A Framework for Evaluating the Utility of Data Altered to Protect Confidentiality

Karr, Alan F.; Kohnen, Christine N.; Oganian, Anna; Reiter, Jerome P.; Sanil, Ashish

doi:10.1198/000313006x124640

Cited by 160 publications

(126 citation statements)

References 18 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…This disclosure risk must be weighted by the data releaser against the complementary concept of data utility, which measures the value of the released data source to the legitimate data user. In general, decreasing the amount of disclosure risk by applying more stringent geographic masking processes also decreases the accuracy of inferences obtainable from the released data source (Karr et al, 2006). While there is a wide understanding of this tradeoff between disclosure risk and data utility, there is no consensus on a particular methodology to visualize and share confidential data without dramatically limiting any analyses (Curtis et al, 2011).…”

Section: Literature Reviewmentioning

confidence: 99%

Wider Dissemination of Household Travel Survey Data Using Geographical Perturbation Methods

Clifton¹,

Gehrke²

2014

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Wider Dissemination of Household Travel Survey Data Using Geographical Perturbation Methods

Clifton¹,

Gehrke²

2014

View full text Add to dashboard Cite

“…Reiter (2012) mentions, without presenting numerical results, that the comparison of measures based on specific models is often done informally. If the regression coefficients obtained from original and perturbed data are considered close, for example if the confidence intervals obtained from the models largely overlap, the released data have high utility for that particular analysis (see also Karr et al 2006). …”

Section: General Methods For Measuring Data Utilitymentioning

confidence: 99%

“…They concentrate only on data utility measures and do not account for disclosure risk. Karr et al (2006) propose measures based on differences between inferences on original and perturbed data that are tailored to normally distributed data, and they also use the propensity score method in Oganian and Karr (2006). Reiter (2012) mentions, without presenting numerical results, that the comparison of measures based on specific models is often done informally.…”

Section: General Methods For Measuring Data Utilitymentioning

confidence: 99%

Quality Indicators for Statistical Disclosure Methods: A Case Study on the Structure of Earnings Survey

Templ

2015

Journal of Official Statistics

View full text Add to dashboard Cite

1Scientific-or public-use files are typically produced by applying anonymisation methods to the original data. Anonymised data should have both low disclosure risk and high data utility.Data utility is often measured by comparing well-known estimates from original data and anonymised data, such as comparing their means, covariances or eigenvalues.However, it is a fact that not every estimate can be preserved. Therefore the aim is to preserve the most important estimates, that is, instead of calculating generally defined utility measures, evaluation on context/data dependent indicators is proposed.In this article we define such indicators and utility measures for the Structure of Earnings Survey (SES) microdata and proper guidelines for selecting indicators and models, and for evaluating the resulting estimates are given. For this purpose, hundreds of publications in journals and from national statistical agencies were reviewed to gain insight into how the SES data are used for research and which indicators are relevant for policy making.Besides the mathematical description of the indicators and a brief description of the most common models applied to SES, four different anonymisation procedures are applied and the resulting indicators and models are compared to those obtained from the unmodified data. The disclosure risk is reported and the data utility is evaluated for each of the anonymised data sets based on the most important indicators and a model which is often used in practice.

show abstract

“…In particular, we estimate a AR(2) process for each of X k t , X s k t , and X (i) k t . We then assess the number of missing time-series estimates (repeated suppressions in X s k t may lead to time-series that are too short), the number of significant coefficients for the first lag of the AR (2) 1 , and the interval overlap measure J k as suggested by [12]. Table 2 presents these results for job creation births.…”

Section: Analytical Validitymentioning

confidence: 99%

Using Partially Synthetic Data to Replace Suppression in the Business Dynamics Statistics: Early Results

Miranda

Vilhuber

2014

Privacy in Statistical Databases

View full text Add to dashboard Cite

Abstract. The Business Dynamics Statistics is a product of the U.S. Census Bureau that provides measures of business openings and closings, and job creation and destruction, by a variety of cross-classifications (firm and establishment age and size, industrial sector, and geography). Sensitive data are currently protected through suppression. However, as additional tabulations are being developed, at ever more detailed geographic levels, the number of suppressions increases dramatically. This paper explores the option of providing public-use data that are analytically valid and without suppressions, by leveraging synthetic data to replace observations in sensitive cells.

show abstract

A Framework for Evaluating the Utility of Data Altered to Protect Confidentiality

Cited by 160 publications

References 18 publications

Wider Dissemination of Household Travel Survey Data Using Geographical Perturbation Methods

Wider Dissemination of Household Travel Survey Data Using Geographical Perturbation Methods

Quality Indicators for Statistical Disclosure Methods: A Case Study on the Structure of Earnings Survey

Using Partially Synthetic Data to Replace Suppression in the Business Dynamics Statistics: Early Results

Contact Info

Product

Resources

About