What's new in version 25?

Welcome dialog

The welcome dialog has been updated as follows:

  • The Sample Files tab provides a convenient method for instantly opening an existing SPSS® Statistics sample file (*.sav).
  • The What's New section provides a brief description and illustration for each new feature.

Bayesian statistics

SPSS Statistics now supports Bayesian statistics. Bayesian inference is a method of statistical inference in which Baye's theorem is used to update the probability for a hypothesis as more information becomes available. The following Bayesian statistics are supported:

  • One Sample and Pair Sample t-tests
  • One Sample Binomial Proportion tests
  • One Sample Poisson Distribution Analysis
  • Related Samples
  • Independent Samples t-tests
  • Pairwise Correlation (Pearson)
  • Linear Regression
  • One-way ANOVA
  • Loglinear Regression

GLM Profile Plots

Profile plots (interaction plots) are useful when comparing marginal means in your model. A profile plot is a line plot in which each point indicates the estimated marginal mean of a dependent variable (adjusted for any covariates) at one level of a factor. The following Profile Plot enhancements are now available:

  • Error bars - You can include error bars that represent the confidence interval or a number of standard errors. The confidence interval is based on the significance level that is specified on the Options dialog.
  • Chart type - The chart can be a line chart or a bar chart.
  • Y axis starts at 0 - For line charts with all positive or all negative values, forces the Y axis to start at 0. Bar charts always start at (or include) 0.
  • Include reference line for grand mean - Includes a reference line that represents the overall grand mean.

For more information, see GLM Profile Plots.

GLM Repeated Measures

GLM Repeated Measures now support nested models in dialogs. Nesting for repeated measures is limited to between-subjects factors. There is no option to specify the within-subjects factor because the multivariate general linear model that is fitted, when you specify repeated measures, always includes all possible within-subjects factor interactions. For more information, see GLM Repeated Measures Model.

GLM Options

Parameter estimates with robust standard errors display a table of parameter estimates, along with robust or heteroskedasticity-consistent (HC) standard errors; and t statistics, significance values, and confidence intervals that use the robust standard errors. For more information, see GLM Options.

UNIANOVA procedure

The following enhancements are now available:

  • Print subcommand - White’s test for heteroscedasticity tests the null hypothesis that the variance of the errors does not depend on the values of the independent variables. For more information, see PRINT Subcommand (UNIANOVA command).
  • EMMEANS subcommand - EMMEANS was moved out of the Options dialog to a separate EMMEANS dialog, which makes the information easier to find.


The following enhancements are now available:

  • New feature for displaying the predicted values of the random effects parameters (empirical best linear unbiased predictions) in the output from the GENLINMIXED procedure. For more information, see Random Effects (generalized linear mixed models) and Random Effect Block (generalized linear mixed models).
  • New SOLUTION keyword on the RANDOM subcommand. The new keyword generates the new Empirical Best Linear Unbiased Predictions table for the set of random effects that are specified on the current RANDOM subcommand. For more information, see RANDOM Subcommand (GENLINMIXED command).
  • New options for specifying the covariance type in the GENLINMIXED procedure. In prior releases, options for handling time-based covariance assumed that the data is equally spaced in time. New options are now available that treat discrete time measurements as a spatial ordering and allow for going beyond the equally-spaced-in-time case. For more information, see Generalized linear mixed models.
  • New Pivot tables and charts system default output type for Generalized Linear Mixed Models and Nonparametric Tests. For more information, see Output options.

EMMEANS subcommand

The following enhancements are now available:

  • GLM, UNIANOVA, and MIXED procedures - When you specify a value at which to fix a covariate on the EMMEANS subcommand's WITH keyword, the specified numeric value is now reproduced exactly as it was entered (instead of the variable format determining the number of decimals).
  • UNIANOVA procedure - EMMEANS was moved out of the Options dialog to a separate EMMEANS dialog, which makes the information easier to find.

Chart Builder

The following enhancements are now available:

  • A new default template provides users options for creating charts with modern graphics. If you choose to retain the previous template styles, the legacy template (LegacyDefault.sgt) is available via the Use chart template file setting (Edit > Options > Chart > Chart Template or from the Chart Appearance tab in the Chart Builder interface).
  • Users can now filter chart data by selecting categorical variable values from the active dataset. In prior versions, the only mechanism for filtering categorical variable values was to include the variables as an aspect of the chart (such as paneling or clustering) and then exclude selected categories. Users can now simply drag-and-drop non-numeric variables into the new filter drop zone on the chart canvas, and then exclude selected categories.
  • Users who are new to charting in SPSS Statistics are able to quickly build charts (without guessing and verifying).
  • Chart properties can now be quickly edited and the results instantly seen. (Chart Preview and Element Properties)
  • Charts now update in real time as users build them. With a single mouse click, users are able to generate a scatterplot with a regression (without programming).
  • Chart titles are now automatically generated.
  • Statistics client users can copy their GGRAPH charts as either pictures or Microsoft Object Graphics.
  • By using predefined templates or custom color schemes, a single click can now change chart colors (without programming).
  • Users are provided a new Shades of Grey template (PublicationGray.sgt).

For more information, see Building Charts.


The Add Variables from [dataset/file name] dialog was improved by the inclusion of more descriptive text for the available merge methods and more intelligent default variable list assignments (particularly for key values merge methods). These enhancements allow users to more easily merge large datasets (> 1 million cases each). For more information, see Add Variables.

Syntax Editor

The following Syntax Editor enhancements are now available:

  • You can now duplicate one or more syntax lines. The Duplicate lines feature is available through the Edit menu, or by using the Ctrl+U keyboard shortcut.
  • You can now join lines in selected syntax lines (the selected lines are moved to a single line). The Join lines feature is available through the Edit menu, or by using the Ctrl+J keyboard shortcut.
  • You can now remove empty lines that are contained within selected syntax lines. The Remove empty lines feature is available through the Edit menu, or by using the Ctrl+M keyboard shortcut.
  • You can now move selected syntax lines up or down. The Move lines up and Move lines down features are available through the Edit menu, or by using the Alt+Up and Alt+Down keyboard shortcuts.
  • You can now activate and deactivate column edit mode. Column edit mode allows you to apply similar changes across multiple syntax lines. The Toggle column edit mode and Exit column edit mode features are available through the Edit menu, or by using the Ctrl+G and ESC keyboard shortcuts.
  • You can now trim leading and trailing spaces in selected syntax lines. The Trim leading spaces, Trim trailing spaces, and Trim leading and trailing spaces features are available through the Edit menu, or by using the Ctrl+L, Ctrl+T, and Ctrl+B keyboard shortcuts.
  • The Find and Replace dialog now recognizes /n as a newline character.

For more information, see Formatting Syntax

Improved Microsoft Office support

The following enhancements are now available:

  • You can now copy charts as Microsoft Graphic Objects, which allows you to manipulate charts in Microsoft Office. For more information, see Copying output into other applications.
  • Microsoft Excel data, that include variable names, can now be pasted directly into the Statistics Data Editor. Variable names are converted automatically, and the full variable names are stored as variable labels. The option is presented as the Paste with Variable Names right-click menu option.

    For more information, see Cutting, copying, and pasting data values.

  • Data can now be copied from the Statistics Data Editor with the options of no variables, variable names, or variable labels. The copy options are presented as the following right-click menu options:
    • Copy with variable names
    • Copy with variable labels

    For more information, see Cutting, copying, and pasting data values.

Output Viewer "Copy as" enhancement

You can now right-click a selected object in the Output Viewer and select Edit > Copy as to copy to the most popular formats (for example, All, Image, or Microsoft Office Graphic Object). Selecting Edit > Copy copies All.

Graph export

You can now export graphs as high resolution PDF files that are cropped to the size of the graphic. For more information, see Printing, saving, copying, and exporting graphs.

Accessibility enhancements for the visually impaired

Toolbar updates

The following enhancements are now available:

  • Infrequently used buttons are now automatically removed from the toolbar.
  • The Direct Marketing feature is now located under the Analyze menu (Analyze > Direct Marketing).
  • The new Go to Active Syntax Window and Go to Active Output Viewer toolbar buttons are now available.
  • With a single mouse click, users can now display the Customize Toolbar dialog.

Incremental Safenet licensing improvements

Online help

In prior releases, the online help system was installed alongside SPSS Statistics. The online help system is now contained within the IBM Knowledge Center. F1 help calls within the SPSS Statistics application now result in the associated help topics being opened in a separate web browser instance that links to the IBM Knowledge Center.

RFE Community

IBM Knowledge Center is now in the Request for Enhancement (RFE) Community, where IBM product users can make suggestions for improving our IBM KC application and its content. Besides opening and tracking new requests, users can also search existing requests, and comment on them as well. The RFE Community provides a great opportunity for users to interact more directly with the IBM KC and product development teams. For information about getting started with the RFT Community, see the Help tab. An IBMid and password is required to use any feature other than the Help tab.