http://statmath.wu.ac.at/~hornik/
KURT HORNIK: SOFTWARE
My truly major project is working on R, an open source implementation of the award-winning language S for data analysis and graphics. R is free software distributed under a GNU-style copyleft, and an official part of the GNU project ("GNU S").
I am a member of the R Core Team, a group of individuals located in Austria, Denmark, England, Italy, New Zealand, Switzerland, and the U.S.A., who collectively develop the R base distribution.
I am the principal architect and maintainer of the "Comprehensive R Archive Network" (CRAN), a collection of sites which carry identical material, consisting of the R distribution(s), the contributed extensions, documentation for R, and binaries.
I have written the packages clue (for computing on CLUster Ensembles), OAIHarvester (functionality for harvesting and processing OAI-PMH metadata), ISOcodes (ISO language, territory, currency, script and character codes) and Unicode (Unicode character data and utilities), and coauthored a variety of packages including RKEA (an interface to KEA [for Keyphrase Extraction Algorithm]), RWeka (an interface to Weka, a collection of machine learning algorithms for data mining tasks written in Java), Rglpk (an interface to the GNU Linear Programming Kit), Rsymphony (an interface to the to the SYMPHONY MILP solver), TSP (infrastructure and some algorithms for Traveling Salesperson Problems), arules (a computational environment for mining Association RULES and frequent itemsets), coin (COnditional INference procedures in a permutation test framework), e1071 (a collection of functions for Independent Component and Latent Class Analysis, support vector machines, fuzzy and voting/bagged clustering, and more), exactRankTests (exact conditional inference for rank tests for the 2-sample problem), isotone (active set and generalized PAVA for isotone optimization), kernlab (Kernel-based machine learning methods including support vector machines), party (unbiased recursive partitioning in a conditional inference framework), movMF (inference for mixtures von Mises-Fisher distributions), openNLP (an interface to openNLP, a collection of natural language processing tools), relations (data structures and algorithms for relations), seriation (infrastructure for seriation), sets (data structures and basic operations for sets and generalized sets), skmeans (spherical k-means clustering), slam (Sparse Lightweight Arrays and Matrices), strucchange (tests for STRUCtural CHANGE in linear regression relationships), tau (utilities for text analysis), textcat (n-gram based text categorization), topicmodels (topic models for text), tseries (advanced time series analysis and computational finance), vcd (Visualizing Categorical Data), and wordnet (an interface to WordNet using the Jawbone Java API to WordNet). I also maintain several other packages I ported from S.
Contributions to the R base system include in particular a collection of classical statistical inference tools such as the Bartlett, Fisher, Kruskal-Wallis, Kolmogorov-Smirnov, and Wilcoxon tests, formerly in package 'ctest' and in the base package 'stats' as of R 1.9.0).
I have developed a quality management system for R and its extension packages.
I maintain the R FAQ which should help you obtaining further information on R.
I am part of the development team of ESS ("Emacs Speaks Statistics"), an Emacs Lisp interface for interactive statistical programming and data analysis which currently supports S dialects (R, S 3/4, and S-PLUS 3.x/4.x/5.x/6.x), SAS, BUGS, Stata, and XLispStat (including Arc and ViSta).
I am part of the core group of Bioconductor, an open source initiative with the primary goal of providing infrastructure in terms of design and software for analyzing genomic data.
The most current versions of the R base distribution, my as well as others' extension packages, and ESS are always available from CRAN.
I have also written an Emacs Lisp interface (EOS, Emacs Octave Support) and a multitude of code scripts for Octave, a high-level language, primarily intended for numerical computations, similar to Matlab. The scripts, formerly available as part of our site's 'octave-ci' collection, and EOS have meanwhile been integrated into the Octave distribution; EOS is also part of GNU Emacs 20 or later.
以及一大堆paper: http://statmath.wu.ac.at/~hornik/papers.html