All releases of SOFA Statistics
Release Notes: Support for inconsistent data and missing values was improved. The user is informed what happens to files being imported. The user has the option of halting a large raw data table report. CSV importing now asks the user if a file has a header and offers to clean up files with mixed line separators. New projects have the default SOFA database preconfigured ready to save tables to. A useful message is now returned if an SQLite table fails because of non-numeric values (in a purportedly numeric field). Users are given the opportunity to pull out of opening a large data table.
Release Notes: The installation options on Windows were made more flexible. For example, you can install it to a drive other than C:\. Support for international text and Unicode was improved in project, variable details, HTML report files, and CSS files. Interface behavior when configuring a project was improved. Better feedback is given when there are errors with missing or malformed files. A version of SOFA Statistics in the Galician language now works on Windows.
Release Notes: A major bug preventing interaction with data on Windows Vista and Windows 7 was fixed. Support for international text and Unicode was improved. Better feedback is given when there are errors saving data to database tables. There is now a version of SOFA Statistics in the Galician language.
Release Notes: Users can now view the design of tables in the default SOFA database. A more netbook-friendly design of the projects form is used. Miscellaneous improvements were made to the interface, especially when selecting data.
Release Notes: This is a significant maintenance release. The process of creating new tables directly into SOFA Statistics has been significantly improved. Numerous interface bugs affecting settings tables have been fixed.
Release Notes: Users are now able to add data directly to SOFA Statistics by configuring new tables in the default SQLite database and adding data directly to them. An important bug was fixed for PostgreSQL when making report tables.
Release Notes: Dialogs for making report tables and for configuring statistical tests now have close buttons in the bottom right like elsewhere. Other minor UI improvements were made. Important bugs were fixed for PostgreSQL and MS Access and MS SQL Server.
Release Notes: This release adds support for PostgreSQL databases, gives each item of output a preceding display line and a description of its data source (database and table) and when it was created, improves the layout of exported scripts, adds unit tests for the main statistical algorithms, and better handles timestamp and autonumber fields in data entry/editing.
Release Notes: ANOVA now has the option of precision or speed. Precision passes the hardest NIST test and is the default. ANOVA displays more information in output to enable comparison with known results. HTML output can now display multiple styles for different tables. Importing now requires alphanumeric names for tables.
Release Notes: This release can explicitly set variables to Nominal, Ordinal, or Quantity. These settings are used to limit the variables displayed in various tests to those which are of the appropriate type. Pearson's Chi Square now has a contingency table with both observed and expected values. One-way ANOVA and Kruskal Wallis H now provide more information in the output (e.g., average rank per group). Variables can be configured from a right-click when running statistical tests. Statistical tests can be selected by double-clicking, and are sorted alphabetically to make direct selection faster.
