Maryland Population Research Center...

MPRC -> Research -> Data & Methods -> Data Projects

MPRC Data Projects

American Time Use Survey

Perhaps the best example of MPRC’s collaborative relationship with federal statistical agencies is the current work at MPRC on the dissemination of the ATUS. In 2003, MPRC formed a Time Use Work Group headed by Katharine Abraham (JPSM) that included researchers from the Bureau of Labor Statistics. After a series of discussions and presentations by both MPRC and BLS researchers, the idea for an “early results” conference from the ATUS emerged and MPRC became the organizing group. On December 8th and 9th, 2005, MPRC sponsored the American Time Use Survey Early Results Conference held in Bethesda, Maryland in collaboration with several federal agencies, including the BLS. The conference commissioned 14 papers from a call for papers that brought in 68 proposals from 100 authors. The conference also included nearly 30 posters and more than 125 registered participants. Papers included questions related to child care, care of elderly adults, household bargaining, work schedules, travel patterns and sleep effects on health.

The enthusiastic response to the request for conference paper proposals demonstrated the high demand for the ATUS data by the research community. However, it also became clear that the data files released by the BLS were cumbersome, a common theme in several paper presentations. This is likely to discourage their use by researchers who would otherwise find them of value. As an outgrowth of the conference, Abraham and Suzanne Bianchi (Sociology), in collaboration with the Minnesota Population Research Center, applied for and were awarded an R01 by NICHD to construct a web-based tool that will give researchers easy access to both the American Time Use Survey (ATUS) data and documentation, and the core and supplement data from the Current Population Survey (CPS) interviews in which the ATUS respondents participate. The ATUS sample is drawn from the outgoing rotations of the CPS, so that, in principle, the ATUS data can be matched back both to the CPS core questions as well as to the topical modules conducted during the various CPS months. Because the ATUS is fielded throughout the calendar year, households in the ATUS respond to different CPS monthly questionnaires. This means that core CPS information is available for all ATUS households, but different monthly supplements are available for different sub-samples of the full ATUS sample. At project completion, the data access system will cover all ATUS data collected during the seven-year period from 2003 through 2009, as well as all CPS data collected from those who are ATUS respondents during these years. User support will be provided through an email help line, a data users’ forum and two user conferences to be hosted during the project timeline.

In November 2007, the Time Use Work Group coordinated the International Association of Time Use Researchers International Conference in Washington DC, in collaboration with the U.S. Bureau of Labor Statistics.

More information can be found at the ATUS Users Information Center.

Historical Census Research File (HCR)

Over the last 5 years, MPRC, in collaboration with the Population Distribution Division of the U.S. Census Bureau, has been engaged in a project to make the 1960 – 2000 Decennial Census long and short form micro data available in a unified modern computing environment to both the Population Division of the U.S. Census Bureau and to the larger research community. This project originated in response to needs of several Maryland faculty members who required these data for specific projects. The long and short form data have four principal advantages for population researchers. First, the long and short form data contain much more detailed geography on respondents than is available in public data. This has two analytic advantages: data can be aggregated to geographic units that are consistent over time (e.g. wages for single women can be measured over time at the county level); and, users can aggregate geography into non-standard geographic units (e.g. school districts, contiguous areas). Second, the Public Use Micro Data Sample (PUMS) products contain only a fraction of the data available in the long form (and none of the data from the short form). As an example, the largest PUMS from 1980 contains only 1/3 of the observations available in the long form; even less data for earlier years is available in the PUMS. Third, the long form data has more detail on individual items than is on the PUMS files. For example, the PUMS top codes dollar amounts and collapses together rare categories (e.g., while the long form records the type of group quarters of a respondent – dormitory, prison, juvenile facility, mental institution, etc. – the PUMS only records non-institutional or institutional group quarters). Lastly, the detail of the long form allows for some matching of long form data with other census products. MPRC Director Seth Sanders (Economics) took the primary responsibility of working with staff in the Population Division to complete the data recovery effort. Currently ASCII and SAS data files are available in the Population Division, in the Center for Economic Studies and at the Research Data Centers located throughout the U.S. While the data are available, the second stage of the project, led by the Minnesota Population Research Center, will harmonize this data over the years and make the data comparable in format to the IPUMS data. This will allow users to develop research projects outside of a restricted access facility on public use data and limit the amount of time needed within the Research Data Centers to gain the additional data elements available.

Several population researchers both inside and outside of MPRC (including researchers at the Bureau of Labor Statistics) are already using this product that was just made available in June 2006. MPRC Director Seth Sanders (Economics) began work on a project to describe factors that have led to regional convergence in poverty and poverty related outcomes from 1960-2000. While summary tape files can be used to describe the convergence from 1970 to 2000, there is no electronic version of the Summary Tape Files for 1960. Perhaps more importantly, they cannot be used to decompose regional differences in earnings into changes due to shifting skill composition of the population and changes due to different returns to skills. Such decompositions are possible with micro data that includes fine geographic detail. Wage regressions can be run within small geographic units (e.g. counties) or for non-standard geographic regions (e.g. Appalachia, the Rio Grand Valley, the Mississippi Delta). MPRC associate John Iceland (Sociology) is using the 1990 and 2000 long form data to examine the changing nature of residential segregation in the United States. His work looks not only at racial segregation but segregation across various immigrant groups. He is also relying heavily on the detailed geography to study segregation within metropolitan areas. Furthermore, MPRC associate William Evans (Economics) is using the 1990 and 2000 long form data to identify households living on or near Indian Reservations.

The 1990 and 2000 Decennial Employee-Employer Databases (DEEDs)

Judy Hellerstein (Economics), with David Neumark and colleagues, constructed new datasets based on a name and address match of Long Form (one-in-six) respondents in the 1990 and 2000 Decennial Censuses to their employers. The construction of these new matched data files, the 1990 and 2000 Decennial Employee-Employer Databases (DEEDs), is possible because on the long form of the Census, employed respondents reported the business address of their current primary employer. Hellerstein and her colleagues use this business address to match a worker to an employer, obtaining business addresses of employers from the Business Register (formerly known as the Standard Statistical Establishment List, or SSEL) for 2000, a master list at the Census Bureau of all business establishments in the U.S. The DEEDs contains, for every matched worker, information from the long form and information on the establishment in which that individual works. Similarly, information on every matched worker exists for every included establishment. The opportunity to compare and contrast the earnings and characteristics of employees working for the same employer at the same physical establishment provides one of the most unique features of the DEED.

The construction of the DEED was a major undertaking-- using the name and address information written on the questionnaires by long form respondents. Hellerstein worked with the Census Bureau to develop sophisticated probabilistic matching algorithms that took into account the various spellings of street names and variations on addresses as well as dealing with issues of measurement error in two data sources. This dataset is now available through out the Research Data Center network.

Hellerstein also made substantial progress on research associated with this project. Her paper (with David Neumark), "Production Function and Wage Equation Estimation with Heterogeneous Labor: Evidence from a New Matched Employer-Employee Data Set" is now forthcoming in a University of Chicago Press Volume. She and Neumark have also completed (and submitted to a peer-reviewed journal) an NBER working paper (11599) entitled, "Workplace Segregation in the United States: Race, Ethnicity, and Skill.” Both of these papers use the 1990 DEED. Finally, Hellerstein, Neumark, and a graduate student Melissa McInerney recently completed a paper entitled, "Changes in Workplace Segregation in the United States: Evidence from the 1990 and 2000 Employer-Employee Datasets," which uses data from both the 1990 DEED and the beta-version of the 2000 DEED.

The Longitudinal Employer-Household Dynamic (LEHD)

MPRC faculty associate John Haltiwanger (Economics), with Julia Lane and John Abowd, is responsible for the LEHD project. Like the DEED, the core of this project is the matching of existing data sources to build new datasets. The LEHD program has now expanded to 40 states and is headed towards being a national program. The special feature of the LEHD is the matching of comprehensive state administrative data on employers and employees with the business and economic censuses. Match rates are extremely high (more than 97 percent) and with virtual universal coverage of workers and firms, the entire distribution of an employer's workforce can be measured and analyzed. This dataset will allow researchers to study human capital, immigration and low wage labor markets in much more detail (and at much lower levels of geographic aggregation) than previously possible.

The LEHD has now been used in dozens of papers. However it’s potential to inform demographic research is just now being exploited. John Haltiwinger (Economics) with Seth Sanders (Economics), with Fredrik Andersen of the U.S. Census Bureau use the LEHD data to examine immigration in the U.S. including exploring the adjustments that firms make to absorb immigrants. As discussed above, for this work, and likely for other demographic work, the LEHD data offers three unique advantages. First, it contains an extremely large panel on earnings, large enough to conduct analyses on groups that are a small fraction of the population. Second, it allows observations on the firms in which workers are employed and has panel data on these firms. And third, it is linked to demographic surveys which allows users to conduct analyses by demographic subgroups.