B1761
Title: FSDA4R: Porting the FSDA toolbox to R
Authors: Emmanuele Sordini - Joint Research Centre (JRC) (Italy) [presenting]
Valentin Todorov - UNIDO (Austria)
Aldo Corbellini - Faculty of Economics - University of Parma (Italy)
Abstract: The FSDA (Flexible Statistics for Data Analysis) toolbox is a software library that extends MATLAB and its Statistics Toolbox to support a robust and efficient analysis of complex datasets, affected by different sources of heterogeneity. FSDA was born around the forward search approach, and has since developed to become a comprehensive and computationally efficient software package for robust statistics, thanks to its tools for regression and multivariate analysis, robust transformations, cluster analysis and model selection. A distinctive feature motivating the choice of the MATLAB platform is its high level of interactivity, which is particularly useful for exploratory data analysis and for a deep understanding of the influence of each individual observation on statistical estimates. One downside of FSDA, however, is that it is based on commercial software (MATLAB), and therefore it is not so appealing to the bulk of the statistical community, where the use of R is predominant. For this reason, we started a new project of porting selected FSDA tools to R (FSDA4R) which we hope to make available to the R community as an R package in CRAN. In particular, we plan to implement several general-purpose R methods, along the lines of the approach adopted in rrcov and robustbase. This presentation will focus on: i) The code porting approach; ii) The pre-requisites to be met in order to use FSDA functions in R; iii) The features of FSDA currently available in R and iv) A live demo.
Journal