The Microdata Analysis System at the U.S. Census Bureau

The U.S. Census Bureau has the responsibility to release high quality data products while maintaining the confidentiality promised to all respondents under Title 13 of the U.S. Code. This paper describes a Microdata Analysis System (MAS) that is currently under development, which will allow users to...

Descripción completa

Detalles Bibliográficos
Autores: Lucero, Jason, Freiman, Michael, Singh, Lisa, You, Jiashen, DePersio, Michael, Zayatz, Laura
Tipo de recurso: artículo
Fecha de publicación:2011
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2099/11379
Acceso en línea:https://hdl.handle.net/2099/11379
Access Level:acceso abierto
Palabra clave:Mathematical statistics
Statistical disclosure limitation
Microdata analysis
Information retrieval
Cross-tabulations
Estadística matemàtica -- Aplicacions
Estadística -- Taules
Classificació AMS::62 Statistics::62P Applications
Classificació AMS::62 Statistics::62Q05 Statistical tables
Àrees temàtiques de la UPC::Matemàtiques i estadística::Estadística matemàtica
Descripción
Sumario:The U.S. Census Bureau has the responsibility to release high quality data products while maintaining the confidentiality promised to all respondents under Title 13 of the U.S. Code. This paper describes a Microdata Analysis System (MAS) that is currently under development, which will allow users to receive certain statistical analyses of Census Bureau data, such as crosstabulations and regressions, without ever having access to the data themselves. Such analyses must satisfy several statistical confidentiality rules; those that fail these rules will not be output to the user. In addition, the Drop q Rule, which requires removing a relatively small number of units before performing an analysis, is applied to all datasets. We describe the confidentiality rules and briefly outline an evaluation of the effectiveness of the Drop q Rule. We conclude with a description of other approaches to creating a system of this sort, and some directions for future research.