- Statistical use of program administrative data
- Data analysis
- Income and poverty measurement
- Survey nonresponse
- Nonsampling error
- Statistical disclosure limitation
- Statistics and Measurements
- Medicaid and CHIP
- Nutrition and Food Assistance Programs
John Czajka is well known for his extensive experience in the analysis and evaluation of survey data and his expertise in statistical and policy applications of program administrative records. His work has addressed the design of cross-sectional and panel samples to support tax policy analysis, the potential use of administrative records in the decennial census, the measurement of income and assets in federal surveys, analysis of the dynamics of health insurance coverage, the development of small area estimates, and the application of techniques to protect the confidentiality of public use data.
Czajka’s recent work has included two comparative studies of the measurement of income and poverty in federal surveys, an analysis of Supplemental Nutrition Assistance Program (SNAP) unit composition using state SNAP administrative records linked to Census Bureau surveys, analyses of the dynamics of Medicaid coverage based on Medicaid enrollment records, the application of statistical disclosure limitation methods to federal tax data, and a study of survey underreporting of participation in SNAP and other means-tested programs.
Czajka, who joined Mathematica in 1978 as a research sociologist, is a fellow of the American Statistical Association and a past president of the Washington Statistical Society. He has served on several National Research Council panels on topics including the redesign of the Survey of Income and Program Participation, the measurement of medical care economic risk, research and development priorities for the U.S. Census Bureau’s state and local government statistics programs, data and methods for measuring the effects of changes in social welfare programs, and alternative census methodologies. He has a Ph.D. in sociology from the University of Michigan.