Despite the longitudinal design of the Current Population Survey (CPS), researchers have almost exclusively analyzed these data as though they were collected through a series of cross-sectional surveys. We propose to develop integrated data, dissemination software, and associated metadata that will make longitudinal analyses of CPS data radically easier. We will freely disseminate the data through an innovative user interface that will dramatically simplify and improve search, discovery, research design, and data access. We will provide researchers with flexible access to integrated and well-documented longitudinal data across all CPS surveys, including all surviving basic monthly surveys and all topical supplements. The project will serve the scientific enterprise by reducing wasteful duplication of effort (e.g., in linking files and harmonizing variables), eliminating common technical errors (e.g., in variance estimation), making findings easier to replicate, and encouraging and facilitating sophisticated and powerful new longitudinal analyses in many research domains. To accomplish these goals, we propose 7 specific tasks: (1) Develop user-friendly web-based longitudinal data access tools to enable researchers to capitalize on the longitudinal information embedded in CPS data from 1962 to 2014; (2) Create search and discovery tools to allow researchers to locate variables across supplements and design longitudinal analyses; (3) Construct appropriate weights for longitudinal analysis and create appropriate stratification and clustering variables to support reliable variance estimation ; (4) Make all CPS supplements compatible with the Integrated Public Use Microdata Series (IPUMS) by adding new IPUMS- compatible variables; (5) Clean all CPS files, correcting all known errors and providing new variables that consistently and reliably identify subfamilies in all samples; (6) Compile consistently-structured metadata for all CPS data (including comprehensive machine-understandable documentation of every CPS data product as well as data integration metadata); and (7) Work with the Census Bureau to identify, recover, preserve, and disseminate older CPS data and variables currently at risk of destruction. The proposed work will be carried out by a team of highly-skilled researchers with unparalleled expertise and experience in data integration, record linkage, and the Current Population Survey. Collaborators include leading researchers from the University of Minnesota, the U.S. Census Bureau, Unicon Corporation, the National Opinion Research Center, and the University of Maryland's Survey Research Center. The project will employ cutting-edge software innovations, extensive usability testing, and established metadata standards. Data integration and software development will take place in the Minnesota Population Center, the leading developer of large-scale data resources for demographic and health research.
The fully linked and harmonized IPUMS-CPS will be a new class of data for public health, social science, economic, and other forms of research. No other resource provides the same combination of broad subject coverage, large sample size, monthly observations, and long chronological coverage. As a result, this project will open entirely new avenues for longitudinal analyses of long-run change in the social, economic, and public health foundations of American society.