tableDataAccess: Differentially Private Contingency Table Data Access Function

In DPpack: Differentially Private Statistical Analysis and Machine Learning

Differentially Private Contingency Table Data Access Function

Description

This function performs the data access step in the computation of a differentially private contingency table. The true values are computed using table,while the sensitivities are calculated based on bounded and unbounded differential privacy \insertCiteKifer2011DPpack according to the theoretical values \insertCiteLiu2019bDPpack.

Usage

tableDataAccess(..., mechanism = "Laplace")

Arguments

...	Vectors of data from which to create the contingency table.
mechanism	String indicating which mechanism to use for differential privacy. If the 'Laplace' mechanism is chosen, l1 sensitivities are returned. If the 'Gaussian' mechanism is chosen, l2 sensitivities are returned.

Value

List of the true contingency table and the sensitivities calculated based on bounded and unbounded differential privacy.

References

\insertRef

Liu2019bDPpack

\insertRef

Kifer2011DPpack

Examples

x <- MASS::Cars93$Type;
y <- MASS::Cars93$Origin;
tableDataAccess(x, y, mechanism='Laplace')

DPpack documentation built on April 8, 2023, 9:09 a.m.