sdcMicro (version 2.6.3)

sdcMicro-package: Statistical Disclosure Control (SDC) for the generation of protected microdata for researchers and for public use.

Description

This package includes all methods of the popular software mu-Argus plus several new methods. In comparison with mu-Argus the advantages of this package are that the results are fully reproducible even with the included GUI, that the package can be used in batch-mode from other software, that the functions can be used in a very flexible way, that everybody could look at the source code and that there are no time-consuming meta-data management is necessary. However, the user should have a detailed knowledge about SDC when applying the methods on data. The implemented graphical user interface (GUI) for microdata protection serves as an easy-to-handle tool for users who want to use the sdcMicro package for statistical disclosure control but are not used to the native R command line interface. In addition to that, interactions between objects which results from the anonymization process are provided within the GUI. This allows an automated recalculation and displaying information of the frequency counts, individual risk, information loss and data utility after each anonymization step. In addition to that, the code for every anonymization step carried out within the GUI is saved in a script which can then be easily modified and reloaded. Please note, that methods shuffling, robShuffle (robust shuffling), gadp and robgadp are not included in the package because method shuffling is under a US-patent by other authors, even shuffling consits only of 8 lines of code ...

Details

ll{ Package: sdcMicro Type: Package Version: 2.5.9 Date: 2009-07-22 License: GPL 2.0 }

References

Templ, M. Statistical Disclosure Control for Microdata Using the R-Package sdcMicro, Transactions on Data Privacy, vol. 1, number 2, pp. 67-85, 2008. http://www.tdp.cat/issues/abs.a004a08.php Templ, M. New Developments in Statistical Disclosure Control and Imputation: Robust Statistics Applied to Official Statistics, Suedwestdeutscher Verlag fuer Hochschulschriften, 2009, ISBN: 3838108280, 264 pages.

Examples

## example from Capobianchi, Polettini and Lucarelli:
data(francdat)
f <- freqCalc(francdat, keyVars=c(2,4,5,6),w=8)
f
f$fk
f$Fk
## with missings:
x <- francdat
x[3,5] <- NA
x[4,2] <- x[4,4] <- NA
x[5,6]  <- NA
x[6,2]  <- NA
f2 <- freqCalc(x,  keyVars=c(2,4,5,6),w=8)
f2$Fk
## individual risk calculation:
indivf <- indivRisk(f)  
indivf$rk         
## Local Suppression            
localS <- localSupp(f, keyVar=2, indivRisk=indivf$rk, threshold=0.25)
f2 <- freqCalc(localS$freqCalc, keyVars=c(2,4,5,6), w=8)
indivf2 <- indivRisk(f2)
indivf2$rk

## select another keyVar and run localSupp once again, if you think the table is not fully protected
data(free1)
f <- freqCalc(free1, keyVars=1:3, w=30)
ind <- indivRisk(f)
## and now you can use the interactive plot for individual risk objects: 
## plot(ind)

## Local suppression with localSupp2 and localSupp2Wrapper is more effective:
## example from Capobianchi, Polettini and Lucarelli:
data(francdat)
l1 <- localSupp2(francdat, keyVars=c(2,4,5,6), w=8)
l1
l1$x
l2 <- localSupp2(francdat, keyVars=c(2,4,5,6), w=8, k=2)
l3 <- localSupp2(francdat, keyVars=c(2,4,5,6), w=8, k=4)
## long computation time:
## l = localSupp2(free1, keyVar=1:3, w=30, k=2, importance=c(0.1,1,0.8))

## we want to avoid missings in column 5:
l1 <- localSupp2Wrapper(francdat, keyVars=c(2,4,5,6), importance=c(1,1,0,1), w=8, kAnon=1)
l1$x
## we want to avoid missings in column 5 and allow missings in 1 only if
## is really necessary:
l1 <- localSupp2Wrapper(francdat, keyVars=c(2,4,5,6), importance=c(0.1,1,0,1), w=8, kAnon=1)
l1$x
plot(l1)

## Data from mu-Argus:
## Global recoding:
data(free1)
free1[, "AGE"] <- globalRecode(free1[,"AGE"], c(1,9,19,29,39,49,59,69,100), labels=1:8)

## Top coding:
topBotCoding(free1[,"DEBTS"], value=9000, replacement=9100, kind="top")

## Numerical Rank Swapping:
## do not use the mu-Argus test data set (free1) since the numerical variables are (probably) faked.
data(Tarragona)
Tarragona1 <- swappNum(Tarragona, p=10) 

## Microaggregation:
m1 <- microaggregation(Tarragona, method="onedims", aggr=3)
m2 <- microaggregation(Tarragona, method="pca", aggr=3)
# summary(m1)
# valTable(Tarragona, method=c("simple","onedims","pca")) ## approx. 1 minute computation time

data(microData)
m1 <- microaggregation(microData, method="mdav")
x <- m1$x  ### fix me
summary(m1)
plotMicro(m1, 0.1, which.plot=1)  # too less observations...
data(free1)
plotMicro(microaggregation(free1[,31:34], method="onedims"), 0.1, which.plot=1)


## disclosure risk (interval) and data utility:
data(free1)
m1 <- microaggregation(Tarragona, method="onedims", aggr=3)
dRisk(x=Tarragona, xm=m1$blowxm)
dRisk(x=Tarragona, xm=m2$blowxm)
dUtility(x=Tarragona, xm=m1$blowxm)
dUtility(x=Tarragona, xm=m2$blowxm)

## S4 class code for Adding Noise methods will be included in the next version of sdcMicro.

## Fast generation of synthetic data with aprox. the same covariance matrix as the original one.

data(mtcars)
cov(mtcars[,4:6])
cov(dataGen(mtcars[,4:6],n=200))
pairs(mtcars[,4:6])
pairs(dataGen(mtcars[,4:6],n=200))

## PRAM

set.seed(123)
x <- sample(1:4, 250, replace=TRUE)
pr1 <- pram(x)
length(which(pr1$x == x))
x2 <- sample(1:4, 250, replace=TRUE)
length(which(pram(x2)$x == x2))

data(free1)
marstatPramed <- pram(free1[,"MARSTAT"])