GitHub

StatMatch R pakage

Marcello D’Orazio

Statistical Matching or Data Fusion

CRAN version CRAN downloadsMentioned in Awesome Official Statistics


Overview

StatMatch is an R package for integrating two data sources referring to the same target population that share a number of common variables. Integration can be performed at:

  • micro level — producing a synthetic (fused) file
  • macro level — estimating correlation coefficients, regression coefficients, contingency tables, etc.

Some functions can also be used to impute missing values through hot deck imputation methods.


Installation

Install the stable version from CRAN:

install.packages("StatMatch")

Main Features

  • Non-parametric hot deck imputation: random, rank, and nearest-neighbour methods
  • Predictive mean matching: a mixed parametric-nonparametric procedure
  • Complex survey designs: methods for data from surveys with unequal weights
  • Uncertainty analysis: tools to explore the uncertainty inherent in the statistical matching framework

Documentation & Tutorials

Additional material including vignettes, tutorials, and presentations is available in the Tutorials_Vignette_OtherDocs folder.


References

  • D’Orazio M., Di Zio M., Scanu M. (2006) Statistical Matching, Theory and Practice. Wiley, Chichester.
  • D’Orazio M. (2015) Integration and imputation of survey data in R: the StatMatch package, Romanian Statistical Review, 2/2015, pp. 57–68.

Links

Read the original on github.com ↗