from Colombia integration project,
February-March, 20004 experts from DANE (census
office)7 academics (3 universities)
9
INTEGRATES
IPUMSi
Integrate (harmonize), not standardize 1.
retain all original detail 2. harmonize every
digit
How is this possible? Composite codes
(multiple digits, 111) Not serial (1, 2, 3,
....) (Please see Table 3)
Why? Researcher confidently understands the
logic uses as much detail as needed
10
Composite coding scheme employment status
Please see Table 3
Codes in original data
integrated codes
1000 Employed, not specified
Variable Description Please see Appendix B
11
Example of Variable Availability China,
1982-2000 (Table 4)
12
DISSEMINATES
IPUMSi
Restricted Access web-based extraction system
(Appendix B)

• Legally-binding license agreement
• protects privacy and confidentiality
• assures proper use
• Access limited to
• Bona-fide researchers (credentials)
• With a demonstrated scientific need
• who agree to abide by license restrictions
• Confidentiality
• Educational, policy uses only (no commercial use)
• No redistribution
• Safely secured
• Proper citation

13
DISSEMINATES
IPUMSi
Restricted Access web-based extraction
systemfacilitates chronological /or
cross-national research
Free Data!!!

• Researcher selects
• Countries,
• Censuses,
• Cases/sub-populations,
• Variables, and
• Sample densities
• Users
• Of 518 applicants, 288 accepted denial of access
  rate 44
• Usage by country ( of projects) Mexico (59),
  USA (50), Colombia (38), Kenya (37), Vietnam
  (37), France (34), China (24).

14
DISSEMINATES
IPUMSi
Affiliations Of 288 Users, May 2002-2004
(examples)

• International Organizations (35)
• WHO (5)
• World Bank (6)
• National Statistical Institutes (9)
• US Universities (195)
• California (17)
• Harvard (7)
• Non-US Universities (49)
• Africa (4)
• Asia (10)
• Europe (21)
• Americas (14)

Many studying own country in USA
15
DISSEMINATES
IPUMSi
Research Topics (examples)

• Living arrangements of the aged
• Female labor-force participation and educational
  attainment
• Regional inequality differentials
• International migration
• Divorce and family composition
• U.S. National Academy of Sciences,
  Transitions to Adulthood in Developing
  Countries uses data from Colombia, Kenya,
  Mexico, and Vietnam to analyze changing
  outcomes such as schooling, work, fertility, and
  marriage as a function of age, gender, etc.

16
BENEFITS
IPUMSi

• Researchers policy-makersHigh-quality,
  harmonized microdatafree of chargeComprehensive,
  integrated metadata

Official Statistics Institutes Fair, free,
uniform solution to providing census microdata
Trust, transparency, more stakeholdersIncreased
usage, better science/policy Enhanced
cost-benefit ratioLittle or no marginal cost
(project pays license fee)
Citizens, Society, and GovernmentsWho we
areWhat the future may bringHow policies might
be improved
17
On a millennial scale, census microdata survive
for only a short, but significant periodMay we
help preserve yours? ... help promote good use?
2010?
18
You are invited to visit the web-siteTwww.ipums
.org/international contact rmccaa_at_umn.edu
Thank you!!