While this wiki is all about SPSS, many of the contributors and users of the site look forward to a day where a reliable and adaptable [open source] [GUI] general statistical package is available to replace it. There are a number of open source solutions available for particular purposes, but the two general purpose front-runners for the title are OpenStat4 (http://www.statprograms4u.com ) and R GUI (http://www.sciviews.org/_rgui/).
PSPP PSPP is a free replacement for SPSS. Nearly all SPSS syntax will work with PSPP and the windows, the dialogs and the output reports are almost identical. Some statistical procedures are not yet supported, but these are under development. Despite that, PSPP is in many instances a viable Free alternative to SPSS. Users who are familiar with SPSS, but don't want to pay the high prices, can download PSPP at no cost.
Like spss, early versions had only a command line interface, however today it is a fully featured system with its own language processor, database engine and windowing system. The current version can perform anova, t-test, factor analysis, non-parametric tests, and all the normal spss data manipulation functions. There are versions available for both Windows and GNU/Linux.
gretl is a cross-platform software package for econometric analysis, written in the C programming language.
R (GUI Project)Edit
R can open an SPSS file (after loading 'foreign' package) and can do more statistics than SPSS. It does have a fairly steep learning curve though.
DataMelt (DMelt) Edit
DaMelt is a Java-based statistical software with support of Python, Groovy, Ruby, Octave/Matlab and BeanShell scripting. The code can be written in Java and deployed as an application. It has about 400 examples and extensive manual. Although the program has a wide community support, the main developer is Dr.S.Chekanov
OpenStat (latest release Dec 2013) is developed by Bill Miller and has a similar appearing interface to SPSS. It features a wide range of statistical tests including paramteric and non-parametric versions of ANOVA, MANOVA, regression,correlation tests and mulitvariate analysis (component analysis, factor analysis and cronbach's alpha as well as others). Openstat accepts data in text, binary, OS4 or Epidata rec format. Openstat also features additional tests for business use such as statistical process control and financial analysis. The software generates a wide array of charts such as boxplot and multifactor scatter plots but the axes are not editable limiting the functionality of the charts somewhat. In summary this software is stable, easy to use and has a comprehensive array of analyses.
PAST is a free, easy-to-use data analysis package originally aimed at paleontology but now also popular in many other fields.
SOFA is a statistics, analysis, and reporting program with an emphasis on ease of use, learn as you go, and beautiful output. SOFA is very easy to use and has helpful tips for beginners on formatting data and selecting the appropriate statistical analysis. Data is accepted in CSV, excel, openoffice and google doc format. The software will connect directly to MS Access or SQL databases. Data manipulation is limited and the software does not have a full range of complex analyses but the software is ideal for students and anyone who does only occasional analyses. Creates attractive charts but axes and other features can't be edited. Ideal for beginners.
Sage Notebook Use Sage, Python, R, Octave, and most other mathematical software with any web browser.