An ad hoc panel will study issues of documentation and archiving of statistical data products for the National Science Foundation's National Center for Science and Engineering Statistics (NCSES). The desired objective is to enable NCSES to enhance the transparency and reproducibility of the agency's statistics and facilitate improvement of the statistical program workflow processes of the agency and its contractors. The panel will consider such issues as:
(1) What documentation and archiving guidance, standards, and tools currently exist to assist NCSES to facilitate transparency and reproducibility? Which ones are most useful and feasible to implement? For censuses and sample surveys? For administrative records? For statistics that may be based on combinations of these and other data sources?
(2) In what ways can the costs of transparency for NCSES and its data users be minimized and the benefits maximized?
(3) How can NCSES obtain value from saving and using the history of statistical program workflow processes to facilitate validation and to guide improvement over time in various processes, such as editing and imputation?
(4) What are best practices to foster transparency internal to NCSES through more comprehensive documentation and archiving of methods and data?
(5) What are best practices to foster transparency external to NCSES while maintaining an appropriate degree of disclosure control for confidential microdata?
(6) What requirements for documentation and archiving standards and tools should NCSES include in contracts with data collectors, such as the U.S. Census Bureau and private survey firms?
(7) What are feasible implementation steps toward better documentation and archiving for NCSES in the next 2-3 years? What should be the goals for a longer term R&D effort in this area?
(8) How can NCSES work with other federal statistical agencies to facilitate adoption of documentation and archiving standards and tools in common?
The panel will meet to gather information and prepare a report with conclusions and recommendations at the end of the study.