Differential Privacy for Clinical Trial Data: Preliminary Evaluations

By Duy Vu, Aleksandra B. Slavkovic. 2009

135 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Public Health, Environmental and Occupational Health

How researchers see this paper

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

In Artificial Intelligence

In Public Health, Environmental and Occupational Health

Citations in the corpus

Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing (2014, neutral): “Differential privacy (DP) is a popular framework for designing statistical release mechanisms, and is often proposed as a solution to privacy concerns in medical settings [10, 12, 45, 47].”
Convergence Rates for Differentially Private Statistical Estimation (2012, background): “Moreover, it has been empirically observed ( e.g. , Chaudhuri et al., 2011; Vu & Slavkovic, 2009) that there is often a signiﬁcant gap in statistical eﬃciency between a diﬀerentially private estimator and its non-private counterpart.”
Differentially Private Bayesian Linear Regression (2019, methodology): “…to point estimation of regression coefﬁcients, including sufﬁcient statistic perturbation (SSP) [Foulds et al., 2016, McSherry and Mironov, 2009, Vu and Slavkovic, 2009, Wang, 2018, Zhang et al., 2016], posterior sampling (OPS) [Dimitrakakis et al., 2014, Geumlek et al., 2017, Minami et al.,…”
Revisiting Differentially Private Hypothesis Tests for Categorical Data (2015, background): “Similar types of negative results produced by running off-the-shelf statistical analyses after input perturbation were reported by Vu and Slavkovic (2009) and Fienberg et al. (2010).”
Differentially Private Nonparametric Hypothesis Testing (2019, methodology): “[35] Duy Vu and Aleksandra Slavkovic.”
Statistical Approximating Distributions Under Differential Privacy (2018, background): “The ability to use differential privacy to protect data has raised the question of how useful would the data be in statistical applications [Wasserman and Zhou, 2010, Fienberg et al., 2010, Dwork and Lei, 2009, Vu and Slavkovic, 2009, Smith, 2011, Chaudhuri and Hsu, 2012].”
Improved Differentially Private Analysis of Variance (2019, background): “Vu and Slavković [21] give an analogue to the test and also compute accurate p-values.”
A New Class of Private Chi-Square Tests (2016, background): “Along these lines, [22] studies how many more samples would be needed before the test with additional noise recovers the same level of power as the original test on the actual data.”
Differentially Private M-Estimators (2011, background): “However, plugging in the perturbed values does not necessarily give the best inference procedure and better alternatives may be possible, see [15] for a hypothesis testing example in contingency tables.”
Differentially Private Uniformly Most Powerful Tests for Binomial Data (2018, methodology): “In Figure 1, we plot the empirical power of our UMP test, the Normal Approximation from Vu and Slavkovic (2009), and the non-private UMP.”
Privacy Preserving GWAS Data Sharing (2011, background): “For related simulations that demonstrate the interactive effect of sample size and privacy level and compare asymptotic efficiency of private and non-private estimators for 2×2 tables and the corresponding χ(2)-statistics, see [7].”
Differentially Private Chi-Squared Hypothesis Testing: Goodness of Fit and Independence Testing (2016, methodology): “If we assume that there is some prior estimates for the contingency table cell probabilities, Vu and Slavkovic (2009) determine the sample size adjustment for the Pearson chi-squared independence test that uses the private counts to achieve the same power as the test with the original counts.”
Privacy-Preserving Data Sharing for Genome-Wide Association Studies (2012, background): “For related simulations that demonstrate the interactive e↵ect of sample size and privacy level ✏ and compare asymptotic e ciency of private and non-private estimators for 2⇥ 2 tables and the corresponding 2-statistics, see [24].”
Privacy-Preserving Data Exploration in Genome-Wide Association Studies (2013, background): “Vu and Slavkovi´c [31] also consider applying differential privacy to medical research data, but focus on determining the population size needed to provide a given power to statistical tests when noise is added using standard mechanisms.”
Probabilistic Inference and Differential Privacy (2010, background): “Much of the existing statistical literature is concerned with identifying cases when the differentially-private observations are “as good” as traditional statistical estimators, in terms of efficiency [1], power [2], and minimax rates [3], and also robust estimators [4].”