R-Package

Page Source
'' The first half of this page is drawn from Wikipedia, (R_(programming_language)), since it is foolish to duplicate what they have already done. Thanks User:Supermjr for finding that content & bringing it in. Does someone know how to dynamically include relevant content from Wikipedia, so our version does not become outdated over time, and we don't have broken links embedded in the page?''

Information on the R-Package
'' R is an open-source statistical package, with capabilities similar to S (after which it was modeled), SPSS, STATA and SAS.

The R programming language, sometimes described as GNU S, is a programming language and software environment for statistical computing and graphics. It was originally created by Ross Ihaka and Robert Gentleman (hence the name R) at the University of Auckland, New Zealand, and is now developed by the R core team. R is considered by its developers to be an implementation of the S programming language, with semantics derived from Scheme.

R is widely used for statistical software development and data analysis, and has become a de-facto standard among statisticians for the development of statistical software. R's source code is freely available under the GNU General Public License, and pre-compiled binary versions are provided for Microsoft Windows, Mac OS X, and several Linux and other Unix-like operating systems. R uses a command line interface, though several graphical user interfaces are available.

Features
R supports a wide variety of statistical and numerical techniques. R is also highly extensible through the use of packages, which are user-submitted libraries for specific functions or specific areas of study. Due to its S heritage, R has stronger object-oriented programming facilities than most statistical computing languages. Extending R is also eased by its permissive lexical scoping rules.

Another of R's strengths is its graphical facilities, which produce publication-quality graphs which can include mathematical symbols.

Although R is mostly used by statisticians and other practitioners requiring an environment for statistical computation and software development, it can also be used as a general matrix calculation toolbox with comparable benchmark results to GNU Octave and its proprietary counterpart, MATLAB.

Packages
The capabilities of R are extended through user-submitted packages, which allow additional statistical techniques, graphical devices, as well as programming interfaces and import/export capabilities to many external data formats. These packages are devloped in R, LaTeX, and often C and Fortran. A core set of packages are included with the installation of R, with over 800 more available at the Comprehensive R Archive Network.

Development
The bioinformatics community has seeded a successful effort to use R for the analysis of data from molecular biology laboratories. The bioconductor project, which started in the fall of 2001, provides R packages for the analysis of genomic data, such as Affymetrix and cDNA microarray object-oriented data handling and analysis tools.

The Gnumeric developers have cooperated with the R project to improve the accuracy of Gnumeric.

Productivity tools
There are several graphical user interfaces for R, including JGR, RKWard, SciViews-R and Rcmdr.

Many editors have specialised modes for R, including:


 * ConTEXT
 * Emacs (Emacs Speaks Statistics)
 * jEdit
 * Kate
 * Syn
 * TextMate
 * Tinn-R
 * Vim


 * Bluefish
 * An R plug-in for the Eclipse IDE framework.
 * WinEdt with R Package RWinEdt

R functionality has been made accessible from the Python programming language by the RPy interface package.

CRAN
R and user-submitted packages are commonly distributed through CRAN, which is an acronym for the Comprehensive R Archive Network. There are over 60 CRAN mirrors world-wide, with the head-node (http://cran.r-project.org/) located in Vienna, Austria.

R newsletter
A free newsletter is released online two to three times a year featuring statistical computing and development articles that might be of interest to both users and developers of R. It has been in press since January 2001.

References, Tutorials

 * The official R documentation http://cran.r-project.org/manuals.html
 * The R Wiki http://wiki.r-project.org/rwiki/doku.php
 * What documentaion exists for R? http://cran.r-project.org/doc/FAQ/R-FAQ.html#What-documentation-exists-for-R_003f
 * "Implementing References in R" -- and how to implement OOD http://www.maths.lth.se/help/R/ImplementingReferences/
 * List of Manuals, Guides: http://cran.r-project.org/other-docs.html

Packages for Making R More User Friendly

 * The Zelig Project, which bundles various tests and simplifies analysis in R http://gking.harvard.edu/zelig/
 * Includes "WhatIf", a program for evaluating Counterfactuals
 * Includes Amelia, a program for filling in Missing Data
 * R-Commander, A GUI front end to R http://socserv.mcmaster.ca/jfox/Misc/Rcmdr/
 * Rmetrics, a package for financial statistics, including many basic useful stats functions (kurtosis, etc) http://www.itp.phys.ethz.ch/econophysics/R/

Extensions

 * Object-Oriented Design and Programming
 * Object Oriented Programming with Standard R's S4 Classes http://www.stat.auckland.ac.nz/S-Workshop/Gentleman/S4Objects.pdf
 * R.oo http://cran.r-project.org/src/contrib/Descriptions/R.oo.html
 * Proto Package http://cran.r-project.org/doc/packages/proto.pdf
 * OmegaHat's OOP Package http://www.omegahat.org/OOP/
 * http://cran.r-project.org/doc/Rnews/Rnews_2001-3.pdf
 * Social Network Analysis
 * See Carter Butts's package, http://cran.r-project.org/src/contrib/Descriptions/sna.html
 * Skewness, Kurtosis: see the "moments" package -- http://cran.r-project.org/src/contrib/Descriptions/moments.html

Specific Topics

 * Marginal Effects with Logit (Probit, etc) -- use the "effects" package, http://finzi.psych.upenn.edu/R/library/effects/html/effect.html
 * Kolmogorov-Smirnov test to check for identical datasets (data distributions) -- ks.test (package:stats).  See http://www.physics.csbsju.edu/stats/KS-test.html for a description of the test.
 * Testing for Similarity of Two Lists
 * Spearman Rank Correlation Coefficients (SRCC)
 * SRCC reports a "rho" value, which is the correlation of the ranks, and a p-value, which represent the chance of observing the given rank correlation in unrelated lists.
 * Kolmogorov-Smirnov test: test to check for identical datasets (data distributions)
 * This is a Boolean test, and is not appropriate for more nuanced comparisions of ranked lists. In that case, the Spearman Rank Correlation Coefficients measures are more common.
 * Understanding the shape of a probability distribution
 * Skewness and Kurtosis, can be used to measure the asymmetry and width/skinniness of a distribution.
 * For background, they are the third and fourth normalized central moments of the distribution -- http://en.wikipedia.org/wiki/Moment_%28mathematics%29.
 * In Excel, use the functions skew and kurt
 * In R, use the functions in the "moments" package -- http://cran.r-project.org/src/contrib/Descriptions/moments.html