Multiple Imputation for Statistical Disclosure Limitation

By Trivellore E. Raghunathan, Jerome P. Reiter, Donald B. Rubin. 2003

500 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Synthesizing Tabular Data using Generative Adversarial Networks (2018, background): “At the same time, some researchers in the statistical sciences community have begun been using randomization-based methods to generate synthetic data [40, 37, 39, 25].”
Utility-Privacy Tradeoffs in Databases: An Information-Theoretic Approach (2011, background): “…transaction, a user learns some public information (e.g. gender and weight), which is allowed and needs to be supported for the transaction to be meaningful, and at the same time he can also learn/infer private information (e.g., cancer and income), which needs to be prevented (or minimized).”
An Ad Omnia Approach to Defining and Achieving Private Data Analysis (2007, background): “There is a rich literature on this problem, principally from the satistics community [11, 15, 24, 25, 26, 34, 36, 23, 35] (see also the literature on controlled release of tabular data, contingency tables, and cell suppression), and from such diverse branches of computer science as algorithms, datab”
Toward Privacy in Public Databases (2005, background): “The statistics literature on imputed data (e.g., [ 26 ] should be helpful in this endeavor.”
Releasing multiply imputed, synthetic public use microdata: an illustration and empirical study (2005, methodology): “Inferential methods that are appropriate for such partially synthetic data sets have been developed by Reiter (2003).”
Differential Privacy for Statistics: What we Know and What we Want to Learn (2010, methodology): “Synthetic data. There has been interest in using synthetic data for protecting privacy ever since Rubin rst proposed that imputation might be helpful in this context [50]. Recent examples include [31, 48 ].”
Generation and evaluation of synthetic patient data (2020, methodology): “An empirical study of releasing synthetic data under the methods proposed in Raghunathan, Reiter and Rubin [14] is presented in Reiter and Drechsler [18].”
Satisfying Disclosure Restrictions With Synthetic Data Sets (2002, methodology): “To describe construction of and inferences from multiple synthetic data sets, we use notation similar to that of Raghunathan et al. (2003). Let Ij = 1 if unit j is selected in the original survey, and Ij = 0 otherwise.”
Privacy-Preserving Datamining on Vertically Partitioned Databases (2004, background): “Other widely-studied techniques include cell suppression, adding simulated data, releasing only a subset of observations, releasing only a subset of attributes, releasing synthetic or partially synthetic data [13,12], data-swapping, and post-randomization.”
Significance tests for multi-component estimands from multiply imputed, synthetic microdata (2005, methodology): “This extends the work of Raghunathan et al. (2003) and Reiter (2003), who develop inferential methods for scalar estimands but do not consider multi-component hypothesis testing.”
Differential Privacy: A Survey of Results (2008, unknown): “There is a rich literature on this problem, principally from the satistics community (see, e.g., [10] [14] [27] [28] [29] [38] [40] [26] [39] and the literature on controlled release of tabular data, contingency tables, and cell suppression), and from such diverse branches of computer science as…”
Economic Analysis and Statistical Disclosure Limitation (2016, methodology): “Abowd and Woodcock (2001), Raghunathan et al. (2003) and Reiter (2004) refined the Rubin and Little methods, allowing them to be applied to complex survey data and combined with other missing data imputations.”
A Framework for Evaluating the Utility of Data Altered to Protect Confidentiality (2006, background): “In the extreme case of synthetic data (Raghunathan et al., 2003; Reiter, 2005b), D0(r ) = D for all r .”
Privacy: Theory meets Practice on the Map (2008, methodology): “Prior to this work, synthetic data methods did not have formal privacy guarantees, despite there being significant work on performing statistical analyses of and drawing inferences from synthetic data [2], [3] based on Rubin's multiple imputation framework [16].”
A Survey of Inference Control Methods for Privacy-Preserving Data Mining (2008, background): “Rubin’s proposal was more completely developed in [57].”
Secure Regression on Distributed Databases (2005, background): “Even entirely synthetic databases may be created, which preserve some characteristics of the original data, but whose records simply do not correspond to real individuals or establishments (Duncan and Keller-McNulty 2001; Reiter 2003a; Raghunathan, Reiter, and Rubin 2003).”
Using CART to generate partially synthetic public use microdata (2005, methodology): “(Raghunathan et al. 2003; Reiter 2005a), generating plausible synthetic data for all”
Synthetic Data for Deep Learning (2019, background): “Since the main emphasis of the present survey is on synthetic data for deep learning, we do not go into details about multiple imputation and refer to the book [156] and the main recent sources in the field [155,476,483,485].”