Purpose: The purpose of this standard is to ensure that data and documentation internal to the Census Bureau are appropriately managed (i.e., files are retained, secured, and accessible to authorized users) to promote the transparency and reproducibility of Census Bureau processes and products, and to inform future projects and improvement efforts.

Note: Statistical Quality Standard F2, Providing Documentation to Support Transparency in Information Products, contains specific requirements about documentation that must be readily accessible to the public to ensure transparency in information products released by the Census Bureau.

Scope: The Census Bureau’s statistical quality standards apply to all information products released by the Census Bureau and the activities that generate those products, including products released to the public, sponsors, joint partners, or other customers. All Census Bureau employees and Special Sworn Status individuals must comply with these standards; this includes contractors and other individuals who receive Census Bureau funding to develop and release Census Bureau information products.

In particular, this standard applies to activities related to managing Census Bureau data and documentation needed to replicate results (e.g., models or survey estimates) from research and evaluation studies, surveys, censuses, and administrative records.

Exclusions:
The global exclusions to the standards are listed in the Preface. No additional exclusions apply to this standard.

Key Terms: Administratively restricted information, protected information, reproducibility, and transparency, and version control.

Requirement S2-1: Throughout all processes associated with managing data and documents, unauthrized release of protected information or administratively restricted information must be prevented by following federal laws (e.g., Title 13, Title 15, and Title 26), Census Bureau policies (e.g., Information Technology (IT) Security policies and Data Stewardship policies, such as DS007 Information Security Management Program), and additional provisions governing the use of the data (e.g., as may be specified in a memorandum of understanding or data-use agreement). (See Statistical Quality Standard S1, Protecting Confidentiality.)

Requirement S2-2: A plan for data and document management must be developed that addresses:

1. Individuals and divisions responsible for managing the data and documents.
2. Data and documents to be managed.
3. Technical issues relevant to managing the data and documents (e.g., media, retention periods, storage locations, user access rules, version control, file naming conventions, and inventory of files retained).
4. Special operations needed to store and access information (e.g., scanning, encrypting, or compressing data).
5. Timetables for reviewing retained files to verify their usefulness and readability in the stored format (e.g., every five years).

Note: The Disposition of Federal Records: A Records Management Handbook provides guidance on establishing, managing, and operating a records disposition program within a Federal agency. The Census Bureau Guideline on the Long-Term Backup of Research and Evaluation Files and the ACSD records management intranet page provide additional guidance on managing data files.

Requirement S2-3: Data and documentation needed to replicate and evaluate program or research results must be retained according to Census Bureau policies (e.g., Census Bureau Records Schedules, Records Management Policies in the Census Bureau’s Policies and Procedures Manual, and division-level policies), data-use agreements with providers of administrative records, and appropriate Federal records disposition and archival regulations (e.g., National Archives and Records Administration’s (NARA) statutes).

Examples of data and documentation to retain include:

• Data files and description of variables.
• Planning and design decisions, including the OMB (Office of Management and Budget) Information Collection Request package.
• Analysis plans.
• Field test design and results.
• Cognitive or usability testing results.
• Sampling plan and justifications, including the sampling frame used and any deviations from the plan.
• Justifications for the items on the survey instrument, including why the final items were selected.
• Instructions to respondents and interviewers.
• Description of the data collection and data processing methodologies.
• Questionnaire images.
• Description of the weighting and estimation methods, including variance estimation.
• Description of the imputation and data editing methodologies.
• Specifications and computer code (e.g., specifications and code for sampling, editing, weighting, imputation, analysis, variance estimation, and tabulation).
• Description of models used for estimates and projections.
• Documentation of disclosure avoidance techniques.
• Quality measures, including the equations and interpretations of the measures.
• Evaluation reports, including special evaluations such as nonresponse bias analyses and interviewer variance studies.
• Publicly available documentation associated with the release of data.

Sub-Requirement S2-3.1: An inventory must be developed and maintained to allow authorized users to identify and access the retained data and documents.

Note:The Census Bureau Guideline on the Long-Term Backup of Research and Evaluation Files provides information on producing an inventory to explain retained data and documents to potential users.