Enhancing Survey Quality: Continuous Data Processing Systems
-
Karl Dinkelmann [1] ; Peter Granda [1] ; Michael Shove [1]
-
[1] University of Michigan–Ann Arbor
University of Michigan–Ann Arbor
City of Ann Arbor, Estados Unidos
-
- Localización: Journal of official statistics, ISSN 0282-423X, Vol. 35, Nº. 2, 2019, págs. 337-352
- Idioma: inglés
- Enlaces
-
Resumen
Producers of large government-sponsored surveys regularly use Computer-Assisted Interviewing (CAI) software to design data collection instruments, monitor fieldwork operations, and evaluate data quality. When used in conjunction with responsive survey designs, last-minute modifications to problems in the field are quickly addressed. Complementing this strategy, but little discussed, is the need to implement similar changes in the post data collection stage of the survey data life cycle. We describe a continuous data processing system where completed interviews are carefully examined as soon as they are collected; editing, recode, and imputation programs are applied using CAI tools; and the results are reviewed to correct problematic cases. The goal: provide higher quality data and shorten the time between the conclusion of data collection and the appearance of public use data files.
