Categories - IBM SPSS Statistics

What SPSS Categories can do for your business

IBM® SPSS® Categories enables you to visualize and explore relationships in your data, helping you predict outcomes based on your statistical analysis. It uses categorical regression techniques to predict the values of nominal, ordinal or numerical outcome variables from a combination of numeric and ordered or unordered categorical predictor variables. The software features statistical procedures such as predictive analysis, statistical learning, perceptual mapping and preference scaling.

This module is included in the IBM® SPSS® Statistics Professional edition for traditional license use and as part of the IBM® SPSS® Complex Sampling and Testing add-on for subscription plans.

Feature spotlights

Analyze differences between categories

Use SPSS Categories to conduct correspondence analysis, making it easier to visualize and analyze differences between categories.

Incorporate supplementary information

Incorporate supplementary information by defining custom attributes for variables. This enables you to add additional context or metadata not captured by standard labels, measurement values or missing values. These attributes can store further information, such as descriptive notes, units of measurement or coding schemes, providing more context for data analysis.

Uncover associations and relationships

Use symmetrical normalization to produce a biplot so you can better see associations.

Easily work with categorical data

Analyze and interpret your multivariate data and its relationships more effectively through in-depth data analysis. For example, understand which consumer characteristics are most closely associated with your product or brand in your dataset, or compare customer perceptions of your products with those offered by you or your competitors.

Use categorical regression procedures

Predict the values of a nominal, ordinal or numerical outcome variable from a combination of numeric and ordered or unordered categorical predictor variables. Use regression with optimal scaling to describe, for example, how job satisfaction can be predicted from job category, geographic region and the amount of work-related travel.

Take advantage of optimal scaling

Quantify variables so that the multiple R is maximized. Optimal scaling may be applied to numeric variables when residuals are nonnormal or when predictor variables are not linearly related to the outcome variable. Regularization methods such as ridge regression, lasso and elastic net can improve prediction accuracy by stabilizing the parameter estimates.

Present your results clearly using perceptual maps

Use dimension-reduction techniques to see relationships in your data. Summary charts display similar variables or categories to provide you with insight into relationships among more than 2 variables.

Get these optimal scaling and dimension reduction techniques

Techniques include correspondence analysis (CORRESPONDENCE), categorical regression (CATREG), multiple correspondence analysis (MULTIPLE CORRESPONDENCE), CATPCA, nonlinear canonical correlation (OVERALS), proximity scaling (PROXSCAL) and preference scaling (PREFSCAL).

Technical details

Software requirements

For on-premises: purchase the Professional edition.
For subscription plans: purchase the Complex Sampling and Testing add-on.

See a complete list of software requirements

Hardware requirements

Processor: 2 GHz or faster
Display: 1024x768 or higher
Memory: 4 GB of RAM required, 8 GB of RAM or more recommended
Disk space: 2 GB or more

See a complete list of hardware requirements

Take the next step

Experience the intuitive interface and robust features at no cost.

Try SPSS Statistics at no cost

See pricing options

More ways to explore

Documentation

Community