Learn R Programming

sdcMicro

sdcMicro is an R-package to anonymize microdata. Most functionalities of the package are also available via an interactive shiny-based graphical user interface.

The online documentation can also be found at sdctools.github.io/sdcMicro.

Copy Link

Version

Install

install.packages('sdcMicro')

Monthly Downloads

2,443

Version

5.8.0

License

GPL-2

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/sdcTools/sdcMicro

Maintainer

Matthias Templ

Last Published

January 9th, 2026

Functions in sdcMicro (5.8.0)

distributeRandom_cpp

extractManipData

Remove certain variables from the data set inside a sdc object.

Additional Information-Loss measures

Demo data set from mu-Argus

get.sdcMicroObj

get.sdcMicroObj

Join levels of a variables in an object of class sdcMicroObj-class or factor or data.frame

Global Recoding

Generate one strata variable from multiple factors

Fast and Simple Microaggregation

kAnon_violations

kAnon_violations

Calculate information loss after targeted record swapping

localSuppression

Local Suppression to obtain k-anonymity

Print method for objects from class micro

Disclosure Risk for Categorical Variables

Detection and winsorization of multivariate outliers

mergeHouseholdData

Replaces the raw household-level data with the anonymized household-level data in the full dataset for anonymization of data with a household structure (or other hierarchical structure). Requires a matching household ID in both files.

patch_groupAndRename_age

Patch faulty groupAndRename() for 'age' in LLM-generated strategy code

Print method for objects from class modrisk

Local Suppression

extract_variable_metadata

Extract Metadata from a Dataset

plot.localSuppression

Plots for localSuppression objects

Random Sampling

Global risk using log-linear models.

data from the casc project

Individual Risk computation

set.sdcMicroObj

set.sdcMicroObj

Remove certain variables from the data set inside a sdc object.

Generate an Html-report from an sdcMicroObj

Print method for objects from class pram

print.sdcMicroObj

Print and Extractor Functions for objects of class sdcMicroObj-class

Post Randomization

Summary method for objects from class pram

Summary method for objects from class micro

sampleDonor_cpp

Random sample for donor records

Print method for objects from class freqCalc.

print.indivRisk

Print method for objects from class indivRisk

Print method for objects from class suda2

Define Swap-Levels

Targeted Record Swapping

query_llm_for_roles

#' Query LLM to Classify Variable Roles

A real-world data set on household income and expenditures

Top and Bottom Coding

print.localSuppression

Print method for objects from class localSuppression

Suda2: Detecting Special Uniques

Creates new randomized IDs

overal disclosure risk

Microaggregation for numerical and categorical key variables based on a distance similar to the Gower Distance

Fast generation of synthetic data

distributeDraws_cpp

Distribute number of swaps

Comparison of different microaggregation methods

summary.freqCalc

Summary method for objects from class freqCalc

Change the a keyVariable of an object of class sdcMicroObj-class from Numeric to Factor or from Factor to Numeric

microaggregation

Microaggregation

Comparison plots

plot.sdcMicroObj

Plotfunctions for objects of class sdcMicroObj

Shuffling and EGADP

subsetMicrodata

subsetMicrodata

Targeted Record Swapping

show,sdcMicroObj-method

read_codebook_snippet

Read and summarize a codebook file for LLM prompt

sdcMicro-package

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

sdcMicroObj-class

Class "sdcMicroObj"

selectHouseholdData

Creates a household level file from a dataset with a household structure.

Tarragona data set

KI_createSdcObj

Create an sdcMicro Object with LLM Assistance

KI_applyAnonymization

KI_applyAnonymization: Automatically apply anonymization strategy using LLM

argus_microaggregation

argus_microaggregation

CASCrefmicrodata

Census data set

Local recoding via Edmond's maximum weighted matching algorithm

Adding noise to perturb data

Recompute Risk and Frequencies for a sdcMicroObj

Clean LLM-generated R code

Small Artificial Data set

Dummy Dataset for Record Swapping

build_llm_prompt

Build LLM Prompt for Variable Role Classification

Data-Utility measures

RMD based disclosure risk

build_anonymization_prompt

Build anonymization strategy prompt from summary info Build anonymization strategy prompt from summary info

Frequencies calculation for risk estimation