Confidentiality Disclosure And Data Access

There is a fundamental tension at the heart of every statistical agency mission. Each is charged with collecting high quality data to inform the national policy and enable statistical research. This necessitates dissemination of both summary and micro data. Each is also charged with protecting the confidentiality of survey respondents. This often necessitates the blurring of the data to reduce the probability of the re-identification of individuals. The tradeoff dilemma, which could well be stated as protecting confidentiality (avoiding disclosure) but optimizing access, has become more complex as both technological advances and public perceptions have altered in an information age. Fortunately, statistical disclosure techniques have kept pace with these changes. This volume is intended to provide a review of new state of the art techniques that directly address these issues from both a theoretical and practical perspective. It provides a review of new research in the area of confidentiality and statistical disclosure techniques. A major section of the book provides an overview of new advances in the field of both economic and demographic data in measuring disclosure risk and information loss. It also presents new information on the different approaches taken by statistical agencies in disseminating data - ranging from licensing agreements , to secure access and provides a new survey of what statistical disclosure techniques are used by statistical agencies around the world. This is complimented by a series of chapters on public perceptions of statistical agency actions, including the results of a new survey on business perceptions. The book concludes with a chapter on the challenges of technology to data protection. National Statistical Agencies, statistical practitioners, thinktanks, research organisations and universities will find this a useful tool.

Regional health care databases are being established around the country with the goal of providing timely and useful information to policymakers, physicians, and patients. But their emergence is raising important and sometimes controversial questions about the collection, quality, and appropriate use of health care data. Based on experience with databases now in operation and in development, Health Data in the Information Age provides a clear set of guidelines and principles for exploiting the potential benefits of aggregated health dataâ€"without jeopardizing confidentiality. A panel of experts identifies characteristics of emerging health database organizations (HDOs). The committee explores how HDOs can maintain the quality of their data, what policies and practices they should adopt, how they can prepare for linkages with computer-based patient records, and how diverse groups from researchers to health care administrators might use aggregated data. Health Data in the Information Age offers frank analysis and guidelines that will be invaluable to anyone interested in the operation of health care databases.

Federal government statistics provide critical information to the country and serve a key role in a democracy. For decades, sample surveys with instruments carefully designed for particular data needs have been one of the primary methods for collecting data for federal statistics. However, the costs of conducting such surveys have been increasing while response rates have been declining, and many surveys are not able to fulfill growing demands for more timely information and for more detailed information at state and local levels. Innovations in Federal Statistics examines the opportunities and risks of using government administrative and private sector data sources to foster a paradigm shift in federal statistical programs that would combine diverse data sources in a secure manner to enhance federal statistics. This first publication of a two-part series discusses the challenges faced by the federal statistical system and the foundational elements needed for a new paradigm.

Improving Access to and Confidentiality of Research Data summarizes a workshop convened by the Committee on National Statistics (CNSTAT) to promote discussion about methods for advancing the often conflicting goals of exploiting the research potential of microdata and maintaining acceptable levels of confidentiality. This report outlines essential themes of the access versus confidentiality debate that emerged during the workshop. Among these themes are the tradeoffs and tensions between the needs of researchers and other data users on the one hand and confidentiality requirements on the other; the relative advantages and costs of data perturbation techniques (applied to facilitate public release) versus restricted access as tools for improving security; and the need to quantify disclosure risksâ€"both absolute and relativeâ€"created by researchers and research data, as well as by other data users and other types of data.

Because statistical confidentiality embraces the responsibility for both protecting data and ensuring its beneficial use for statistical purposes, those working with personal and proprietary data can benefit from the principles and practices this book presents. Researchers can understand why an agency holding statistical data does not respond well to the demand, “Just give me the data; I’m only going to do good things with it.” Statisticians can incorporate the requirements of statistical confidentiality into their methodologies for data collection and analysis. Data stewards, caught between those eager for data and those who worry about confidentiality, can use the tools of statistical confidentiality toward satisfying both groups. The eight chapters lay out the dilemma of data stewardship organizations (such as statistical agencies) in resolving the tension between protecting data from snoopers while providing data to legitimate users, explain disclosure risk and explore the types of attack that a data snooper might mount, present the methods of disclosure risk assessment, give techniques for statistical disclosure limitation of both tabular data and microdata, identify measures of the impact of disclosure limitation on data utility, provide restricted access methods as administrative procedures for disclosure control, and finally explore the future of statistical confidentiality.

Americans are increasingly concerned about the privacy of personal dataâ€"yet we demand more and more information for public decision making. This volume explores the seeming conflicts between privacy and data access, an issue of concern to federal statistical agencies collecting the data, research organizations using the data, and individuals providing the data. A panel of experts offers principles and specific recommendations for managing data and improving the balance between needed government use of data and the privacy of respondents. The volume examines factors such as the growth of computer technology, that are making confidentiality an increasingly critical problem. The volume explores how data collectors communicate with data providers, with a focus on informed consent to use data, and describes the legal and ethical obligations data users have toward individual subjects as well as toward the agencies providing the data. In the context of historical practices in the United States, Canada, and Sweden, statistical techniques for protecting individuals' identities are evaluated in detail. Legislative and regulatory restraints on access to data are examined, including a discussion about their effects on research. This volume will be an important and thought-provoking guide for policymakers and agencies working with statistics as well as researchers and concerned individuals.

Privacy in statistical databases is about ?nding tradeo?s to the tension between the increasing societal and economical demand for accurate information and the legal and ethical obligation to protect the privacy of individuals and enterprises, which are the source of the statistical data. Statistical agencies cannot expect to collect accurate information from individual or corporate respondents unless these feel the privacy of their responses is guaranteed; also, recent surveys of Web users show that a majority of these are unwilling to provide data to a Web site unless they know that privacy protection measures are in place. “Privacy in Statistical Databases2004” (PSD2004) was the ?nal conference of the CASC project (“Computational Aspects of Statistical Con?dentiality”, IST-2000-25069). PSD2004 is in the style of the following conferences: “Stat- tical Data Protection”, held in Lisbon in 1998 and with proceedings published by the O?ce of O?cial Publications of the EC, and also the AMRADS project SDC Workshop, held in Luxemburg in 2001 and with proceedings published by Springer-Verlag, as LNCS Vol. 2316. The Program Committee accepted 29 papers out of 44 submissions from 15 di?erentcountriesonfourcontinents.Eachsubmittedpaperreceivedatleasttwo reviews. These proceedings contain the revised versions of the accepted papers. These papers cover the foundations and methods of tabular data protection, masking methods for the protection of individual data (microdata), synthetic data generation, disclosure risk analysis, and software/case studies.

The need for quality improvement and for cost saving are driving both individual choices and health system dynamics. The health services research that we need to support informed choices depends on access to data, but at the same time, individual privacy and patient-health care provider confidentiality must be protected.