2016-10958. Statistical Policy Directive No. 2 Addendum: Standards and Guidelines for Cognitive Interviews

AGENCY:

Office of Management and Budget, Executive Office of the President.

ACTION:

Notice of solicitation of comments.

SUMMARY:

Under the Budget and Accounting Procedures Act of 1950 (31 U.S.C. 1104(d)) and the Paperwork Reduction Act of 1995 (44 U.S.C. 3504(e)), the Office of Management and Budget (OMB) issues for comment a proposed addendum to Statistical Policy Directive No. 2: Standards and Guidelines for Statistical Surveys (71 FR 55522, September 22, 2006). This addendum reflects the ongoing commitment of the Federal statistical system to ensure robust application across the Government of advances in survey methods.

In its role as coordinator of the Federal statistical system under the Paperwork Reduction Act, OMB, among other responsibilities, is required to ensure the efficiency and effectiveness of the system as well as the relevance, accuracy, objectivity, and confidentiality of information collected for statistical purposes. OMB is also charged with developing and overseeing the implementation of Government-wide principles, policies, standards, and guidelines concerning the development, presentation, and dissemination of statistical information. Accordingly, OMB requests comments on the recommendations that it received from the Federal Committee on Statistical Methodology (FCSM) Subcommittee on Question Evaluation Methodology for an addendum to OMB Statistical Policy Directive No. 2, Standards and Guidelines for Statistical Surveys. The addendum, Standards and Guidelines for Cognitive Interviews is intended to ensure that the results of statistical surveys sponsored by the Federal Government are as reliable and useful as possible while minimizing respondent burden. The addendum may be accessed at www.omb.gov/​inforeg/​Directive_​No. 2_Addendum. Comments are also requested regarding suggestions for other aspects of statistical methodology to be considered for inclusion in future addenda to this directive.

Additional discussion of the proposed addendum may be found in the SUPPLEMENTARY INFORMATION section below.

DATES:

Comments and recommendations on the proposed addendum detailed in this notice must be in writing. To ensure consideration of comments, they must be received no later than June 24, 2016. Please be aware of delays in mail processing at Federal facilities due to security screenings. Respondents are encouraged to send comments electronically via email, FAX, or http://www.regulations.gov (discussed in ADDRESSES below).

ADDRESSES:

Please send any comments or questions about this directive to: Katherine K. Wallman, Chief Statistician, Office of Management and Budget, 1800 G St., 9th Floor, Washington, DC 20503, telephone number: [phone], FAX number: [phone]. You may also send comments or questions via email to [e-mail] or to http://www.regulations.gov—a Federal E-Government Web site that allows the public to find, review, and submit comments on documents that agencies have published in the Federal Register and that are open for comment. Simply type “Directive No. 2 Addendum” (in quotes) in the Comment or Submission search box, click Go, and follow the instructions for submitting comments.

Comments submitted in response to this notice may be made available to the public through relevant Web sites. For this reason, please do not include in your comments information of a confidential nature, such as sensitive personal information or proprietary information. If you send an email comment, your email address will be automatically captured and included as part of the comment that is placed in the public docket. Please note that responses to this public comment request containing any routine notice about the confidentiality of the communication will be treated as public comments that may be made available to the public notwithstanding the inclusion of the routine notice. Because of delays in the receipt of regular mail related to security screening, respondents are encouraged to use electronic communications.

Electronic Availability: This document is available on the Internet on the OMB Web site at www.omb.gov/​inforeg/​Directive_​No._​2_​Addendum.

FOR FURTHER INFORMATION CONTACT:

Jennifer Park, 1800 G St., 9th Floor, Washington, DC 20503, email address: [e-mail] with subject Directive No. 2 Addendum, telephone number: [phone], FAX number: [phone].

SUPPLEMENTARY INFORMATION:

The Nation relies on the flow of credible statistics to support the decisions of governments, businesses, individuals, households, and other organizations. Federal surveys collect much of the information available about the United States' economy, population, natural resources, environment, and public and private institutions. It is essential that these surveys collect information in a clear, straight-forward manner so as to maximize the accuracy of data while minimizing respondent burden.

Background: Consistent with the Information Quality Act (Pub. L. 106-554, Division C, title V, Sec. 515, Dec. 21, 2000; 114 Stat. 2763A-153 to 2763A-154) and in accordance with Statistical Policy Directive No. 1: Fundamental Responsibilities of Federal Statistical Agencies and Recognized Statistical Units (79 FR 71610, Dec. 2, 2014), it is the responsibility of Federal agencies engaging in statistical work to continuously review statistical methodologies and implement improvements as they are identified so as to better ensure the relevance, accuracy, and objectivity of the statistical products our Nation uses to monitor and assess performance, progress, and needs. Further, these responsibilities must be achieved in a manner that protects the confidentiality of information acquired solely for statistical purposes. Among other requirements, Federal guidelines, such as those provided in Statistical Policy Directive No. 2: Standards and Guidelines for Statistical Surveys, recommend robust testing of survey questions before implementation.

Cognitive interviewing is a key method used to pretest survey questions and questionnaires. This method investigates whether respondents understand survey questions according to their intended design and whether respondents can provide accurate answers based on that intent. Cognitive interviews determine respondent interpretations and detail the phenomena considered by respondents in forming their answer. Findings from cognitive interviews can indicate whether a survey question captures the intended construct; cognitive interview findings can also identify difficulties that respondents experience when formulating responses. Ultimately, rigorous cognitive interviews support the efficient production of useful statistics since the findings from cognitive interviews can be used to help minimize costs and burden while ensuring the accuracy of the information collected.

Although cognitive interviews are broadly used across a variety of Federal agencies engaged in statistical activities, to date no specific Federal guidance has established the manner in which this particular method should be conducted. As such, the term “cognitive interview,” when applied to Federal statistical surveys could refer to any of an array of related research techniques that differ in their appropriate use for statistical surveys. The purpose of this addendum is to establish rigorous standards for the use of cognitive interviews in Federal information collections. These standards would allow data collectors and users alike to better evaluate the quality of survey questions and the resulting survey statistics. The addendum would apply to all Federal agencies subject to the Paperwork Reduction Act of 1995. Agencies not subject to the PRA would also benefit from this addendum, and are therefore encouraged to apply this guidance as well.

Development and Review: Statistical Policy Directive No. 2: Standards and Guidelines for Statistical Surveys was issued in 2006. It remains a robust and comprehensive source of guidance to Federal agencies engaged in statistical acitivites. Specifically, Statisical Policy Directive No. 2 was issued to ensure implementation of improved survey methods across Federal agencies. To achieve this, periodic updates and addenda are required to ensure that this Directive remains most useful to Federal agencies.

Accordingly, in 2014 OMB requested members of the Federal Interagency Council on Statistical Policy (ICSP) to nominate representatives for a new subcommittee formed under the aegis of the Federal Committee on Statistical Methodology (FCSM). The Question Evaluation Methodology Subcommittee was asked to identify best practices for conducting cognitive interviews so as to improve the resulting data quality. Subcommittee members reviewed relevant scientific literature, the Paperwork Reduction Act, the Information Quality Act, Government-wide Information Quality Guidelines (Information Quality Guidelines) (67 FR 8453, Jan. 3, 2002), Statistical Policy Directive No. 1 and Directive No. 2, and other information quality standards currently used by Federal statistical agencies. Through this careful process, the subcommittee reached a consensus in identifying seven standards for cognitive interviews. The subcommittee provided draft standards and guidelines for review by the FCSM and the ICSP in 2015. The subcommittee addressed the comments it received at each stage and provided its final recommendations to the FCSM in 2015. OMB proposes the issuance of these recommendations as an addendum to Statistical Policy Directive No. 2: Standards and Guidelines for Cognitive Interviews.

Issues for Comment: With this notice, OMB requests comments on the proposed addendum, which can be accessed at www.omb.gov/​inforeg/​Directive_​No. 2_Addendum. OMB seeks comments from all interested parties on all aspects of this proposed addendum. In particular, OMB seeks comment on the merit of the proposed standards and guidelines both about technical terms, such as statistical definitions, and as statistical policy. These standards and guidelines for cognitive interviews should reflect best practices for Federal agencies and their contractors in conducting statistical surveys as well as sound policy for the Federal statistical system. OMB seeks comment on whether some provisions of this proposal should be modified or deleted to meet these goals. Finally, OMB seeks comment from affected agencies on the expected benefits and burdens of the proposed addendum. Suggestions regarding other aspects of statistical methodology that should be considered as future addenda to Directive No. 2 are also encouraged.

Howard A. Shelanski,

Administrator, Office of Information and Regulatory Affairs.