Finding Microlevel Data for Economists at Princeton University: Education and Labor
Contacts • Bobray Bordelon, Economics/Finance/Data email@example.com • Linda Oppenheim, Industrial Relations Librarian (labor and education) firstname.lastname@example.org • Todd Hines, Economics/Finance/Data email@example.com • Data & Statistics Consultants firstname.lastname@example.org
A Few Definitions • Summary statistics: Aggregated counts of survey or administrative data. (e.g. Number of persons in an area) • Micro-data: Survey or administrative data about an entity. (e.g. person, family, household, establishment)
A Few Definitions (from ICPSR) • Cross-sectional Study: Data from particular subjects are obtained only once. (Note that questions in a cross-sectional study can apply to previous or later time periods.) • Longitudinal (Panel) Study: Same group of individuals (panel) is interviewed at intervals over a period of time.
A Few Definitions (from ICPSR) • Panel: A group of individuals who are interviewed more than once over time in a longitudinal survey. • Wave: In a panel study, interviewing period during which the entire panel is surveyed and asked the same questions.
Cautions Using Microdata • 1. Time lag: typically 2+ years from collection to release • 2. Sub-national data: very little available and often restricted. • 3. Restricted data: not uncommon to wait a year before getting permission or denial to use the data. Need to show why public use version is not sufficient. Each country has its own rules. • 4. Public use versions: Aggregation of some variables
Cautions (cont’d.) • 5. Level of specificity of question • 6. Title of survey v. subject of survey • 7. Cross-national comparisons: What exists for one country may not exist for another country. Data is generally inconsistent across borders.
Identifying & Finding Microdata Literature search: Check methodology section of articles, books, working papers, etc. Literature Databases: Econlit – economics including labor ERIC – education ICPSR Bibliography of Data-related Literature
Smith, James P. “Immigrants and the labor market,” Journal of Labor Economics, 2006, vol. 24, no. 2.
Identifying & Finding Microdata Statistical tables Use the table footnotes, methodology sections, etc. in yearbooks, statistical compilations, etc.
Statistical Compilations: Labor Statistical Abstract of the United States Handbook of U.S. Labor Statistics (electronic 2006, print 2009 in Social Science Reference Center (SSRC) call no. HD8051 .A63) Year-book of Labour Statistics(ILO) (Social Science Reference Center (SSRC) call no. HD7801.I6 A36) Laborsta (ILO): International Labour Office database for over 200 countries or territories regarding labor and consumer prices.
Statistical Compilations: Education • Statistical Abstract of the United States • Digest of Education Statistics (NCES) • Condition of Education(NCES) • Education at a Glance (OECD) (SSRC) LB2846 .E247 (paper version) • Education Statistics on the Web
Identifying & Finding Microdata DSS web site: Subject categories for data sets.
Identifying & Finding Microdata Government statistical agencies:Bureau of Labor Statistics, National Center for Education Statistics, etc.
Identifying & Finding Microdata Data archives: Repositories such as ICPSR, UK Data Archive, etc. ICPSR • Search data • Variables Database • Bibliography of Data-Related Literature • Series
Identifying & Finding Microdata Princeton University Library Catalog
Identifying & Finding Microdata • Google • Be careful about authority • Use “microdata” + keyword term
Labor Microdata • Survey of Income and Program Participation (SIPP) • Panel Study on Income Dynamics (PSID) • National Longitudinal Surveys (NLS) • Comparison chart
National Longitudinal Surveys National Longitudinal Surveys of Young Men and Older Men-- The Young Men's survey, which was discontinued in 1981, includes ~5200 men who were ages 14-24 when first interviewed in 1966. The Older Men's survey, which was discontinued in 1990, includes ~5000 men who were ages 45-59 when first interviewed in 1966. National Longitudinal Surveys of Young Women and Mature Women (NLSW)—Sample size: The Young Women's survey includes ~ 5000 women who were ages 14-24 when first interviewed in 1968. The Mature Women's survey includes ~5000 women who were ages 30-44 when first interviewed in 1967. Frequency: These surveys are now conducted simultaneously in odd-numbered years. National Longitudinal Survey of Youth 1979 (NLSY79)-- Survey of men and women born in the years 1957-64; respondents were ages 14-22 when first interviewed in 1979. Frequency: annual, 1979 to 1994; biennial, 1994— present Sample size: 12,686 NLSY79 Children and Young Adults-- Survey of the biological children of women in the NLSY79. Frequency: 11 biennial rounds National Longitudinal Survey of Youth 1997 (NLSY97)-- Survey of young men and women born in the years 1980-84; respondents were ages 12-17 when first interviewed in 1997. Frequency: 10 annual rounds (1997-2008). Sample size: 9000
Education Microdata • National Education Longitudinal Study (NELS) • Common Core of Data (CCD) • Schools and Staffing Survey (SASS) • Private School Universe Survey (PSS) • Integrated Postsecondary Education Data System (IPEDS)
Statistical Software Supported • Stata • MATLAB • SPSS • SAS • Also: Microsoft Excel, Microsoft Access, DBMS/Copy
Finally • Remote access “Connect from off-campus” • Citing and bibliographic software