What's new in IBM SPSS Statistics

Proximity mapping

Proximity mapping is a visualization technique that is used to reduce the dimensionality of multivariate data and to display relationships among objects (cases, items, or other entities) in a spatial configuration. It supports multiple proximity sources, incorporates additional variables (attributes and properties), and offers a wide range of transformation and restriction options. These features make PROXMAP a powerful tool for exploring multivariate structure and integrating diverse types of data into a unified spatial representation.

You can access this feature from the menu: Analyze > Mapping > Proximity Mapping to run the procedure.

Distance Correlation

Distance Correlation is a versatile metric that detects any form of statistical dependence between variables (linear or nonlinear). It addresses the limitations of analyzing real-world data that often exhibits nonlinear and complex dependencies.

You can access this feature from the menu: Analyze > Correlate > Distance Correlation.

Time series filtering

Time series filtering is a vital technique in econometrics and time series analysis, often employed to decompose a time series into trend and cyclical components. This is especially important in macroeconomics and finance, where identifying business-cycle fluctuations or long-term economic trends is essential.

Time Series Filters (TSF) is added as an extension procedure with Python plug-in. Search and install the extension Time Series Filters from extension hub (Extensions > Extension hub). You can access this feature from the menu after installing the extension: Analyze > Forecasting > Time Series Filters (TSF).

Conditional Inference Tree

The Conditional Inference Tree procedure estimates classification and regression trees, by using a unified framework for conditional inference or permutation tests. It provides more stable trees with reduced chances of overfitting. The two types of trees that are provided by this procedure are conditional inference trees and model-based trees.

Conditional Inference Tree is added as an extension procedure with R plug-in. Search and install the extension Conditional Inference Tree from extension hub (Extensions > Extension hub). You can access this feature from the menu after installing the extension: Analyze > Classify > Conditional Inference Tree.

STATS EARTH

STATS EARTH uses the MARS algorithm to perform regression analysis to detect nonlinearities and interactions. This is added as an extension procedure with R plug-in. Search and install the extension Multiple Adaptive Regression Splines from extension hub (Extensions > Extension hub).

You can access this feature from the menu after installing the extension: Analyze > Generalized Linear Models > Multiple Adaptive Regression Splines.

Curated help

Curated Help is a feature that analyzes the output of a procedure and provides a summary of key findings. For IBM SPSS Statistics 31, Curated Help is available for the following procedures.

• Bivariate Correlations (Analyze > Correlate > Bivariate)
• Partial Correlation (Analyze > Correlate > Partial)
• Distances (Analyze > Correlate > Distances)
• Canonical Correlation (Analyze > Correlate > Canonical Correlation)
• Correlation in Linear Regression (Analyze > Regression > Linear)

See Curated Help.

Enhancements

Chi Square

Added a direct option to include Chi Square test of independence under the Analyze menu. A new command syntax, CHISQUARE INDEPENDENCE is also designed to run this procedure from Syntax Editor.

The Chi Square test tabulates a variable into categories and computes a chi-square statistic. The chi-squared test is a statistical hypothesis test that is used to determine whether a significant association exists between two categorical variables. The test evaluates whether the observed frequencies in the data differ from the expected frequencies under the null hypothesis, which assumes no association between the variables.

Go to Analyze > Descriptive Statistics > ChiSquare.

T-Test UI enhancement

An optional control is added to select Homogeneity of variance test when you run the procedure for Independent-Samples T-Test (Analyze > Compare Means > Independent-Samples T Test). With the new control, you can choose to include the results for the Levene statistic in your output.

Coefficient of variation

Implemented a new option to calculate coefficient of variation in the following procedures. The output tables for these procedures display the values for coefficient of variation in percentages.

• Go to Analyze > Descriptive Statistics > Frequencies. Click Statistics. Under Dispersion, a checkbox that indicates the coefficient of variation, CV is added.
• Go to Analyze > Descriptive Statistics > Descriptives. Click Options. Under Dispersion, a checkbox that indicates the coefficient of variation, CV is added.

The command syntaxes for the procedures now support the keyword CV in the /STATISTICS subcommand

In the following procedures, the label for coefficient of variation is replaced to CV to maintain consistency.

• Analyze > Complex Samples > Frequencies > Statistics
• Analyze > Complex Samples > Descriptives > Statistics
• Analyze > Complex Samples > Ratios > Statistics
• Analyze > Descriptive Statistics > Ratio > Statistics

Capability to search Design of Experiments from application search bar

Design of experiments (DOE) is a branch in statistics that deals with statistical methods to define relationships between input variables and output variables to understand the cause-and-effect relationship. They are powerful methodologies for improving processes, products, and systems by planning, conducting, and interpreting controlled tests.

The following are the features that are related to DOE in IBM SPSS Statistics. You can directly select the procedures from search bar in Dataview.

• Analyze > Compare Means and Proportions > One way ANOVA
• Analyze > Power Analysis > Means > One way ANOVA
• Analyze > General Linear Models > Univariate
• Analyze > General Linear Models > Multivariate
• Analyze > General Linear Models > Repeated Measures
• Analyze > General Linear Models > Variance Components
• Analyze > General Linear Models > Generalized Linear Models
• Analyze > General Linear Models > Generalized Estimating Equations
• Analyze > Mixed Models > Linear
• Analyze > Loglinear > General
• Analyze > Loglinear > Logit
• Analyze > Loglinear > Model Selection
• Analyze > Bayesian Statistics > One way ANOVA
• Analyze > Bayesian Statistics > One way Repeated Measures ANOVA

Type Design of Experiments or DOE in the search bar in Dataview. Procedures that are related to DOE appears in the search results. Click the procedure that you want to use on your dataset.

Enhanced dark mode

The following components are now compatible with dark mode.

• Table header and Tabbed pane background color in Data View
• Toolbar icons
• Tables and charts in the Output Viewer
• Charts in the Overview tab

Option to display only the correlations value in the Correlations table

In the Correlations table, you can opt to display only the correlations values and exclude other rows. Complete the following steps if you want to exclude the rows.

1. Run the Correlations procedure as usual from Analyze > Correlate. The Output viewer displays the correlations table.
2. If you want to remove the rows, Sig and N, click Utilities > Run Script.
3. The Run Script dialog displays the file IBM SPSS Statistics/Resources/Scripts/Reformat Correlations Table.py. Select the file and click Run.

The script automatically removes the other rows from the Correlation table, leaving only the correlation values.

If you want to restore the hidden rows, run the Correlations procedure again from Analyze > Correlate.

Customizing excel import

In the imported excel files (File > Import Data > Excel), you can choose to read variable names from the first row of the file or the first row of the defined range. Values that don't conform to variable naming rules are converted to valid variable names, and the original names are used as variable labels.

Select either Yes and provide the row number, or No for Are variable names included at the top of your file. See Reading Excel files.

Create output themes

With Output Theme, you can save your preferred styles for Pivot tables, Charts, and Viewer output into a single, reusable theme.

Go to Edit > Options and click Output tab.

In the Output Theme, select a theme from the list to apply its settings to your current output. You can Add, Change, or Remove output themes. If you want to reset the settings, choose Default from the list of themes. See Output options.

Charts support background images

You can fill background images in your charts. With the Fill Image option in the Properties Window dialog box, you can set and customize the background images of your charts.

You can export charts with background images in formats such as .png, .jpg, .svg, .bmp, and .tif. However, exporting charts with background images is not supported in the .eps format.

3-D charts do not support background images. See Fill and Border Style.

Mandatory input fields are highlighted in Power Analysis, Meta Analysis, and Reports

Mandatory input fields now appear as highlighted in red for all procedures coming under the following menu items. The enhancement aims to guide you effectively and makes you aware of the required inputs to run a procedure.

• Analyze > Power Analysis
• Analyze > Meta Analysis
• Analyze > Reports

Support New GB18030-2022 Glyphs (specific to Chinese Characters)

IBM SPSS Statistics now supports the display of Chinese characters from the new GB18030-2022 standard.

Integrated Cognos Analytical server with IBM SPSS Statistics

You can import data from Cognos Analytics to IBM SPSS Statistics. Go to File > Import Data > Cognos Business Intelligence. Data input works seamlessly in the modes, Data and Report

Redesigned the Activate IBM SPSS Statistics dialog

The user interface for activating IBM SPSS Statistics is improved to clearly differentiate between product activation by using IBM SPSS Statistics Digital license or by using an authorization code.

Default Column Width

You can set a default column width in Variable View and customize how wide each column appears. With this enhancement, you no longer need to manually resize columns every time you open a dataset. Your preferred column widths are saved and preserved across sessions.

Improved usability with option to view unlicensed features

You can now discover and learn more about unlicensed features in SPSS Statistics. These features are visible in the menu and indicated as locked feature icons in the menu. Click on an unlicensed menu item to know more about the feature and for guidance on how to upgrade your license to access the feature.

Added support for mnemonic shortcuts to tabbed pane tabs in Custom Dialog Builder (Windows only)

• You can now use Alt + [Mnemonic Key] to quickly switch between tabs.
• Mnemonic keys are visually indicated by an underscored character in the tab name.
• This enhancement is available exclusively on Windows.

This is applicable for Windows. You can create mnemonic key for tabs in Custom Dialog Builder.

Change common properties to resolve the difficulty in changing several variables

With Change Common Properties, you can change the following attributes of multiple variables at the same time.

• Width
• Decimal
• Align
• Measure
• Role

See Changing attribute values of multiple variables.

New option to display license details in Help menu

You can view your license details such as components, renewal dates, and version number from the Help menu. Click Help > Show License Detail.

Redesigned splash screen

Redesigned the splash screen for IBM SPSS Statistics and IBM SPSS Statistics Digital.

Status bar enhancements

Status bar in Data Editor now shows the count of selected cases when a filter is set.

Python upgrade

Python version is upgraded to 3.13.1.

Java Runtime Environment (JRE) and Java Development Kit (JDK) upgrades

Versions of JRE and JDK are upgraded to 17.0.13.0.

Standalone Data File Driver is deprecated

The standalone data file driver for IBM SPSS Statistics is deprecated.