extractManipData: Remove certain variables from the data set inside a sdc...

In sdcMicro: Statistical Disclosure Control Methods for Anonymization of Microdata and Risk Estimation

Description

Extract the manipulated data from an object of class sdcMicroObj-class

Usage

extractManipData(obj, ignoreKeyVars = FALSE, ignorePramVars = FALSE,
  ignoreNumVars = FALSE, ignoreGhostVars = FALSE, ignoreStrataVar = FALSE,
  randomizeRecords = "no")

Arguments

obj	object of class sdcMicroObj-class
ignoreKeyVars	If manipulated KeyVariables should be returned or the unchanged original variables
ignorePramVars	if manipulated PramVariables should be returned or the unchanged original variables
ignoreNumVars	if manipulated NumericVariables should be returned or the unchanged original variables
ignoreGhostVars	if manipulated Ghost (linked) Variables should be returned or the unchanged original variables
ignoreStrataVar	if manipulated StrataVariables should be returned or the unchanged original variables
randomizeRecords	(logical) specifies, if the output records should be randomized. The following options are possible: 'no'default, no randomization takes place 'simple'records are just randomly swapped. 'byHH'if slot 'hhId' is not NULL, the clusters defined by this variable are randomized across the dataset. If slot 'hhId' is NULL, the records or the dataset are randomly changed. 'withinHH'if slot 'hhId' is not NULL, the clusters defined by this variable are randomized across the dataset and additionally, the order of records within the clusters are also randomly changed. If slot 'hhId' is NULL, the records or the dataset are randomly changed.

Value

a data.frame containing the anonymized data set

Author(s)

Alexander Kowarik, Bernhard Meindl

Examples

## for objects of class sdcMicro:
data(testdata2)
sdc <- createSdcObj(testdata,
  keyVars=c('urbrur','roof'),
  numVars=c('expend','income','savings'), w='sampling_weight')
sdc <- removeDirectID(sdc, var="age")
dataM <- extractManipData(sdc)

sdcMicro documentation built on May 16, 2018, 5:06 p.m.