The Census Longitudinal Infrastructure Project (CLIP) is a collaborative effort to create an integrated set of linkable data files from the decennial Censuses, surveys, and administrative records held at the Census Bureau for research. For the past several decades, the Census Bureau has developed and used probabilistic matching software to link person records in decennial census, survey, and administrative datasets. These linkages are central to the Census Bureau’s mission to utilize multiple resources to evaluate survey data quality and to improve social and economic measurement. CLIP established a pilot program for collaborative research projects using the Census Bureau’s established infrastructure. In addition, CLIP build on the established procedures for linking records across data sources by appending consistent linkage identifiers, referred to as Protected Identification Keys (PIKs), to the 1940 Census. The PIKs allow for the linkage of individuals from the 1940 census to the 2000 and 2010 Censuses as well as a wide range of survey data and administrative records that are part of the Census Bureau Linkage Infrastructure.
Linking the 1940 U.S. Census with modern data
Discusses development of core linkable data, focusing on the techniques used to create a linkable 1940 Census.
Creating a Longitudinal Data Infrastructure at the Census Bureau
Discusses development of core linkable data, including the 1940, 2000, & 2010 Censuses. Provides overview of record linkage methods to create longitudinal data.
Person Matching in Historical Files using the Person Validation System
Summarizes linkage techniques employed by the Census Bureau. Discusses utilization of the techniques to append protected identification keys to the 1940 Census.