SPSS Statistics features

Talk to us

For understanding licensing options: Subscription vs Perpetual, Base packs & addons

SPSS Statistics modules vs packages mapping

Depending on the license / subscription type opted, different combinations of modules (modules = set of features) are available in different packages. The mapping is as follows:

SPSS Statistics ModulesWhich package(s) includes the module?
Subscription PackagesPerpetual / Term License Packages
Data access and managementBase PackageBase, Standard, Professional, Premium
Data preparation
Help features
Data editor enhancements
Extended programmability
Multithreaded algorithms
Custom tablesAdd-on: Custom tables and advanced statisticsStandard, Professional, Premium
Advanced statistics
Complex samples (CS)Add-on: Complex sampling and testingPremium Package
Exact tests
CategoriesProfessional, Premium
Missing values
ConjointPremium Package
Decision treesAdd-on: Forecasting and decision treesProfessional, Premium
Neural networksPremium
Direct marketing
AMOS (Structural Equation Modeling)Not available

SPSS Statistics features list

The exhaustive list of features as of July 2022, grouped into modules is as follows:

Data access and management

  • Compare two data files for compatibility
  • Data prep features: Define Variable Properties tool; Copy Data Properties tool, Visual Bander, Identify Duplicate Cases; Date/Time wizard
  • Data Restructure wizard: Single record to multiple records, Multiple records to single record
  • Direct Excel data access
  • Easier importing from Excel and CSV
  • Export data to SAS and current versions of Excel
  • Export/insert to Database wizard
  • Import data from IBM Cognos® Business Intelligence
  • Import/export to/from Dimensions
  • Import Stata files (until V14)
  • Long variable names
  • Longer value labels
  • Multiple datasets can be run in one SPSS session
  • ODBC Capture—DataDirect drivers
  • OLE DB data access
  • Password protection
  • SAS 7/8/9 data files including compressed files)
  • Text wizard
  • Unicode support
  • Very long text strings

Data preparation

  • Automated data preparation—enhanced modelviewer for automated data preparation
  • Validate data—streamline the process of validatingdata before analyzing it
  • Anomaly detection—identify unusual cases in amultivariate setting
  • Optimal binning


  • Auto and cross correlation graphs
  • Basic graphs
  • Mapping (geospatial analysis)
  • Chart gallery
  • Chart options
  • Chart Builder UI for commonly used charts
  • Charts for multiple response variables
  • Graphics Production Language for custom charts
  • Interactive graphs-scriptable
  • Overlay and dual Y charts
  • Panelled charts
  • ROC analysis
  • Time series charts
  • Relationship map


  • Case summaries
  • Style output
  • Conditional formatting
  • Codebook
  • Export charts as Microsoft Graphic Object
  • Export model as XML to Smart Score
  • Export to PDF
  • Export to Word/Excel/PowerPoint
  • HTML output

Help features

  • Application examples
  • Index
  • Tutorial
  • Extensions
  • Search

Data editor enhancements

  • Custom attributes for user-defined metadata
  • Spell checker
  • Splitter controls
  • Variable sets for wide data
  • Variable icons
  • Optimal binning
  • Improved performance for large pivot tables
  • OLAP cubes/pivot tables
  • Output management system
  • Output scripting
  • Reports summaries in rows and columns
  • Search and replace
  • Smart devices (tablets and phones)
  • Table to graph conversion
  • Web reports

Extended programmability

  • Custom UI builder enhancements (work seamlessly with Python and R and can be used in IBM SPSS Modeler)
  • New Extensions hub
  • Custom dialog builder for Extensions
  • Flow control or syntax jobs
  • Partial least squares regression
  • Python, .NET and Java for front-end scripting
  • SPSS equivalent of the SAS DATA STEP
  • Support for R algorithms and graphics
  • User-defined procedures


  • ANOVA (in syntax only)
  • Automatic linear models
  • Cluster
  • Correlate—bivariate, partial, distances
  • Crosstabs–Define variable sets
  • Descriptive ratio statistics (PVA)
  • Descriptive
  • Discriminant analysis
  • Enhanced model viewer on two-step cluster and new nonparametric
  • Explore
  • Factor analysis
  • Frequencies
  • Geo-spatial analytics (STP and GSAR) (NEW!)
  • Improved performance for frequencies, crosstabs, descriptive
  • Power Analysis–(Statistics Base Server)
  • Matrix operations
  • Means
  • Monte Carlo simulation
  • Nearest neighbour analysis
  • New nonparametric tests
  • One way ANOVA
  • Ordinal regression (PLUM)
  • Ordinary least squares regression
  • Power Analysis
  • PP plots
  • QQ plots
  • Ratio
  • Reliability and ALSCAL multidimensional scaling
  • ROC curve
  • Compare ROC curves
  • Rule checking on secondary SPC charts
  • Summarize data
  • T tests: paired samples, independent samples, one-samples
  • Two-step cluster: categorical and continuous data/large data sets
  • Weighted Cohen’s kappa
  • Meta-analysis

Multithreaded algorithms

  • SORT


  • Sampling and pooling
  • Descriptive procedures that can be bootstrapped:
  • Correlations/nonparametric correlations
  • Crosstabs
  • Descriptives
  • Examine
  • Frequencies
  • Means
  • Partial correlations
  • T tests

Custom tables

  • 35 descriptive statistics
  • Drag and drop interface
  • Inferential statistics
  • Nested tables
  • Place totals in any row, column, or layer
  • Post computed categories
  • Effective base for weighted sample results
  • Put multiple variables into the same table
  • Significance tests on multiple response variables
  • Significance test in custom tables main table
  • Significance values for column means and column proportion tests
  • Specialized multiple response set tables
  • False discovery correction method for multiple comparisons
  • Syntax converter


  • Binary logistic regression
  • Logit response models
  • Multinomial logistic regression
  • Nonlinear regression
  • Probit response analysis
  • Two stage least squares
  • Weighted least squares
  • Quantile regression

Advanced statistics

  • Cox regression
  • General linear modelling (GLM):
  • General factorial
  • Multivariate (MANOVA)
  • Repeated measures
  • Variance components
  • Generalized linear models and generalized estimating equations
  • Gamma regression
  • Poisson regression
  • Negative binomial
  • GENLOG for loglinear and logit
  • Generalized linear mixed models (GLMM) (ordinal targets included)
  • Bayesian statistics
  • Hierarchical loglinear models
  • Kaplan Meier
  • Linear mixed-level models (aka hierarchical linear models)
  • Survival
  • Variance component estimation

Complex samples (CS)

  • CS Cox regression (also multithreaded)
  • CS descriptives
  • CS general linear models
  • CS logistic regression
  • CS ordinal regression
  • CS selection
  • CS tabulate
  • Sampling wizard/Analysis Plan wizard

Exact tests

  • Cochran’s Q test
  • Contingency coefficient
  • Cramer’s V
  • Fisher’s exact test
  • Somers’ D—symmetric and asymmetric
  • Friedman test
  • Gamma
  • Goodman and Kruskal tau
  • Jonckheere-Terpstra test
  • Kappa
  • Kendall’s coefficient of concordance
  • Kendall’s tau-b and tau-c
  • Kruskal-Wallis test
  • Likelihood ratio test
  • Linear-by-linear association test
  • Mann-Whitney U or Wilcoxon rank-sum W test
  • Marginal homogeneity test
  • McNemar test
  • Median test
  • Pearson Chi-square test
  • Pearson’s R
  • Phi
  • Sign test
  • Spearman correlation
  • Uncertainty coefficient—symmetric or asymmetric
  • Wald-Wolfowitz runs test
  • Wilcoxon signed-rank test


  • Correspondence analysis (ANACOR)
  • Principal components analysis for categorical data (CATPCA; replaces PRINCALS)
  • Ridge regression, lasso, elastic net (CATREG)
  • Nonlinear canonical correlation (OVERALS)
  • Multidimensional scaling for individual differences scaling with constraints (PROXSCAL)
  • Preference scaling (PREFSCAL; multidimensional unfolding)
  • Multiple correspondence analysis

Missing values

  • Data patterns table
  • Imputation with means estimation or regression
  • Listwise and pairwise statistics
  • Missing patterns table
  • Multiple imputation of missing data
  • Pooling


  • Estimate utilities (CONJOINT)
  • For conjoint analysis (ORTHOPLAN)

Decision trees

  • C&RT
  • Exhaustive CHAID


  • Auto regressive integrated moving average
  • Autoregression
  • Expert modeler exponential smoothing methods
  • Forecast multiple series (outcomes) at once
  • Temporal causal modelling
  • Seasonal decomposition
  • Spectral analysis

Neural networks

  • Multilayer perception
  • Radial basis function

Direct marketing

  • Cluster analysis
  • Contact profiling
  • Control package test
  • Propensity to purchase
  • RFM analysis: recency, frequency, monetary
  • Zip code response


AMOS (Structural Equation Modelling )

  • Bayesian estimation
  • Confirmatory factor analysis
  • Enter the model into a spreadsheet-like table (no programming)
  • Estimation of categorical and censored data
  • Latent class analysis
  • Non-graphical method of modeling
  • Structural equation modeling/path analysis
  • Specify path diagram using syntax