- SPSS 16 will have a new Java interface that will be compatable with Windows XP and Vista equipped PCs as well as Intel processor equipped Macs that meet the "hardware requirements" for this software. Please note I am being vague here to CYA.
- Apple and PC versions of will be at the same level, but some functionality that is dependent on Microsoft Windows technology will not be available on the Mac version. It is not clear SPSS 16 will be able to, or be certified to, run on the upcoming Mac OS X 10.5 "Leopard" that has not yet been released by Apple.
- Data files should remain backward compatable with previous versions. This new version will have more Unicode functions and a Unicode mode, so folks working and sharing information with downlevel (pre SPSS 16) users will need to be sure that data files are not saved in a format that includes these features.
- SPSS 16 output and modules will not be backward compatable. The new Java interface makes this even harder to achieve.
- SPSS 16 will support R algorithms. R is an open-source language and environment for statistical computing and graphics. R is similar to the S language and environment. There are some important differences, but much code written for S runs unaltered under R.
- SPSS 16 will reportedly feature powerful statistics, including a new Neural Networks add-on module, a new Partial Least Squares algorithm, a new Cox Regression for Complex Samples module, support for algorithms written in R and improvements to Generalized Linear Models and General Estimating Equations.
- SPSS 16 will reportedly feature Unicode support, import/export of Excel 2007 data, and an improved data editor.
- SPSS 16.0 will reportedly have improved programmability (more Python access.)
- SPSS 16 will reportedly feature more integration with SPSS’s other products (Predictive Enterprise Services).
- The next version of Amos will be Amos 16 to bring Amos version numbers in line with SPSS.
Monday, July 23, 2007
About upcoming version of SPSS
What I know so far about new SPSS 16 features: