General statistics packages and information

Well-respected library of free statistical software, from Carnegie Mellon University.
Scientific data processing packages
Extensive list of shareware and public domain scientific data processing, visualization, image analysis, plotting packages and libraries designed for use with Linux or other UNIX systems. (P)
R, and is associated archive network of Web servers CRAN, is a language and environment for statistical computing and graphics very similar to Bell Lab's S package. It operates under UNIX and Windows. It provides a wide variety of techniques including: generalized linear modelling, least-squares and maximum likelihood nonlinear modelling, statistical tests, time series analysis, multivariate classification and clustering, and a variety of praphical functions. C, C++ and Fortran code can be linked. P
Large mathematics library (about 900 modules) including random number generators, weighted spline and piecewise polynomial fitting, nonlinear least squares fitting (P)
Large subroutine library (about 170 modules) for probability and density distributions, line-printer plots (histograms, scatter), general statistical analysis, time series analysis, polynomial regression. (P)
NIST Core Math Library collection of subroutine libraries including BLAS, EISPACK, FISHPAK, FNLIB, FFTPACK, LINPACK and QUASPACK. Contains about 750 modules. Includes k-means and hierarchical cluster analyses, spine and piecewise polynomial fits, fast Fourier transforms, nonlinear weighted orthogonal distance regression, multivariate historgrams, maximum-likelihood mixture models, bivariate linear regression with measurement errors, and random number generators. (P)
Matlab and other resources
An extensive multidisciplinary collection of data analysis programs and toolboxes in Matlab, Mideva, Excel, C, C++, Fortran, Java, IDL and PVWave. These are provided by
Inexpensive ($17-$62) PC-based package with 220 statistical tests and routines. Includes descriptive statistics, ANOVA, parametric and nonparametric correlation and regression, 1- and 2-sample hypothesis testing, contingency tables with chi-square tets, many nonparametric tests, statistical distributions, and some specialized routines. (P)
Matlab econometrics toolbox
Matlab routines for: least-squares and simultaneous systems; limited-dependent variables (i.e. censored & truncated dta) regression; auto-regressive time-series estimation with forecasting; ridge, Theil-Goldberger, switching regimes, and robust regression; regression diagnostics (e.g. Belsley, Kuh Welsch, Cook-Weisberg); cointegration testing; statistical distributions; Bayesian Gibbs sampling estimation and MCMC convergence diagnostics; maximum-likelihood and Bayesian spatial modelling; and lots more. Produced by J. P. LeSage, Dept. of Economics, University of Toledo, with a 350-page manual. (P)
Powerful interactive statistical computing environmentwith statistical functions, graphics and visualization, dynamic linking of Fortran/C++ procedures, help files and tutorials with XWindows and Java interfaces. Built-in libraries include matrix operations, basic statistics, linear and LOWESS regression, principal components and factor analysis, 2- and 3-dimensional graphics, wavelets, generalized additive models, ARMA and nonlinear ARCH time series models, censored and truncated linear regression (Tobit models), errors-in-variables measurement error linear models, generalized linear models for non-linear and truncated problems, nonparametric single index models, kernel smoothing, spline regression, neural network regression and classification, wavelet transforms and regression. Platforms include Solaris 2 and Linux using X11 and Motif. Commercial package (P)
Comprehensive data analysis package for life scientists. Statistical portion includes descriptive statistics (means, variance, contingency tables), graphs (histograms, boxplots, scatter plots, Kaplan-Meier survival curves, graph editing), testing (test equality of means and variances [chi-squares, F-test, t-test, ANOVA, nonparametric tests [Kruskal-Wallis, Wilcoxon, Mann-Whitney, Friedman's, Cochran's Q., McNemar's Q., Ansari-Bradley, sign], correlation and ANCOVA, contingency table analysis, survival analysis, testing distributions [Shapiro-Wilk, Kolmogorov-Smirnov], survival analysis [Kaplan-Meier estimator, logrank, Gehan-Breslow and Taronw-Ware two-sample tests], probit analysis; linear and multiple regression, nonlinear modeling, logistic regression. Comprehensive on-line documentation and glossary. Commercial package (P)
UNIX utilities for numerical analysis and graphics including animation, rotations, Fourier transforms, data filtering. (P)
Data manipulation and analysis programs for UNIX and MS-DOS. Statistics includes 20 descriptive statistics for univariate distribution, analysis of variance, partial correlation and multiple regression, time series analysis with autocorrelation, rank statistics (Friedman, Wilcoxon, Spearman, Median Mann-Whitney, Kruskal-Wallis), and contingency tables. (P)
On-line introductory statistics courses & textbooks and Electronic statistics textbook
On-line textbook covering basic statistics, multivariate analysis, clustering and classification, data ining, experimental design, linear regression and nonlinear estimation, nonparametrics, quality control, survival analysis, time series and more.
Online statistical education
Extensive metasite listing on-line WWW and Java interactive services, textbooks, graphics, course materials, journals, teaching material, datasets, software, and more.
Econometric software
Large collection of commercial and public software used in econometrics including regression, time series analysis, Bayesian analyses, linear modeling, limited-dependent variables (i.e. censoring & truncation), optimization, and links to other metasites. From the Econometrics Journal online.
Comprehensive collection of links to statistical resources on the Internet, from the US Dept. of Agriculture. Includes software libraries, journals, departments and organizations, SAS/S+ software, forecasting and neural network information, and more.
Matlab toolboxes
Large collection of software libraries and links associated with the Matlab software. Topics include statistics, time serles, wavelets, neural networks, graphics and visualization, fitting and interpolation, filtering and astronommy. Less extensive lists are also available for Fortran, C/C++, MS Excel and Java resources at
Software Information Bank of iec ProGamma (SIByl)
Catalogue and distributor of several hundred packages for data analysis in the social and behavioral sciences. Includes structural regression modeling, multivariate analysis, survival analysis, bootstrap and jackknife analysis, general statistics and data handling.
Software for graphics and data analysis
Enormous list of free, shareware and commercial software packages, toolkits and libraries for visualization, image processing, data formats and compression, graphical interfaces. Emphasis on large 2- and 3-dimensional databases associated with geography, geophysics, oceanography, meteorology, and climate studies. Most are UNIX-based.
The following are large metasites for the fields of statistical pattern recognition, classification, neural networks, perceptrons, machine vision and learning, data mining, and image processing (including medical imaging)
Pattern Recognition Group, TU Delft;
TOOLDIAG (Brazil);
Computer vision software, Carnegie-Mellon;
Classification Society of North America;
Knowledge Discovery and data mining, Katholieke Univ; and
St@tServ Data Mining Software.
Statistics and Statistical Graphics Resources , Statistics on the Web, Univ. Florida, StatsNet and Claremont Grad Univ.
Metasites with several hundred links to Web resources on statistics including societies, journals, departments, on-ine courses and textbooks, commercial and public somain software packages, data visualization, on-line statistical analyses, databases, and more. and Univ. Koeln
Comprehensive lists of commercial statistical packages.
SciTech Computing
Reseller of a large collection (about 80) of commercial statistical packages, with pricing.
Fortran libraries
Collection of public domain libraries including BLAS, EISPACK, LAPACK, LINPACK. MINPACK, MUDPACK, SLATEC, TOMS, and others. A service of the Fortran Market.
Glossaries of statistical terms

Return to StatCodes homepage