The following software is available at no charge, or nominal charge, for use in certain Statistics.com courses. Please note that the instructor may provide illustrations, examples, exercises and occasional pointers in a particular software package with which he/she is familiar, but his/her role is not to serve as a help desk for the software. Where possible, teaching assistants have provided supplemental examples in other packages, and will provide feedback on student work in a variety of software packages. Please check the course description page for details about how software is supported in each course.
IMPORTANT! For free trial versions, check the duration before installing, and don't install the software too early -- make sure that the free trial will run until the end of the course. For a 30-day trial, this generally means you should wait until at least the first week of the course. Once the course opens, you can review information about assignments and due dates to be sure that your installation will carry you as long as needed.
MAC USER: Please note that, in most cases, statistical software differs in the capabilities that are available on the Mac, and, in some cases is not available at all on the Mac (or on the most recent Macs). If you are a Mac user, please check first to be sure that the software/capabilities you are interested in are available.
Data Desk is a user friendly statistical package with special facilities for exploration and visualization. Check the Data Desk web site - www.datadesk.com - for trial copies and more information about Data Desk.
Many people use the functionality provided in Excel's Analysis Toolpak for basic statistical analysis. If you are going to continue with more advanced statistics, you will need to purchase a statistical add-in for Excel, suited to your needs. Several Statistics.com courses in resampling and data mining use Excel add-ins.
IBM SPSS Statistics student software available online through several web sites. Please click here for options. If you are a student enrolled in a university, you may obtain a student version of IBM SPSS Statistics from SPSS.
JMP is an easy-to-use data analysis and graphics tool from SAS. JMP provides a broad collection of statistics and graphics tools, from basic statistics to DOE to Data Mining and is available for Windows, Macintosh and Linux operating systems. JMP also integrates with SAS providing an intuitive interface to SAS' extensive library and enterprise data. You can download a 30-day evaluation copy of JMP here. This software will be supported by our teaching assistants beginning in the second quarter of 2007.
A free 30 day trial version of this software (version 15) is available to students enrolled in certain courses at statistics.com. MINITAB is a general statistical and graphical analysis package. It can do various general analyses including time series. To download the 30 day trial version of Minitab 15, click here and carefully follow the on screen instructions. For more information about MINITAB, visit the MINITAB website:
www.minitab.com . This software is supported by our teaching assistants.
This software is free and can be obtained from the R Project website. It does basic statistics, resampling, regression, logistic regression, GLM and GEE (this list includes available user-written routines). To obtain a free copy or to receive more information about R visit the R Project website:
The University Edition of SAS is available free of charge at the following location:
Students will need to create a free account with SAS in order to download the software. The University Edition of SAS is provided as a Virtual Machine in either VirtualBox (ova) format or in a format suitable for VMWare products. A virtual machine is a file or folder that contains an entire computer with operating system and program in software. A virtual machine player is needed to access the SAS virtual machine. Two recommended virtual machine players are Oracle's VirtualBox (runs on Windows, Mac or Linux) and VMWare's VMWare Player (runs on Windows and Linux). Both are free.
A trial copy of Stata is available for use in all courses. It does standard statistics, resampling, time series, regression, logistic regression, GLM and GEE. To request the trial copy, email email@example.com and inform them that you are taking a course with Statistics.com and tell them which of our courses you are taking. Stata licenses are no longer platform specific and will run on all supported platforms of Stata, including Windows, Mac, and Unix varieties. Stata is available as a download, so participants can choose electronic delivery (for no charge) or pay only a shipping charge to receive an installation DVD. For more information about Stata, visit the Stata Corp website: www.stata.com
Statistical process control, quality control, design of experiment, simulation, statistics, graphics and data management functionality are available in a free 30-day trial of STATISTICA. This software trial is only for installation on a personal computer. Download the trial:
StatCrunch is an online statistical software that allows users to perform complex analyses, share data sets, and generate compelling reports of their data. Interactive graphics help users understand statistical concepts and are available for export to enrich reports with visual representations of data.
There is a nominal fee for students. Because it is web-based, the software can be accessed anywhere.
For more information, visit the website at www.statcrunch.com.
STATGRAPHICS is an easy-to-learn, easy-to-use personal computer software package designed for experts and non-experts alike. It combines a broad range of statistical procedures with interactive graphics. A 30-day trial copy of STATGRAPHICS Centurion for Windows is available at statgraphics.co. A free copy of STATGRAPHICS Online can be accessed by Windows, Mac or Linux users at www.statgraphicsonline.com using any web browser.
Python is an extremely popular programming language that is relatively simple to learn. However, the language is also extremely powerful. Python is already a major language in scientific programming and data analysis and its popularity is increasing. One of the most interesting aspects of Python is that it can be used interactively while your program is running. This makes Python extremely useful for data analysis. Python has a large and growing community of online users, numerous online and textbook tutorials and a wealth of add-on modules that help make Python a true 'Swiss Army Knife' of programming languages! Best of all, Python is absolutely free and can be downloaded from http://www.python.org or if you want a more complete Python package with a plethora of modules installed, you can visit http://www.enthought.com or https://code.google.com/p/pythonxy/
With the advent of distributed computation techniques, the analysis of data sets far larger than the capacity of previous generations of computers is now possible. The release of Apache Hadoop in 2005 facilitated this new technology. Hadoop is an open source project with two major components: a distributed file system, which allows for efficient data storage and retrieval and MapReduce, which provides computations. Hadoop has become nearly synonymous with 'Big Data' and you can view more information and download Hadoop at the following link: http://hadoop.apache.org
Comprehensive Meta-Analysis is a software package that helps you summarize and reach conclusions from multiple studies on the same subject. Registered participants in our course "Meta Analysis" will be given access to a copy of Comprehensive Meta Analysis software in the first lesson. For more information about Comprehensive Meta-Analysis, visit: www.metaanalysis.com
Design-Expert(R) software from Stat-Ease, Inc. is a statistical package for Design of Experiments (DOE). With it you can not only screen for vital factors, but also locate ideal process settings for top performance and discover optimal product formulations. To download the free 45-day trial, you may click here. Students of statistics.com qualify for a discounted rate using this form. For more information on Design-Expert, please visit: www.statease.com/dx71descr.html
The following packages all perform specific functions in geostatistics, and are freeware. Crimestat was created for the analysis of crime location data. GeoDa is aimed at exploratory analysis of spatial data in general. LandSerf is for the visualization and analysis of surfaces. All three are referenced in the online course Spatial Statistical Analysis in Geographic Information Systems.
LEM freeware is for latent class, log multiplicative and event history models (it is also used in interpolating missing data values). It is available here.
LISREL software is used for structural equation modeling.
MINISTEP is a free version of WINSTEPS. It is used for Rasch Measurement and is free without a time restriction. To download MINISTEP, please click here. For more information about MINISTEP, visit the MINISTEP website:
Mplus is statistical modeling software, with special capabilities for the inclusion of continuous and categorical latent variables. A free demo is available here. For more information, visit the Mplus website:
nQuery Advisor + nTerim is commercial software for calculating sample size. It is available here - student pricing is available.
OpenEpi is free software for doing analysis of epidemiological data. It is available at www.openepi.com
PASS is used to find the sample size for a study. PASS lets you solve for power, sample size, effect size, and alpha level. PASS website: http://www.ncss.com/software/pass/
Power and Precision
A free 60 day version of this software is available to students enrolled in certain statistics.com courses. It has the ability to do power and sample size analysis. Registered participants in statistics.com's "Sample Size and Power" course will receive information at the beginning of the course on how to obtain a licensed copy for the duration of the course. For more information about Power and Precision visit the Power and Precision website:
A free one year license of Resampling Stats is provided for use in Statistics.com courses; first download the trial software from the site noted below, then request a one year license at the beginning of the course. Resampling Stats does resampling (bootstrapping, permutation tests). For more information about Resampling Stats visit the Resampling Stats website:
With Compumine Rule Discovery System it is easy to create decision trees, rule sets, and robust ensemble models that help you to discover important segments and valuable relationships in your data, and to make reliable predictions. An evaluation version of Rule Discovery System can be freely downloaded from Compumine's web page.
Spotfire is a visualization software. See spotfire.tibco.comStatXact
A 30 day trial license of StatXact is available from Cytel. StatXact performs exact nonparametric analysis, exact analysis for categorical data, and exact sample size and power. To download your trial copy, click here and follow the instructions provided by Cytel. For more information on StatXact, visit the StatXact website:
Tableau is a visualization software. See www.tableausoftware.com
Weka is an open source software program containing tools for data pre-processing, classification, regression, clustering, association rules, and visualization. You can run it on a Windows PC. It requires Java 1.4 or later. WEKA is a freeware program, and is available here.
WINBUGS is free software for Bayesian Markov Chain Monte Carlo (MCMC). It is available here.
WINSTEPS is software that does Rasch analysis. Purchase it here - http://www.winsteps.com/winsteps.htm . See "MINISTEP" (above) for limited evaluation version of WINSTEPS. For more information on WINSTEPS or MINISTEP please visit the WINSTEPS homepage.
This Excel add-in does multiple linear regression and logistic regression (both with variable subset selection), neural nets, CART, k-nearest neighbor, discriminant analysis, Bayesian classifier, principal components analysis, hierarchical and k-means clustering, association rules, time series, partitioning, and sampling. To obtain a 60 day trial for use with Statistics.com's data mining courses, visit the Frontline Systems XLMiner website , download the trial version, and request a key from Solver.com to unlock it for 60 days (be sure to specify which Statistics.com course you are taking).