The Federal Committee on Statistical Methodology (FCSM) is an interagency committee dedicated to improving the quality of Federal statistics. The FCSM was created by the Office of Management and Budget (OMB) to inform and advise OMB and the Interagency Council on Statistical Policy (ICSP) on methodological and statistical issues that affect the quality of Federal data.

2020 FCSM Research and Policy Conference

The 2020 FCSM Research and Policy Conference was held virtually on September 21. Slides for the presentations for are available here.

Latest Products

A Framework for Data Quality   All data have strengths and weaknesses. Effective understanding of data quality is essential for public officials, private businesses, and the public to make data-driven decisions. New sources of data, new uses of existing data and analysis methods, and increasing reliance on integrating data from multiple sources bring new opportunities and challenges to federal agencies that provide information to support public and private decisions. Although new data sources and methods show great promise, the quality of these data must be evaluated. Inferior quality data can result in misleading information and poor decisions. The Interagency Council on Statistical Policy (ICSP) has indicated that "agencies should work to adopt a common language and framework for reporting on the quality of data sets and derivative information they disseminate" (ICSP 2018). This report presents a framework for identifying data quality, built upon the Information Quality Act, and that can be applied to all types of data. The FCSM Data Quality Framework provides a foundation upon which federal agencies can make decision about the management of data products throughout their lifecycle. The report also summarizes the current state of practice in identifying threats to data quality for the components of the framework, and provides guidance for promoting effective reporting of data quality.
Updates on Terminology of Sexual Orientation and Gender Identity Survey Measures   In support of the need for further research on the terminology and ordering of response options for sexual orientation and gender identity (SOGI) questions, this paper highlights insights identified in recent literature reviewed about response option terminology and associated methodological implications. The paper contributes to the broader discussion of measuring SOGI in surveys and identifies possible future research avenues for documenting best practices for SOGI measurement.
A Systematic Review of Nonresponse Bias Studies in Federally Sponsored Surveys   In 2006, the Office of Management and Budget (OMB) published Standards and Guidelines for Statistical Surveys requiring that all Federal surveys with a unit response rate of less than 80 percent conduct an analysis of nonresponse bias (NRB). Since 2006, Federal surveys have increased activities involving analyses of nonresponse bias; however, the quality and style of the reports have greatly varied in terms of methodology, rigor, and reporting. The FCSM chartered the Nonresponse Bias Subcommittee to help assess the overall impact of OMB’s Standards and Guidelines for Statistical Surveys. The NRB subcommittee has finalized a report that summarizes more than 160 NRB studies and describes the general characteristics of nonresponse bias studies, including agency sponsorship, response rates, type of survey, and mode of data collection; the types of NRB assessment method(s) used; the target of the NRB analyses (i.e., sample composition, survey estimates, or both); and whether post-survey nonresponse adjustments appeared to reduce bias in final estimates.
Transparent Reporting for Integrated Data Quality: Practices of Seven Federal Statistical Agencies   This report examines how seven agencies in the federal statistical system assess the quality of integrated (multiple-source) data used in one of the agency’s statistical products and how they report data quality to users of the product. Statistical agencies are making increased use of alternative data sources, including administrative and proprietary data, and combining data from multiple sources. The report also provides results from an exploratory customer survey that solicited from the agencies’ users their assessments of how transparently—that is, how clearly and completely—the agency reports on the data quality of integrated data products so that users can determine if the product can be used for their purposes.

The FCSM and the Interagency Council on Statistical Policy (ICSP) are working to create a unified framework for transparent reporting of data quality for integrated data products, including appropriate statistical standards. Whether federal statistics come from traditional household and establishment surveys and carefully designed administrative records systems or from sources not initially designed for statistical purposes, data quality must be communicated transparently and understood to provide the best available statistical information to the public and to ensure the statistics are used wisely. These are the four newest products related to this ongoing effort.

Principles for Modernizing Production of Federal Statistics, by the Interagency Council on Statistical Policy   Advances in technology and methodology are creating opportunities for statistical agencies and programs to reduce data collection costs and burden on the public while increasing the timeliness and usefulness of resulting statistical products by shifting reliance from surveys to the acquisition and curation of data not initially designed for statistical purposes. Producing official statistics from non–survey data, or integrated data composed of both survey and non–survey data, will require changes to production processes as well as the methods used to evaluate and report strengths and limitations of resulting estimates. This document, prepared by the Interagency Council on Statistical Policy, outlines a set of principles intended to establish priorities for research and ongoing work to advance the use of nontraditional information and data to produce official statistics.

Transparent Quality Reporting in the Integration of Multiple Data Sources: A Progress Report, 2017-2018

  Given the increased opportunity for using non-survey and integrated data to create statistical products, the Interagency Council on Statistical Policy asked the Federal Committee on Statistical Methodology (FCSM) to start work to develop quality standards for integrated data used in statistical programs. The FCSM identified the need to address the gap in understanding the quality of such integrated datasets as compared to traditional sample surveys and the need for improved communication between data producers and data users in order to facilitate informed uses of the data, Therefore, the FCSM is identifying best practices for reporting on quality dimensions of integrated data products created and produced in federal statistical programs. This report summarizes the activities of the FCSM Working Group in its first year.
Findings from the Integrated Data Workshops hosted by the Federal Committee on Statistical Methodology and Washington Statistical Society   The FCSM Working Group on Transparent Quality Reporting in the Integration of Multiple Data Sources and the Washington Statistical Society co-hosted three workshops that explored current practices with respect to reporting on the quality of integrated data. This report, developed in partnership with the Joint Program in Statistical Methodology (JPSM) University of Maryland, summarizes the three workshops and the key themes emerging from them. These workshops are input to the Transparent Quality Reporting in the Integration of Multiple Data Sources: A Progress Report, 2017-2018.
Transparency in the Reporting of Quality for Integrated Data: A Review of International Standards and Guidelines   The research landscape for federal statistical agencies is moving to a new paradigm in which survey data are no longer the principal data type. This shift is due to growing challenges facing traditional survey research, including an increasing reluctance of people to complete surveys and deteriorating coverage of sample frames. The new paradigm is characterized by the use of administrative data and other forms of Big Data as alternatives to survey data, and, increasingly, the use of integrated data that combines data from multiple sources, such as linked survey and administrative data. This new paradigm necessitates new quality standards that address integrated data. This report reviews information on international standards and guidelines on quality reporting relative to statistical estimates that combine survey data with other types of data.

Learn more about FCSM…