GNU R collection of recommended packages [metapackage]

 R is a system for statistical computation and graphics. It consists
 of a language plus a run-time environment with graphics, a debugger,
 access to certain system functions, and the ability to run programs
 stored in script files.
 .
 The design of R has been heavily influenced by two existing languages:
 Becker, Chambers & Wilks' S and Sussman's Scheme. Whereas the
 resulting language is very similar in appearance to S, the underlying
 implementation and semantics are derived from Scheme.
 .
 The core of R is an interpreted computer language which allows
 branching and looping as well as modular programming using functions.
 Most of the user-visible functions in R are written in R. It is
 possible for the user to interface to procedures written in the
 C, C++, or FORTRAN languages for efficiency, and many of R's core
 functions do so. The R distribution contains functionality for a
 large number of statistical procedures and underlying applied math
 computations. There is also a large set of functions which provide
 a flexible graphical environment for creating various kinds of data
 presentations.
 .
 Additionally, several thousand extension "packages" are available from
 CRAN, the Comprehensive R Archive Network, many also as Debian packages,
 named 'r-cran-<name>'.
 .
 This Debian package is now a metapackage that depends on a set of
 packages that are recommended by the upstream R core team as part of a
 complete R distribution, and distributed along with the source of R
 itself, as well as directly via the CRAN network of mirrors. This set
 comprises the following packages (listed in their upstream names):
  - KernSmooth: Functions for kernel smoothing for Wand & Jones (1995)
  - Matrix: Classes and methods for dense and sparse matrices and
    operations on them using Lapack and SuiteSparse
  - MASS, class, nnet and spatial: packages from Venables and Ripley,
    `Modern Applied Statistics with S' (4th edition).
  - boot: Bootstrap R (S-Plus) Functions from the book "Bootstrap Methods
    and Their Applications" by A.C. Davison and D.V. Hinkley (1997).
  - cluster: Functions for clustering (by Rousseeuw et al.)
  - codetools: Code analysis tools for R
  - foreign: Read data stored by Minitab, S, SAS, SPSS, Stata, ...
  - lattice: Implementation of Trellis (R) graphics
  - mgcv: Multiple smoothing parameter estimation and GAMs by GCV
  - nlme: Linear and nonlinear mixed effects models
  - rpart: Recursive partitioning and regression trees
  - survival: Survival analysis, including penalised likelihood.