Package dk.alexandra.fresco.stat.anonymisation

Class NoisyStats

Object

NoisyStats

All Implemented Interfaces:

Computation<List<DRes<SFixed>>,ProtocolBuilderNumeric>

public class NoisyStats
extends Object
implements Computation<List<DRes<SFixed>>,ProtocolBuilderNumeric>

Compute differentially private estimates for the coefficients of a linear model fitted on a dataset. The method is based on the paper Differentially Private Simple Linear Regression by Alabi et. al.

Constructor Summary

Constructors

Constructor	Description
NoisyStats(List<DRes<SFixed>> x, List<DRes<SFixed>> y, double epsilon)

Method Summary

Modifier and Type	Method	Description
DRes<List<DRes<SFixed>>>	buildComputation(ProtocolBuilderNumeric root)

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

NoisyStats

public NoisyStats(List<DRes<SFixed>> x, List<DRes<SFixed>> y, double epsilon)

Method Details

buildComputation

public DRes<List<DRes<SFixed>>> buildComputation(ProtocolBuilderNumeric root)

Specified by:

buildComputation in interface Computation<List<DRes<SFixed>>,ProtocolBuilderNumeric>